1
|
Nazir M, Shakil S, Khurshid K. End-to-End Multi-task Learning Architecture for Brain Tumor Analysis with Uncertainty Estimation in MRI Images. J Imaging Inform Med 2024:10.1007/s10278-024-01009-w. [PMID: 38565728 DOI: 10.1007/s10278-024-01009-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Revised: 11/25/2023] [Accepted: 11/28/2023] [Indexed: 04/04/2024]
Abstract
Brain tumors are a threat to life for every other human being, be it adults or children. Gliomas are one of the deadliest brain tumors with an extremely difficult diagnosis. The reason is their complex and heterogenous structure which gives rise to subjective as well as objective errors. Their manual segmentation is a laborious task due to their complex structure and irregular appearance. To cater to all these issues, a lot of research has been done and is going on to develop AI-based solutions that can help doctors and radiologists in the effective diagnosis of gliomas with the least subjective and objective errors, but an end-to-end system is still missing. An all-in-one framework has been proposed in this research. The developed end-to-end multi-task learning (MTL) architecture with a feature attention module can classify, segment, and predict the overall survival of gliomas by leveraging task relationships between similar tasks. Uncertainty estimation has also been incorporated into the framework to enhance the confidence level of healthcare practitioners. Extensive experimentation was performed by using combinations of MRI sequences. Brain tumor segmentation (BraTS) challenge datasets of 2019 and 2020 were used for experimental purposes. Results of the best model with four sequences show 95.1% accuracy for classification, 86.3% dice score for segmentation, and a mean absolute error (MAE) of 456.59 for survival prediction on the test data. It is evident from the results that deep learning-based MTL models have the potential to automate the whole brain tumor analysis process and give efficient results with least inference time without human intervention. Uncertainty quantification confirms the idea that more data can improve the generalization ability and in turn can produce more accurate results with less uncertainty. The proposed model has the potential to be utilized in a clinical setup for the initial screening of glioma patients.
Collapse
Affiliation(s)
- Maria Nazir
- Medical Imaging and Diagnostics Lab, NCAI COMSATS University Islamabad, Islamabad, Pakistan.
- iVision Lab, Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan.
- BiCoNeS Lab, Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan.
| | - Sadia Shakil
- Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Khurram Khurshid
- iVision Lab, Department of Electrical Engineering, Institute of Space Technology, Islamabad, Pakistan
| |
Collapse
|
2
|
Kim DD, Chandra RS, Yang L, Wu J, Feng X, Atalay M, Bettegowda C, Jones C, Sair H, Liao WH, Zhu C, Zou B, Kazerooni AF, Nabavizadeh A, Jiao Z, Peng J, Bai HX. Active Learning in Brain Tumor Segmentation with Uncertainty Sampling and Annotation Redundancy Restriction. J Imaging Inform Med 2024:10.1007/s10278-024-01037-6. [PMID: 38514595 DOI: 10.1007/s10278-024-01037-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/29/2023] [Revised: 01/30/2024] [Accepted: 02/01/2024] [Indexed: 03/23/2024]
Abstract
Deep learning models have demonstrated great potential in medical imaging but are limited by the expensive, large volume of annotations required. To address this, we compared different active learning strategies by training models on subsets of the most informative images using real-world clinical datasets for brain tumor segmentation and proposing a framework that minimizes the data needed while maintaining performance. Then, 638 multi-institutional brain tumor magnetic resonance imaging scans were used to train three-dimensional U-net models and compare active learning strategies. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotating similar images were also considered. We determined the minimum data necessary to achieve performance equivalent to the model trained on the full dataset (α = 0.05). Bayesian approximation with dropout at training and testing showed results equivalent to that of the full data model (target) with around 30% of the training data needed by random query to achieve target performance (p = 0.018). Annotation redundancy restriction techniques can reduce the training data needed by random query to achieve target performance by 20%. We investigated various active learning strategies to minimize the annotation burden for three-dimensional brain tumor segmentation. Dropout uncertainty estimation achieved target performance with the least annotated data.
Collapse
Affiliation(s)
- Daniel D Kim
- Warren Alpert Medical School of Brown University, Providence, RI, USA
- Department of Diagnostic Imaging, Rhode Island Hospital, Providence, RI, USA
| | - Rajat S Chandra
- Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA
| | - Li Yang
- Department of Neurology, Second Xiangya Hospital, Central South University, Changsha, China
- Clinical Medical Research Center for Stroke Prevention and Treatment of Hunan Province, Department of Neurology, Second Xiangya Hospital, Central South University, Changsha, China
| | - Jing Wu
- Department of Radiology, Second Xiangya Hospital, Central South University, Changsha, China
| | - Xue Feng
- Biomedical Engineering, University of Virginia, Charlottesville, VA, USA
| | - Michael Atalay
- Warren Alpert Medical School of Brown University, Providence, RI, USA
- Department of Diagnostic Imaging, Rhode Island Hospital, Providence, RI, USA
| | - Chetan Bettegowda
- Department of Neurosurgery, Johns Hopkins University, Baltimore, MD, USA
| | - Craig Jones
- Department of Neurosurgery, Johns Hopkins University, Baltimore, MD, USA
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Haris Sair
- Department of Neurosurgery, Johns Hopkins University, Baltimore, MD, USA
| | - Wei-Hua Liao
- Department of Radiology, Xiangya Hospital, Central South University, Changsha, China
| | - Chengzhang Zhu
- College of Literature and Journalism, Central South University, Changsha, China
| | - Beiji Zou
- School of Computer Science and Engineering, Central South University, Changsha, China
| | - Anahita Fathi Kazerooni
- Center for Data-Driven Discovery in Biomedicine (D3b), Children's Hospital of Philadelphia, Philadelphia, PA, USA
- Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Ali Nabavizadeh
- Center for Data-Driven Discovery in Biomedicine (D3b), Children's Hospital of Philadelphia, Philadelphia, PA, USA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Zhicheng Jiao
- Warren Alpert Medical School of Brown University, Providence, RI, USA
- Department of Diagnostic Imaging, Rhode Island Hospital, Providence, RI, USA
| | - Jian Peng
- Department of Neurology, Second Xiangya Hospital, Central South University, Changsha, China.
- Clinical Medical Research Center for Stroke Prevention and Treatment of Hunan Province, Department of Neurology, Second Xiangya Hospital, Central South University, Changsha, China.
| | - Harrison X Bai
- Department of Neurosurgery, Johns Hopkins University, Baltimore, MD, USA
| |
Collapse
|
3
|
Chen Y, Yang Z, Shen C, Wang Z, Zhang Z, Qin Y, Wei X, Lu J, Liu Y, Zhang Y. Evidence-based uncertainty-aware semi-supervised medical image segmentation. Comput Biol Med 2024; 170:108004. [PMID: 38277924 DOI: 10.1016/j.compbiomed.2024.108004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Revised: 12/21/2023] [Accepted: 01/13/2024] [Indexed: 01/28/2024]
Abstract
Semi-Supervised Learning (SSL) has demonstrated great potential to reduce the dependence on a large set of annotated data, which is challenging to collect in clinical practice. One of the most important SSL methods is to generate pseudo labels from the unlabeled data using a network model trained with labeled data, which will inevitably introduce false pseudo labels into the training process and potentially jeopardize performance. To address this issue, uncertainty-aware methods have emerged as a promising solution and have gained considerable attention recently. However, current uncertainty-aware methods usually face the dilemma of balancing the additional computational cost, uncertainty estimation accuracy, and theoretical basis in a unified training paradigm. To address this issue, we propose to integrate the Dempster-Shafer Theory of Evidence (DST) into SSL-based medical image segmentation, dubbed EVidential Inference Learning (EVIL). EVIL performs as a novel consistency regularization-based training paradigm, which enforces consistency on predictions perturbed by two networks with different parameters to enhance generalization Additionally, EVIL provides a theoretically assured solution for precise uncertainty quantification within a single forward pass. By discarding highly unreliable pseudo labels after uncertainty estimation, trustworthy pseudo labels can be generated and incorporated into subsequent model training. The experimental results demonstrate that the proposed approach performs competitively when benchmarked against several state-of-the-art methods on public datasets, i.e., ACDC, MM-WHS, and MonuSeg. The code can be found at https://github.com/CYYukio/EVidential-Inference-Learning.
Collapse
Affiliation(s)
- Yingyu Chen
- College of Computer Science, Sichuan University, China; The Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University, China
| | - Ziyuan Yang
- College of Computer Science, Sichuan University, China
| | - Chenyu Shen
- College of Computer Science, Sichuan University, China
| | - Zhiwen Wang
- College of Computer Science, Sichuan University, China
| | | | - Yang Qin
- College of Computer Science, Sichuan University, China
| | - Xin Wei
- Department of Ophthalmology, West China Hospital, Sichuan University, China
| | - Jingfeng Lu
- School of Cyber Science and Engineering, Sichuan University, China
| | - Yan Liu
- College of Electrical Engineering, Sichuan University, China.
| | - Yi Zhang
- School of Cyber Science and Engineering, Sichuan University, China; The Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University, China
| |
Collapse
|
4
|
Heremans ERM, Seedat N, Buyse B, Testelmans D, van der Schaar M, De Vos M. U-PASS: An uncertainty-guided deep learning pipeline for automated sleep staging. Comput Biol Med 2024; 171:108205. [PMID: 38401452 DOI: 10.1016/j.compbiomed.2024.108205] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 02/16/2024] [Accepted: 02/20/2024] [Indexed: 02/26/2024]
Abstract
With the increasing prevalence of machine learning in critical fields like healthcare, ensuring the safety and reliability of these systems is crucial. Estimating uncertainty plays a vital role in enhancing reliability by identifying areas of high and low confidence and reducing the risk of errors. This study introduces U-PASS, a specialized human-centered machine learning pipeline tailored for clinical applications, which effectively communicates uncertainty to clinical experts and collaborates with them to improve predictions. U-PASS incorporates uncertainty estimation at every stage of the process, including data acquisition, training, and model deployment. Training is divided into a supervised pre-training step and a semi-supervised recording-wise finetuning step. We apply U-PASS to the challenging task of sleep staging and demonstrate that it systematically improves performance at every stage. By optimizing the training dataset, actively seeking feedback from domain experts for informative samples, and deferring the most uncertain samples to experts, U-PASS achieves an impressive expert-level accuracy of 85% on a challenging clinical dataset of elderly sleep apnea patients. This represents a significant improvement over the starting point at 75% accuracy. The largest improvement gain is due to the deferral of uncertain epochs to a sleep expert. U-PASS presents a promising AI approach to incorporating uncertainty estimation in machine learning pipelines, improving their reliability and unlocking their potential in clinical settings.
Collapse
Affiliation(s)
- Elisabeth R M Heremans
- KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium.
| | | | - Bertien Buyse
- UZ Leuven, Department of Pneumology, Herestraat 49, B-3000 Leuven, Belgium
| | - Dries Testelmans
- UZ Leuven, Department of Pneumology, Herestraat 49, B-3000 Leuven, Belgium
| | | | - Maarten De Vos
- KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium.
| |
Collapse
|
5
|
Lu S, Yan Z, Chen W, Cheng T, Zhang Z, Yang G. Dual consistency regularization with subjective logic for semi-supervised medical image segmentation. Comput Biol Med 2024; 170:107991. [PMID: 38242016 DOI: 10.1016/j.compbiomed.2024.107991] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 12/18/2023] [Accepted: 01/13/2024] [Indexed: 01/21/2024]
Abstract
Semi-supervised learning plays a vital role in computer vision tasks, particularly in medical image analysis. It significantly reduces the time and cost involved in labeling data. Current methods primarily focus on consistency regularization and the generation of pseudo labels. However, due to the model's poor awareness of unlabeled data, aforementioned methods may misguide the model. To alleviate this problem, we propose a dual consistency regularization with subjective logic for semi-supervised medical image segmentation. Specifically, we introduce subjective logic into our semi-supervised medical image segmentation task to estimate uncertainty, and based on the consistency hypothesis, we construct dual consistency regularization under weak and strong perturbations to guide the model's learning from unlabeled data. To evaluate the performance of the proposed method, we performed experiments on three widely used datasets: ACDC, LA, and Pancreas. Experiments show that the proposed method achieved improvement compared with other state-of-the-art (SOTA) methods.
Collapse
Affiliation(s)
- Shanfu Lu
- Perception Vision Medical Technologies Co., Ltd, Guangzhou, 510530, China.
| | - Ziye Yan
- Perception Vision Medical Technologies Co., Ltd, Guangzhou, 510530, China
| | - Wei Chen
- The radiotherapy department of second peoples' hospital, neijiang, 641000, China
| | - Tingting Cheng
- Department of Oncology, National Clinical Research Center for Geriatric Disorders and Xiangya Lung Cancer Center, Xiangya Hospital, Central South University, Changsha, 41000, China.
| | - Zijian Zhang
- Department of Oncology, National Clinical Research Center for Geriatric Disorders and Xiangya Lung Cancer Center, Xiangya Hospital, Central South University, Changsha, 41000, China.
| | - Guang Yang
- Bioengineering Department and Imperial-X, Imperial College London, London, UK; National Heart and Lung Institute, Imperial College London, London, UK; Cardiovascular Research Centre, Royal Brompton Hospital, London, UK; School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
| |
Collapse
|
6
|
Li X, Bellotti R, Meier G, Bachtiary B, Weber D, Lomax A, Buhmann J, Zhang Y. Uncertainty-aware MR-based CT synthesis for robust proton therapy planning of brain tumour. Radiother Oncol 2024; 191:110056. [PMID: 38104781 DOI: 10.1016/j.radonc.2023.110056] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 12/06/2023] [Accepted: 12/08/2023] [Indexed: 12/19/2023]
Abstract
BACKGROUND AND PURPOSE Deep learning techniques excel in MR-based CT synthesis, but missing uncertainty prediction limits its clinical use in proton therapy. We developed an uncertainty-aware framework and evaluated its efficiency in robust proton planning. MATERIALS AND METHODS A conditional generative-adversarial network was trained on 64 brain tumour patients with paired MR-CT images to generate synthetic CTs (sCT) from combined T1-T2 MRs of three orthogonal planes. A Bayesian neural network predicts Laplacian distributions for all voxels with parameters (μ, b). A robust proton plan was optimized using three sCTs of μ and μ±b. The dosimetric differences between the plan from sCT (sPlan) and the recalculated plan (rPlan) on planning CT (pCT) were quantified for each patient. The uncertainty-aware robust plan was compared to conventional robust (global ± 3 %) and non-robust plans. RESULTS In 8-fold cross-validation, sCT-pCT image differences (Mean-Absolute-Error) were 80.84 ± 9.84HU (body), 35.78 ± 6.07HU (soft tissues) and 221.88 ± 31.69HU (bones), with Dice scores of 90.33 ± 2.43 %, 95.13 ± 0.80 %, and 85.53 ± 4.16 %, respectively. The uncertainty distribution positively correlated with absolute prediction error (Correlation Coefficient: 0.62 ± 0.01). The uncertainty-conditioned robust optimisation improved the rPlan-sPlan agreement, e.g., D95 absolute difference (CTV) was 1.10 ± 1.24 % compared to conventional (1.64 ± 2.71 %) and non-robust (2.08 ± 2.96 %) optimisation. This trend was consistent across all target and organs-at-risk indexes. CONCLUSION The enhanced framework incorporates 3D uncertainty prediction and generates high-quality sCTs from MR images. The framework also facilitates conditioned robust optimisation, bolstering proton plan robustness against network prediction errors. The innovative feature of uncertainty visualisation and robust analyses contribute to evaluating sCT clinical utility for individual patients.
Collapse
Affiliation(s)
- Xia Li
- Center for Proton Therapy, Paul Scherrer Institut, Switzerland; Department of Computer Science, ETH Zurich, Switzerland
| | - Renato Bellotti
- Center for Proton Therapy, Paul Scherrer Institut, Switzerland; Department of Physics, ETH Zurich, Switzerland
| | - Gabriel Meier
- Center for Proton Therapy, Paul Scherrer Institut, Switzerland
| | | | - Damien Weber
- Center for Proton Therapy, Paul Scherrer Institut, Switzerland; Department of Radiation Oncology, University Hospital of Zurich, Switzerland; Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, Switzerland
| | - Antony Lomax
- Center for Proton Therapy, Paul Scherrer Institut, Switzerland; Department of Physics, ETH Zurich, Switzerland
| | | | - Ye Zhang
- Center for Proton Therapy, Paul Scherrer Institut, Switzerland.
| |
Collapse
|
7
|
Adiga V S, Dolz J, Lombaert H. Anatomically-aware uncertainty for semi-supervised image segmentation. Med Image Anal 2024; 91:103011. [PMID: 37924752 DOI: 10.1016/j.media.2023.103011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2022] [Revised: 08/11/2023] [Accepted: 10/18/2023] [Indexed: 11/06/2023]
Abstract
Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. A prominent way to exploit unlabeled data is to regularize model predictions. Since the predictions of unlabeled data can be unreliable, uncertainty-aware schemes are typically employed to gradually learn from meaningful and reliable predictions. Uncertainty estimation methods, however, rely on multiple inferences from the model predictions that must be computed for each training step, which is computationally expensive. Moreover, these uncertainty maps capture pixel-wise disparities and do not consider global information. This work proposes a novel method to estimate segmentation uncertainty by leveraging global information from the segmentation masks. More precisely, an anatomically-aware representation is first learnt to model the available segmentation masks. The learnt representation thereupon maps the prediction of a new segmentation into an anatomically-plausible segmentation. The deviation from the plausible segmentation aids in estimating the underlying pixel-level uncertainty in order to further guide the segmentation network. The proposed method consequently estimates the uncertainty using a single inference from our representation, thereby reducing the total computation. We evaluate our method on two publicly available segmentation datasets of left atria in cardiac MRIs and of multiple organs in abdominal CTs. Our anatomically-aware method improves the segmentation accuracy over the state-of-the-art semi-supervised methods in terms of two commonly used evaluation metrics.
Collapse
Affiliation(s)
- Sukesh Adiga V
- Computer and Software Engineering Department, ETS Montreal, 1100 Notre Dame St. W., Montreal QC, H3C 1K3, Canada.
| | - Jose Dolz
- Computer and Software Engineering Department, ETS Montreal, 1100 Notre Dame St. W., Montreal QC, H3C 1K3, Canada
| | - Herve Lombaert
- Computer and Software Engineering Department, ETS Montreal, 1100 Notre Dame St. W., Montreal QC, H3C 1K3, Canada
| |
Collapse
|
8
|
Lei H, Bellotti A. Reliable prediction intervals with directly optimized inductive conformal regression for deep learning. Neural Netw 2023; 168:194-205. [PMID: 37769456 DOI: 10.1016/j.neunet.2023.09.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 08/09/2023] [Accepted: 09/03/2023] [Indexed: 09/30/2023]
Abstract
By generating prediction intervals (PIs) to quantify the uncertainty of each prediction in deep learning regression, the risk of wrong predictions can be effectively controlled. High-quality PIs need to be as narrow as possible, whilst covering a preset proportion of real labels. At present, many approaches to improve the quality of PIs can effectively reduce the width of PIs, but they do not ensure that enough real labels are captured. Inductive Conformal Predictor (ICP) is an algorithm that can generate effective PIs which is theoretically guaranteed to cover a preset proportion of data. However, typically ICP is not directly optimized to yield minimal PI width. In this study, we propose Directly Optimized Inductive Conformal Regression (DOICR) for neural networks that takes only the average width of PIs as the loss function and increases the quality of PIs through an optimized scheme, under the validity condition that sufficient real labels are captured in the PIs. Benchmark experiments show that DOICR outperforms current state-of-the-art algorithms for regression problems using underlying Deep Neural Network structures for both tabular and image data.
Collapse
Affiliation(s)
- Haocheng Lei
- School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, 315100, Zhejiang, China
| | - Anthony Bellotti
- School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, 315100, Zhejiang, China.
| |
Collapse
|
9
|
Gudhe NR, Kosma VM, Behravan H, Mannermaa A. Nuclei instance segmentation from histopathology images using Bayesian dropout based deep learning. BMC Med Imaging 2023; 23:162. [PMID: 37858043 PMCID: PMC10585914 DOI: 10.1186/s12880-023-01121-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2023] [Accepted: 10/05/2023] [Indexed: 10/21/2023] Open
Abstract
BACKGROUND The deterministic deep learning models have achieved state-of-the-art performance in various medical image analysis tasks, including nuclei segmentation from histopathology images. The deterministic models focus on improving the model prediction accuracy without assessing the confidence in the predictions. METHODS We propose a semantic segmentation model using Bayesian representation to segment nuclei from the histopathology images and to further quantify the epistemic uncertainty. We employ Bayesian approximation with Monte-Carlo (MC) dropout during the inference time to estimate the model's prediction uncertainty. RESULTS We evaluate the performance of the proposed approach on the PanNuke dataset, which consists of 312 visual fields from 19 organ types. We compare the nuclei segmentation accuracy of our approach with that of a fully convolutional neural network, U-Net, SegNet, and the state-of-the-art Hover-net. We use F1-score and intersection over union (IoU) as the evaluation metrics. The proposed approach achieves a mean F1-score of 0.893 ± 0.008 and an IoU value of 0.868 ± 0.003 on the test set of the PanNuke dataset. These results outperform the Hover-net, which has a mean F1-score of 0.871 ± 0.010 and an IoU value of 0.840 ± 0.032. CONCLUSIONS The proposed approach, which incorporates Bayesian representation and Monte-Carlo dropout, demonstrates superior performance in segmenting nuclei from histopathology images compared to existing models such as U-Net, SegNet, and Hover-net. By considering the epistemic uncertainty, our model provides a more reliable estimation of the prediction confidence. These findings highlight the potential of Bayesian deep learning for improving medical image analysis tasks and can contribute to the development of more accurate and reliable computer-aided diagnostic systems.
Collapse
Affiliation(s)
- Naga Raju Gudhe
- Institute of Clinical Medicine, Pathology and Forensic Medicine, Multidisciplinary Cancer research community RC Cancer, University of Eastern Finland, P.O. Box 1627, Kuopio, 70211, Finland.
| | - Veli-Matti Kosma
- Institute of Clinical Medicine, Pathology and Forensic Medicine, Multidisciplinary Cancer research community RC Cancer, University of Eastern Finland, P.O. Box 1627, Kuopio, 70211, Finland
- Biobank of Eastern Finland, Kuopio University Hospital, Kuopio, Finland
| | - Hamid Behravan
- Institute of Clinical Medicine, Pathology and Forensic Medicine, Multidisciplinary Cancer research community RC Cancer, University of Eastern Finland, P.O. Box 1627, Kuopio, 70211, Finland
| | - Arto Mannermaa
- Institute of Clinical Medicine, Pathology and Forensic Medicine, Multidisciplinary Cancer research community RC Cancer, University of Eastern Finland, P.O. Box 1627, Kuopio, 70211, Finland
- Biobank of Eastern Finland, Kuopio University Hospital, Kuopio, Finland
| |
Collapse
|
10
|
Mehrtens HA, Kurz A, Bucher TC, Brinker TJ. Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise. Med Image Anal 2023; 89:102914. [PMID: 37544085 DOI: 10.1016/j.media.2023.102914] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Revised: 05/17/2023] [Accepted: 07/25/2023] [Indexed: 08/08/2023]
Abstract
In the past years, deep learning has seen an increase in usage in the domain of histopathological applications. However, while these approaches have shown great potential, in high-risk environments deep learning models need to be able to judge their uncertainty and be able to reject inputs when there is a significant chance of misclassification. In this work, we conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole Slide Images, with a focus on the task of selective classification, where the model should reject the classification in situations in which it is uncertain. We conduct our experiments on tile-level under the aspects of domain shift and label noise, as well as on slide-level. In our experiments, we compare Deep Ensembles, Monte-Carlo Dropout, Stochastic Variational Inference, Test-Time Data Augmentation as well as ensembles of the latter approaches. We observe that ensembles of methods generally lead to better uncertainty estimates as well as an increased robustness towards domain shifts and label noise, while contrary to results from classical computer vision benchmarks no systematic gain of the other methods can be shown. Across methods, a rejection of the most uncertain samples reliably leads to a significant increase in classification accuracy on both in-distribution as well as out-of-distribution data. Furthermore, we conduct experiments comparing these methods under varying conditions of label noise. Lastly, we publish our code framework to facilitate further research on uncertainty estimation on histopathological data.
Collapse
Affiliation(s)
- Hendrik A Mehrtens
- Division of Digital Biomarkers for Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Alexander Kurz
- Division of Digital Biomarkers for Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Tabea-Clara Bucher
- Division of Digital Biomarkers for Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Titus J Brinker
- Division of Digital Biomarkers for Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany.
| |
Collapse
|
11
|
Hansen S, Gautam S, Salahuddin SA, Kampffmeyer M, Jenssen R. ADNet++: A few-shot learning framework for multi-class medical image volume segmentation with uncertainty-guided feature refinement. Med Image Anal 2023; 89:102870. [PMID: 37541101 DOI: 10.1016/j.media.2023.102870] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2022] [Revised: 04/23/2023] [Accepted: 06/12/2023] [Indexed: 08/06/2023]
Abstract
A major barrier to applying deep segmentation models in the medical domain is their typical data-hungry nature, requiring experts to collect and label large amounts of data for training. As a reaction, prototypical few-shot segmentation (FSS) models have recently gained traction as data-efficient alternatives. Nevertheless, despite the recent progress of these models, they still have some essential shortcomings that must be addressed. In this work, we focus on three of these shortcomings: (i) the lack of uncertainty estimation, (ii) the lack of a guiding mechanism to help locate edges and encourage spatial consistency in the segmentation maps, and (iii) the models' inability to do one-step multi-class segmentation. Without modifying or requiring a specific backbone architecture, we propose a modified prototype extraction module that facilitates the computation of uncertainty maps in prototypical FSS models, and show that the resulting maps are useful indicators of the model uncertainty. To improve the segmentation around boundaries and to encourage spatial consistency, we propose a novel feature refinement module that leverages structural information in the input space to help guide the segmentation in the feature space. Furthermore, we demonstrate how uncertainty maps can be used to automatically guide this feature refinement. Finally, to avoid ambiguous voxel predictions that occur when images are segmented class-by-class, we propose a procedure to perform one-step multi-class FSS. The efficiency of our proposed methodology is evaluated on two representative datasets for abdominal organ segmentation (CHAOS dataset and BTCV dataset) and one dataset for cardiac segmentation (MS-CMRSeg dataset). The results show that our proposed methodology significantly (one-sided Wilcoxon signed rank test, p<0.05) improves the baseline, increasing the overall dice score with +5.2, +5.1, and +2.8 percentage points for the CHAOS dataset, the BTCV dataset, and the MS-CMRSeg dataset, respectively.
Collapse
Affiliation(s)
- Stine Hansen
- Department of Physics and Technology, UiT The Arctic University of Norway, NO-9037 Tromsø, Norway.
| | - Srishti Gautam
- Department of Physics and Technology, UiT The Arctic University of Norway, NO-9037 Tromsø, Norway
| | - Suaiba Amina Salahuddin
- Department of Physics and Technology, UiT The Arctic University of Norway, NO-9037 Tromsø, Norway
| | - Michael Kampffmeyer
- Department of Physics and Technology, UiT The Arctic University of Norway, NO-9037 Tromsø, Norway
| | - Robert Jenssen
- Department of Physics and Technology, UiT The Arctic University of Norway, NO-9037 Tromsø, Norway
| |
Collapse
|
12
|
Min H, Dowling J, Jameson MG, Cloak K, Faustino J, Sidhom M, Martin J, Cardoso M, Ebert MA, Haworth A, Chlap P, de Leon J, Berry M, Pryor D, Greer P, Vinod SK, Holloway L. Clinical target volume delineation quality assurance for MRI-guided prostate radiotherapy using deep learning with uncertainty estimation. Radiother Oncol 2023; 186:109794. [PMID: 37414257 DOI: 10.1016/j.radonc.2023.109794] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Revised: 06/19/2023] [Accepted: 06/30/2023] [Indexed: 07/08/2023]
Abstract
BACKGROUND AND PURPOSE Previous studies on automatic delineation quality assurance (QA) have mostly focused on CT-based planning. As MRI-guided radiotherapy is increasingly utilized in prostate cancer treatment, there is a need for more research on MRI-specific automatic QA. This work proposes a clinical target volume (CTV) delineation QA framework based on deep learning (DL) for MRI-guided prostate radiotherapy. MATERIALS AND METHODS The proposed workflow utilized a 3D dropblock ResUnet++ (DB-ResUnet++) to generate multiple segmentation predictions via Monte Carlo dropout which were used to compute an average delineation and area of uncertainty. A logistic regression (LR) classifier was employed to classify the manual delineation as pass or discrepancy based on the spatial association between the manual delineation and the network's outputs. This approach was evaluated on a multicentre MRI-only prostate radiotherapy dataset and compared with our previously published QA framework based on AN-AG Unet. RESULTS The proposed framework achieved an area under the receiver operating curve (AUROC) of 0.92, a true positive rate (TPR) of 0.92 and a false positive rate of 0.09 with an average processing time per delineation of 1.3 min. Compared with our previous work using AN-AG Unet, this method generated fewer false positive detections at the same TPR with a much faster processing speed. CONCLUSION To the best of our knowledge, this is the first study to propose an automatic delineation QA tool using DL with uncertainty estimation for MRI-guided prostate radiotherapy, which can potentially be used for reviewing prostate CTV delineation in multicentre clinical trials.
Collapse
Affiliation(s)
- Hang Min
- CSIRO Australian e-Health Research Centre, Herston, Queensland, Australia; Ingham Institute for Applied Medical Research, Sydney, New South Wales, Australia; South Western Clinical Campuses, University of New South Wales, Australia.
| | - Jason Dowling
- CSIRO Australian e-Health Research Centre, Herston, Queensland, Australia; South Western Clinical Campuses, University of New South Wales, Australia; Centre for Medical Radiation Physics, University of Wollongong, New South Wales, Australia; Institute of Medical Physics, The University of Sydney, New South Wales, Australia; School of Mathematical and Physical Sciences, University of Newcastle, New South Wales, Australia
| | - Michael G Jameson
- Ingham Institute for Applied Medical Research, Sydney, New South Wales, Australia; St Vincent's Clinical School, Faculty of Medicine, University of New South Wales, Australia; GenesisCare, Sydney, New South Wales, Australia; Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - Kirrily Cloak
- Ingham Institute for Applied Medical Research, Sydney, New South Wales, Australia; South Western Clinical Campuses, University of New South Wales, Australia
| | - Joselle Faustino
- Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - Mark Sidhom
- South Western Clinical Campuses, University of New South Wales, Australia; Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - Jarad Martin
- Calvary Mater Newcastle Hospital, Radiation Oncology, Newcastle, Australia
| | - Michael Cardoso
- Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - Martin A Ebert
- Centre for Medical Radiation Physics, University of Wollongong, New South Wales, Australia; Department of Radiation Oncology, Sir Charles Gairdner Hospital, Nedlands, Western Australia, Australia; School of Physics Mathematics and Computing, University of Western Australia, Perth, Western Australia, Australia
| | - Annette Haworth
- Institute of Medical Physics, The University of Sydney, New South Wales, Australia
| | - Phillip Chlap
- Ingham Institute for Applied Medical Research, Sydney, New South Wales, Australia; South Western Clinical Campuses, University of New South Wales, Australia; Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - Jeremiah de Leon
- GenesisCare, Sydney, New South Wales, Australia; Illawarra Cancer Care Centre, Wollongong, Australia
| | - Megan Berry
- Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - David Pryor
- Princess Alexandra Hospital, Brisbane, Queensland, Australia
| | - Peter Greer
- School of Mathematical and Physical Sciences, University of Newcastle, New South Wales, Australia; Calvary Mater Newcastle Hospital, Radiation Oncology, Newcastle, Australia
| | - Shalini K Vinod
- Ingham Institute for Applied Medical Research, Sydney, New South Wales, Australia; South Western Clinical Campuses, University of New South Wales, Australia; Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| | - Lois Holloway
- Ingham Institute for Applied Medical Research, Sydney, New South Wales, Australia; South Western Clinical Campuses, University of New South Wales, Australia; Centre for Medical Radiation Physics, University of Wollongong, New South Wales, Australia; Institute of Medical Physics, The University of Sydney, New South Wales, Australia; Liverpool and Macarthur Cancer therapy Centres, Liverpool Hospital, New South Wales, Australia
| |
Collapse
|
13
|
Šuster S, Baldwin T, Verspoor K. Analysis of predictive performance and reliability of classifiers for quality assessment of medical evidence revealed important variation by medical area. J Clin Epidemiol 2023; 159:58-69. [PMID: 37120028 DOI: 10.1016/j.jclinepi.2023.04.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Revised: 03/30/2023] [Accepted: 04/18/2023] [Indexed: 05/01/2023]
Abstract
OBJECTIVES A major obstacle in deployment of models for automated quality assessment is their reliability. To analyze their calibration and selective classification performance. STUDY DESIGN AND SETTING We examine two systems for assessing the quality of medical evidence, EvidenceGRADEr and RobotReviewer, both developed from Cochrane Database of Systematic Reviews (CDSR) to measure strength of bodies of evidence and risk of bias (RoB) of individual studies, respectively. We report their calibration error and Brier scores, present their reliability diagrams, and analyze the risk-coverage trade-off in selective classification. RESULTS The models are reasonably well calibrated on most quality criteria (expected calibration error [ECE] 0.04-0.09 for EvidenceGRADEr, 0.03-0.10 for RobotReviewer). However, we discover that both calibration and predictive performance vary significantly by medical area. This has ramifications for the application of such models in practice, as average performance is a poor indicator of group-level performance (e.g., health and safety at work, allergy and intolerance, and public health see much worse performance than cancer, pain, and anesthesia, and Neurology). We explore the reasons behind this disparity. CONCLUSION Practitioners adopting automated quality assessment should expect large fluctuations in system reliability and predictive performance depending on the medical area. Prospective indicators of such behavior should be further researched.
Collapse
Affiliation(s)
- Simon Šuster
- School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia.
| | - Timothy Baldwin
- School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia; Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
| | - Karin Verspoor
- School of Computing Technologies, RMIT University, Melbourne, Australia; School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia
| |
Collapse
|
14
|
Huttinga NRF, Bruijnen T, van den Berg CAT, Sbrizzi A. Gaussian Processes for real-time 3D motion and uncertainty estimation during MR-guided radiotherapy. Med Image Anal 2023; 88:102843. [PMID: 37245435 DOI: 10.1016/j.media.2023.102843] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2022] [Revised: 05/11/2023] [Accepted: 05/15/2023] [Indexed: 05/30/2023]
Abstract
Respiratory motion during radiotherapy causes uncertainty in the tumor's location, which is typically addressed by an increased radiation area and a decreased dose. As a result, the treatments' efficacy is reduced. The recently proposed hybrid MR-linac scanner holds the promise to efficiently deal with such respiratory motion through real-time adaptive MR-guided radiotherapy (MRgRT). For MRgRT, motion-fields should be estimated from MR-data and the radiotherapy plan should be adapted in real-time according to the estimated motion-fields. All of this should be performed with a total latency of maximally 200 ms, including data acquisition and reconstruction. A measure of confidence in such estimated motion-fields is highly desirable, for instance to ensure the patient's safety in case of unexpected and undesirable motion. In this work, we propose a framework based on Gaussian Processes to infer 3D motion-fields and uncertainty maps in real-time from only three readouts of MR-data. We demonstrated an inference frame rate up to 69 Hz including data acquisition and reconstruction, thereby exploiting the limited amount of required MR-data. Additionally, we designed a rejection criterion based on the motion-field uncertainty maps to demonstrate the framework's potential for quality assurance. The framework was validated in silico and in vivo on healthy volunteer data (n=5) acquired using an MR-linac, thereby taking into account different breathing patterns and controlled bulk motion. Results indicate end-point-errors with a 75th percentile below 1 mm in silico, and a correct detection of erroneous motion estimates with the rejection criterion. Altogether, the results show the potential of the framework for application in real-time MR-guided radiotherapy with an MR-linac.
Collapse
Affiliation(s)
- Niek R F Huttinga
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, The Netherlands; Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, The Netherlands.
| | - Tom Bruijnen
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, The Netherlands; Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, The Netherlands
| | - Cornelis A T van den Berg
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, The Netherlands; Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, The Netherlands
| | - Alessandro Sbrizzi
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, The Netherlands; Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, The Netherlands
| |
Collapse
|
15
|
Yang R, Liu H, Li Y. Quantifying uncertainty of marine water quality forecasts for environmental management using a dynamic multi-factor analysis and multi-resolution ensemble approach. Chemosphere 2023; 331:138831. [PMID: 37137396 DOI: 10.1016/j.chemosphere.2023.138831] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/23/2023] [Revised: 04/25/2023] [Accepted: 04/30/2023] [Indexed: 05/05/2023]
Abstract
Unpredictable climate change and human activities pose enormous challenges to assessing the water quality components in the marine environment. Accurately quantifying the uncertainty of water quality forecasts can help decision-makers implement more scientific water pollution management strategies. This work introduces a new method of uncertainty quantification driven by point prediction for solving the engineering problem of water quality forecasting under the influence of complex environmental factors. The constructed multi-factor correlation analysis system can dynamically adjust the combined weight of environmental indicators according to the performance, thereby increasing the interpretability of data fusion. The designed singular spectrum analysis is utilized to reduce the volatility of the original water quality data. The real-time decomposition technique cleverly avoids the problem of data leakage. The multi-resolution-multi-objective optimization ensemble method is adopted to absorb the characteristics of different resolution data, so as to mine deeper potential information. Experimental studies are conducted using 6 actual water quality high-resolution signals with 21,600 sampling points from the Pacific islands and corresponding low-resolution signals with 900 sampling points, including temperature, salinity, turbidity, chlorophyll, dissolved oxygen, and oxygen saturation. The results illustrate that the model is superior to the existing model in quantifying the uncertainty of water quality prediction.
Collapse
Affiliation(s)
- Rui Yang
- Institute of Artificial Intelligence and Robotics (IAIR), Key Laboratory of Traffic Safety on Track of Ministry of Education, School of Traffic and Transportation Engineering, Central South University, Changsha, 410075, Hunan, China
| | - Hui Liu
- Institute of Artificial Intelligence and Robotics (IAIR), Key Laboratory of Traffic Safety on Track of Ministry of Education, School of Traffic and Transportation Engineering, Central South University, Changsha, 410075, Hunan, China.
| | - Yanfei Li
- School of Mechatronic Engineering, Hunan Agricultural University, Changsha, 410128, Hunan, China
| |
Collapse
|
16
|
Murugesan B, Liu B, Galdran A, Ayed IB, Dolz J. Calibrating segmentation networks with margin-based label smoothing. Med Image Anal 2023; 87:102826. [PMID: 37146441 DOI: 10.1016/j.media.2023.102826] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Revised: 02/15/2023] [Accepted: 04/17/2023] [Indexed: 05/07/2023]
Abstract
Despite the undeniable progress in visual recognition tasks fueled by deep neural networks, there exists recent evidence showing that these models are poorly calibrated, resulting in over-confident predictions. The standard practices of minimizing the cross-entropy loss during training promote the predicted softmax probabilities to match the one-hot label assignments. Nevertheless, this yields a pre-softmax activation of the correct class that is significantly larger than the remaining activations, which exacerbates the miscalibration problem. Recent observations from the classification literature suggest that loss functions that embed implicit or explicit maximization of the entropy of predictions yield state-of-the-art calibration performances. Despite these findings, the impact of these losses in the relevant task of calibrating medical image segmentation networks remains unexplored. In this work, we provide a unifying constrained-optimization perspective of current state-of-the-art calibration losses. Specifically, these losses could be viewed as approximations of a linear penalty (or a Lagrangian term) imposing equality constraints on logit distances. This points to an important limitation of such underlying equality constraints, whose ensuing gradients constantly push towards a non-informative solution, which might prevent from reaching the best compromise between the discriminative performance and calibration of the model during gradient-based optimization. Following our observations, we propose a simple and flexible generalization based on inequality constraints, which imposes a controllable margin on logit distances. Comprehensive experiments on a variety of public medical image segmentation benchmarks demonstrate that our method sets novel state-of-the-art results on these tasks in terms of network calibration, whereas the discriminative performance is also improved. The code is available at https://github.com/Bala93/MarginLoss.
Collapse
Affiliation(s)
- Balamurali Murugesan
- LIVIA, ÉTS Montréal, Canada; International Laboratory on Learning Systems (ILLS), McGill - ETS - MILA - CNRS - Université Paris-Saclay - CentraleSupélec, Canada.
| | - Bingyuan Liu
- LIVIA, ÉTS Montréal, Canada; International Laboratory on Learning Systems (ILLS), McGill - ETS - MILA - CNRS - Université Paris-Saclay - CentraleSupélec, Canada
| | | | - Ismail Ben Ayed
- LIVIA, ÉTS Montréal, Canada; International Laboratory on Learning Systems (ILLS), McGill - ETS - MILA - CNRS - Université Paris-Saclay - CentraleSupélec, Canada; Centre de Recherche du Centre Hospitalier de l'Université de Montréal (CRCHUM), Canada
| | - Jose Dolz
- LIVIA, ÉTS Montréal, Canada; International Laboratory on Learning Systems (ILLS), McGill - ETS - MILA - CNRS - Université Paris-Saclay - CentraleSupélec, Canada; Centre de Recherche du Centre Hospitalier de l'Université de Montréal (CRCHUM), Canada
| |
Collapse
|
17
|
Del Amor R, Silva-Rodríguez J, Naranjo V. Labeling confidence for uncertainty-aware histology image classification. Comput Med Imaging Graph 2023; 107:102231. [PMID: 37087899 DOI: 10.1016/j.compmedimag.2023.102231] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2022] [Revised: 02/23/2023] [Accepted: 03/27/2023] [Indexed: 04/25/2023]
Abstract
Deep learning-based models applied to digital pathology require large, curated datasets with high-quality (HQ) annotations to perform correctly. In many cases, recruiting expert pathologists to annotate large databases is not feasible, and it is necessary to collect additional labeled data with varying label qualities, e.g., pathologists-in-training (henceforth, non-expert annotators). Learning from datasets with noisy labels is more challenging in medical applications since medical imaging datasets tend to have instance-dependent noise and suffer from high inter/intra-observer variability. In this paper, we design an uncertainty-driven labeling strategy with which we generate soft labels from 10 non-expert annotators for multi-class skin cancer classification. Based on this soft annotation, we propose an uncertainty estimation-based framework to handle these noisy labels. This framework is based on a novel formulation using a dual-branch min-max entropy calibration to penalize inexact labels during the training. Comprehensive experiments demonstrate the promising performance of our labeling strategy. Results show a consistent improvement by using soft labels with standard cross-entropy loss during training (∼4.0% F1-score) and increases when calibrating the model with the proposed min-max entropy calibration (∼6.6% F1-score). These improvements are produced at negligible cost, both in terms of annotation and calculation.
Collapse
Affiliation(s)
- Rocío Del Amor
- Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València, Valencia, Spain.
| | | | - Valery Naranjo
- Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València, Valencia, Spain.
| |
Collapse
|
18
|
Linmans J, Elfwing S, van der Laak J, Litjens G. Predictive uncertainty estimation for out-of-distribution detection in digital pathology. Med Image Anal 2023; 83:102655. [PMID: 36306568 DOI: 10.1016/j.media.2022.102655] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2022] [Revised: 09/26/2022] [Accepted: 10/12/2022] [Indexed: 11/06/2022]
Abstract
Machine learning model deployment in clinical practice demands real-time risk assessment to identify situations in which the model is uncertain. Once deployed, models should be accurate for classes seen during training while providing informative estimates of uncertainty to flag abnormalities and unseen classes for further analysis. Although recent developments in uncertainty estimation have resulted in an increasing number of methods, a rigorous empirical evaluation of their performance on large-scale digital pathology datasets is lacking. This work provides a benchmark for evaluating prevalent methods on multiple datasets by comparing the uncertainty estimates on both in-distribution and realistic near and far out-of-distribution (OOD) data on a whole-slide level. To this end, we aggregate uncertainty values from patch-based classifiers to whole-slide level uncertainty scores. We show that results found in classical computer vision benchmarks do not always translate to the medical imaging setting. Specifically, we demonstrate that deep ensembles perform best at detecting far-OOD data but can be outperformed on a more challenging near-OOD detection task by multi-head ensembles trained for optimal ensemble diversity. Furthermore, we demonstrate the harmful impact OOD data can have on the performance of deployed machine learning models. Overall, we show that uncertainty estimates can be used to discriminate in-distribution from OOD data with high AUC scores. Still, model deployment might require careful tuning based on prior knowledge of prospective OOD data.
Collapse
Affiliation(s)
- Jasper Linmans
- Department of Pathology, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands.
| | | | - Jeroen van der Laak
- Department of Pathology, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands; Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden
| | - Geert Litjens
- Department of Pathology, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
| |
Collapse
|
19
|
Zakeri A, Hokmabadi A, Bi N, Wijesinghe I, Nix MG, Petersen SE, Frangi AF, Taylor ZA, Gooya A. DragNet: Learning-based deformable registration for realistic cardiac MR sequence generation from a single frame. Med Image Anal 2023; 83:102678. [PMID: 36403308 DOI: 10.1016/j.media.2022.102678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Revised: 08/24/2022] [Accepted: 10/27/2022] [Indexed: 11/06/2022]
Abstract
Deformable image registration (DIR) can be used to track cardiac motion. Conventional DIR algorithms aim to establish a dense and non-linear correspondence between independent pairs of images. They are, nevertheless, computationally intensive and do not consider temporal dependencies to regulate the estimated motion in a cardiac cycle. In this paper, leveraging deep learning methods, we formulate a novel hierarchical probabilistic model, termed DragNet, for fast and reliable spatio-temporal registration in cine cardiac magnetic resonance (CMR) images and for generating synthetic heart motion sequences. DragNet is a variational inference framework, which takes an image from the sequence in combination with the hidden states of a recurrent neural network (RNN) as inputs to an inference network per time step. As part of this framework, we condition the prior probability of the latent variables on the hidden states of the RNN utilised to capture temporal dependencies. We further condition the posterior of the motion field on a latent variable from hierarchy and features from the moving image. Subsequently, the RNN updates the hidden state variables based on the feature maps of the fixed image and the latent variables. Different from traditional methods, DragNet performs registration on unseen sequences in a forward pass, which significantly expedites the registration process. Besides, DragNet enables generating a large number of realistic synthetic image sequences given only one frame, where the corresponding deformations are also retrieved. The probabilistic framework allows for computing spatio-temporal uncertainties in the estimated motion fields. Our results show that DragNet performance is comparable with state-of-the-art methods in terms of registration accuracy, with the advantage of offering analytical pixel-wise motion uncertainty estimation across a cardiac cycle and being a motion generator. We will make our code publicly available.
Collapse
Affiliation(s)
- Arezoo Zakeri
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, School of Computing, University of Leeds, UK.
| | - Alireza Hokmabadi
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, School of Computing, University of Leeds, UK
| | - Ning Bi
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, School of Computing, University of Leeds, UK
| | - Isuru Wijesinghe
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, School of Mechanical Engineering, University of Leeds, UK
| | - Michael G Nix
- Leeds Cancer Centre, Leeds Teaching Hospitals NHS Trust, UK
| | - Steffen E Petersen
- William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, UK; Barts Heart Centre, St Bartholomew's Hospital, Barts Health NHS Trust, London, UK; Health Data Research UK, London, UK; Alan Turing Institute, London, UK
| | - Alejandro F Frangi
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, School of Computing, University of Leeds, UK
| | - Zeike A Taylor
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, School of Mechanical Engineering, University of Leeds, UK
| | - Ali Gooya
- Alan Turing Institute, London, UK; School of Computing Science, University of Glasgow, Glasgow, UK.
| |
Collapse
|
20
|
Carnegie-Peake L, Taprogge J, Murray I, Flux GD, Gear J. Quantification and dosimetry of small volumes including associated uncertainty estimation. EJNMMI Phys 2022; 9:86. [PMID: 36512147 DOI: 10.1186/s40658-022-00512-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2022] [Accepted: 11/17/2022] [Indexed: 12/15/2022] Open
Abstract
BACKGROUND Accurate quantification of radioactivity in a source of interest relies on accurate registration between SPECT and anatomical images, and appropriate correction of partial volume effects (PVEs). For small volumes, exact registration between the two imaging modalities and recovery factors used to correct for PVE are unreliable. There is currently no guidance relating to quantification or the associated uncertainty estimation for small volumes. MATERIAL AND METHODS A method for quantification of small sources of interest is proposed, which uses multiple oversized volumes of interest. The method was applied to three Na[131I]I activity distributions where a Na[131I]I capsule was situated within a cylindrical phantom containing either zero background, uniform background or non-uniform background and to a scenario with small lesions placed in an anthropomorphic phantom. The Na[131I]I capsule and lesions were quantified using the proposed method and compared with measurements made using two alternative quantification methods. The proposed method was also applied to assess the absorbed dose delivered to a bone metastasis following [131I]mIBG therapy for neuroblastoma including the associated uncertainty estimation. RESULTS The method is accurate across a range of activities and in varied radioactivity distributions. Median percentage errors using the proposed method in no background, uniform backgrounds and non-uniform backgrounds were - 0.4%, - 0.3% and 1.7% with median associated uncertainties of 1.4%, 1.4% and 1.6%, respectively. The technique is more accurate and robust when compared to currently available alternative methods. CONCLUSIONS The proposed method provides a reliable and accurate method for quantification of sources of interest, which are less than three times the spatial resolution of the imaging system. The method may be of use in absorbed dose calculation in cases of bone metastasis, lung metastasis or thyroid remnants.
Collapse
Affiliation(s)
- Lily Carnegie-Peake
- Joint Department of Physics, Royal Marsden NHSFT, Downs Road, Sutton, SM2 5PT, UK.,The Institute of Cancer Research, 15 Cotswold Road, Sutton, SM2 5NG, UK
| | - Jan Taprogge
- Joint Department of Physics, Royal Marsden NHSFT, Downs Road, Sutton, SM2 5PT, UK.,The Institute of Cancer Research, 15 Cotswold Road, Sutton, SM2 5NG, UK
| | - Iain Murray
- Joint Department of Physics, Royal Marsden NHSFT, Downs Road, Sutton, SM2 5PT, UK.,The Institute of Cancer Research, 15 Cotswold Road, Sutton, SM2 5NG, UK
| | - Glenn D Flux
- Joint Department of Physics, Royal Marsden NHSFT, Downs Road, Sutton, SM2 5PT, UK.,The Institute of Cancer Research, 15 Cotswold Road, Sutton, SM2 5NG, UK
| | - Jonathan Gear
- Joint Department of Physics, Royal Marsden NHSFT, Downs Road, Sutton, SM2 5PT, UK. .,The Institute of Cancer Research, 15 Cotswold Road, Sutton, SM2 5NG, UK.
| |
Collapse
|
21
|
González C, Gotkowski K, Fuchs M, Bucher A, Dadras A, Fischbach R, Kaltenborn IJ, Mukhopadhyay A. Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation. Med Image Anal 2022; 82:102596. [PMID: 36084564 PMCID: PMC9400372 DOI: 10.1016/j.media.2022.102596] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Revised: 08/04/2022] [Accepted: 08/18/2022] [Indexed: 11/16/2022]
Abstract
Automatic segmentation of ground glass opacities and consolidations in chest computer tomography (CT) scans can potentially ease the burden of radiologists during times of high resource utilisation. However, deep learning models are not trusted in the clinical routine due to failing silently on out-of-distribution (OOD) data. We propose a lightweight OOD detection method that leverages the Mahalanobis distance in the feature space and seamlessly integrates into state-of-the-art segmentation pipelines. The simple approach can even augment pre-trained models with clinically relevant uncertainty quantification. We validate our method across four chest CT distribution shifts and two magnetic resonance imaging applications, namely segmentation of the hippocampus and the prostate. Our results show that the proposed method effectively detects far- and near-OOD samples across all explored scenarios.
Collapse
Affiliation(s)
- Camila González
- Darmstadt University of Technology, Karolinenplatz 5, 64289 Darmstadt, Germany.
| | - Karol Gotkowski
- Darmstadt University of Technology, Karolinenplatz 5, 64289 Darmstadt, Germany
| | - Moritz Fuchs
- Darmstadt University of Technology, Karolinenplatz 5, 64289 Darmstadt, Germany
| | - Andreas Bucher
- Uniklinik Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany
| | - Armin Dadras
- Uniklinik Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany
| | - Ricarda Fischbach
- Uniklinik Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany
| | | | | |
Collapse
|
22
|
Fooladgar F, Jamzad A, Connolly L, Santilli A, Kaufmann M, Ren K, Abolmaesumi P, Rudan JF, McKay D, Fichtinger G, Mousavi P. Uncertainty estimation for margin detection in cancer surgery using mass spectrometry. Int J Comput Assist Radiol Surg 2022. [PMID: 36175747 DOI: 10.1007/s11548-022-02764-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2022] [Accepted: 09/19/2022] [Indexed: 11/05/2022]
Abstract
PURPOSE Rapid evaporative ionization mass spectrometry (REIMS) is an emerging technology for clinical margin detection. Deployment of REIMS depends on construction of reliable deep learning models that can categorize tissue according to its metabolomic signature. Challenges associated with developing these models include the presence of noise during data acquisition and the variance in tissue signatures between patients. In this study, we propose integration of uncertainty estimation in deep models to factor predictive confidence into margin detection in cancer surgery. METHODS iKnife is used to collect 693 spectra of cancer and healthy samples acquired from 91 patients during basal cell carcinoma resection. A Bayesian neural network and two baseline models are trained on these data to perform classification as well as uncertainty estimation. The samples with high estimated uncertainty are then removed, and new models are trained using the clean data. The performance of proposed and baseline models, with different ratios of filtered data, is then compared. RESULTS The data filtering does not improve the performance of the baseline models as they cannot provide reliable estimations of uncertainty. In comparison, the proposed model demonstrates a statistically significant improvement in average balanced accuracy (75.2%), sensitivity (74.1%) and AUC (82.1%) after removing uncertain training samples. We also demonstrate that if highly uncertain samples are predicted and removed from the test data, sensitivity further improves to 88.2%. CONCLUSIONS This is the first study that applies uncertainty estimation to inform model training and deployment for tissue recognition in cancer surgery. Uncertainty estimation is leveraged in two ways: by factoring a measure of input noise in training the models and by including predictive confidence in reporting the outputs. We empirically show that considering uncertainty for model development can help improve the overall accuracy of a margin detection system using REIMS.
Collapse
|
23
|
Du L, Liu C, Wei R, Chen J. Uncertainty-aware dynamic integration for multi-omics classification of tumors. J Cancer Res Clin Oncol 2022:10.1007/s00432-022-04219-3. [PMID: 35925427 DOI: 10.1007/s00432-022-04219-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2022] [Accepted: 07/18/2022] [Indexed: 12/12/2022]
Abstract
PURPOSE Omics data are crucial for medical diagnosis as it contains intrinsic biomedical information. Multi-omics integrated analysis has become a new direction for scientists to explore life mechanisms. Nevertheless, the quality of complex omics data often varies greatly due to different samples or even different omics types, it is challenging to dynamically capture the uncertainty for different kinds of omics data. METHODS This paper proposes a uncertainty-aware dynamic integration framework for multi-omics classification. The framework consists of three modules: deep embedding, confidence prediction, and downstream tasks. The deep embedding module extract key information from multi-omics data to obtain a low-dimensional feature representation which is used to train downstream tasks. Combined with the deep embedding module, the confidence prediction module is used to dynamically capture the uncertainty of the data. We introduce "confidNet" to assign a confidence value for each type of omics data, which is used for dynamic integration between multi-omics. RESULTS Compared with other integration methods, the proposed method can contain more crucial biomedical information in the obtained low-dimensional representation. Our framework realizes reliable integration among multiple omics, and it can still achieve high accuracy on small sample data sets. We have verified the effectiveness of the model in a large number of experiments. CONCLUSION Our framework can be widely applied to high-dimensional omics data and has great potential to facilitate medical decision-making and biological analysis.
Collapse
Affiliation(s)
- Ling Du
- School of Software, TianGong University, Tianjin, China.
| | - Chaoyi Liu
- School of Software, TianGong University, Tianjin, China
| | - Ran Wei
- School of Life Sciences, TianGongUniversity, Tianjin, China
| | - Jinmiao Chen
- Singapore Immunology Network (SIgN), Agency for Science, Technology and Research (A*STAR), 1386481, Singapore, Singapore
- Immunology Translational Research Program, Yong Loo Lin School of Medicine, Department of Microbiology and Immunology, National University of Singapore(NUS), 117545, Singapore, Singapore
| |
Collapse
|
24
|
Tong X, Wang D, Ding X, Tan X, Ren Q, Chen G, Rong Y, Xu T, Huang J, Jiang H, Zheng M, Li X. Blood-brain barrier penetration prediction enhanced by uncertainty estimation. J Cheminform 2022; 14:44. [PMID: 35799215 PMCID: PMC9264551 DOI: 10.1186/s13321-022-00619-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2021] [Accepted: 05/28/2022] [Indexed: 01/01/2023] Open
Abstract
Blood–brain barrier is a pivotal factor to be considered in the process of central nervous system (CNS) drug development, and it is of great significance to rapidly explore the blood–brain barrier permeability (BBBp) of compounds in silico in early drug discovery process. Here, we focus on whether and how uncertainty estimation methods improve in silico BBBp models. We briefly surveyed the current state of in silico BBBp prediction and uncertainty estimation methods of deep learning models, and curated an independent dataset to determine the reliability of the state-of-the-art algorithms. The results exhibit that, despite the comparable performance on BBBp prediction between graph neural networks-based deep learning models and conventional physicochemical-based machine learning models, the GROVER-BBBp model shows greatly improvement when using uncertainty estimations. In particular, the strategy combined Entropy and MC-dropout can increase the accuracy of distinguishing BBB + from BBB − to above 99% by extracting predictions with high confidence level (uncertainty score < 0.1). Case studies on preclinical/clinical drugs for Alzheimer’ s disease and marketed antitumor drugs that verified by literature proved the application value of uncertainty estimation enhanced BBBp prediction model, that may facilitate the drug discovery in the field of CNS diseases and metastatic brain tumors.
Collapse
Affiliation(s)
- Xiaochu Tong
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China
| | - Dingyan Wang
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China
| | - Xiaoyu Ding
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China
| | - Xiaoqin Tan
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China
| | - Qun Ren
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,Nanjing University of Chinese Medicine, 138 Xianlin Road, Nanjing, 210023, China
| | - Geng Chen
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China.,School of Pharmaceutical Science and Technology, Hangzhou Institute for Advanced Study, UCAS, Hangzhou, 310024, China
| | - Yu Rong
- Tencent AI Lab, Shenzhen, 518057, China
| | | | | | - Hualiang Jiang
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China.,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China
| | - Mingyue Zheng
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China. .,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China.
| | - Xutong Li
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai, 201203, China. .,University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing, 100049, China.
| |
Collapse
|
25
|
Fathabadi A, Seyedian SM, Malekian A. Comparison of Bayesian, k-Nearest Neighbor and Gaussian process regression methods for quantifying uncertainty of suspended sediment concentration prediction. Sci Total Environ 2022; 818:151760. [PMID: 34801498 DOI: 10.1016/j.scitotenv.2021.151760] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/27/2021] [Revised: 11/13/2021] [Accepted: 11/13/2021] [Indexed: 06/13/2023]
Abstract
Suspended sediment transport in river system is a complex process influenced by many factors that their interactions lead to nonlinear and high scatter of concentration-discharge relationships. This makes the model prediction subject to high uncertainty and providing one value as the model prediction is somehow useless and cannot provide adequate information about the model accuracy and associated uncertainty. Current study compares the efficiency of Bayesian (i.e. Bayesian segmented linear regression (BSLR) and Bayesian linear model (BLR)), Gaussian Process Regression (GPR) and k-Nearest Neighbor (k-NN) in quantifying uncertainty of the suspended sediment concentration prediction in three watersheds namely Arazkoseh, Oghan and Jajrood located in Iran. Three input combinations including, contemporary discharge, slow and quick flow components and contemporary, one and two antecedent days discharge, were used. The BSLR model was able to identify threshold value, furthermore, pre-threshold and post-threshold slopes of BSLR model indicated that for Arazkoseh watershed channel and for Oghan and Jajrood watersheds, upland area are dominate sediment sources. In all three studied cases, given prediction interval width and the percent of enclosed observed data by prediction interval, k-NN model provided more reliable prediction interval. Moreover, separation stream flow into slow and quick flow components lead to improved performance of GPR and k-NN models in the studied watersheds, and the best results for Arazkoseh and Oghan watersheds were obtained when slow and quick flow components were used as the model input.
Collapse
Affiliation(s)
- Aboalhasan Fathabadi
- Department of Range and Watershed Management, Gonbad Kavous University, Gonbad Kavous, Golestan Province, Iran.
| | - Seyed Morteza Seyedian
- Department of Range and Watershed Management, Gonbad Kavous University, Gonbad Kavous, Golestan Province, Iran
| | - Arash Malekian
- Faculty of Natural Resources, University of Tehran, Tehran, Iran
| |
Collapse
|
26
|
Ran X, Xu M, Mei L, Xu Q, Liu Q. Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation. Neural Netw 2021; 145:199-208. [PMID: 34768090 DOI: 10.1016/j.neunet.2021.10.020] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2020] [Revised: 08/28/2021] [Accepted: 10/22/2021] [Indexed: 10/20/2022]
Abstract
Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to out-of-distribution (OOD) inputs than in-distribution (ID) inputs. To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs. In this study, we propose an improved noise contrastive prior (INCP) to be able to integrate into the encoder of VAEs, called INCPVAE. INCP is scalable, trainable and compatible with VAEs, and it also adopts the merits from the INCP for uncertainty estimation. Experiments on various datasets demonstrate that compared to the standard VAEs, our model is superior in uncertainty estimation for the OOD data and is robust in anomaly detection tasks. The INCPVAE model obtains reliable uncertainty estimation for OOD inputs and solves the OOD problem in VAE models.
Collapse
Affiliation(s)
- Xuming Ran
- Shenzhen Key Laboratory of Smart Healthcare Engineering, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, China; College of Mathematics and Statistics, Chongqing Jiaotong University, Chongqing 400074, China.
| | - Mingkun Xu
- Center for Brain Inspired Computing Research, Department of Precision Instrument, Tsinghua University, Beijing 100084, China
| | - Lingrui Mei
- China Automotive Engineering Research Institute, Chongqing 401122, China
| | - Qi Xu
- School of Artifical Intelligence, Electronic and Electrical Engineering, School of Artifical Intelligence Dalian University of Technology, Dalian 116024, China; College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
| | - Quanying Liu
- Shenzhen Key Laboratory of Smart Healthcare Engineering, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, China.
| |
Collapse
|
27
|
Mervin LH, Trapotsi MA, Afzal AM, Barrett IP, Bender A, Engkvist O. Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty. J Cheminform 2021; 13:62. [PMID: 34412708 PMCID: PMC8375213 DOI: 10.1186/s13321-021-00539-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2021] [Accepted: 07/30/2021] [Indexed: 11/24/2022] Open
Abstract
Measurements of protein–ligand interactions have reproducibility limits due to experimental errors. Any model based on such assays will consequentially have such unavoidable errors influencing their performance which should ideally be factored into modelling and output predictions, such as the actual standard deviation of experimental measurements (σ) or the associated comparability of activity values between the aggregated heterogenous activity units (i.e., Ki versus IC50 values) during dataset assimilation. However, experimental errors are usually a neglected aspect of model generation. In order to improve upon the current state-of-the-art, we herein present a novel approach toward predicting protein–ligand interactions using a Probabilistic Random Forest (PRF) classifier. The PRF algorithm was applied toward in silico protein target prediction across ~ 550 tasks from ChEMBL and PubChem. Predictions were evaluated by taking into account various scenarios of experimental standard deviations in both training and test sets and performance was assessed using fivefold stratified shuffled splits for validation. The largest benefit in incorporating the experimental deviation in PRF was observed for data points close to the binary threshold boundary, when such information was not considered in any way in the original RF algorithm. For example, in cases when σ ranged between 0.4–0.6 log units and when ideal probability estimates between 0.4–0.6, the PRF outperformed RF with a median absolute error margin of ~ 17%. In comparison, the baseline RF outperformed PRF for cases with high confidence to belong to the active class (far from the binary decision threshold), although the RF models gave errors smaller than the experimental uncertainty, which could indicate that they were overtrained and/or over-confident. Finally, the PRF models trained with putative inactives decreased the performance compared to PRF models without putative inactives and this could be because putative inactives were not assigned an experimental pXC50 value, and therefore they were considered inactives with a low uncertainty (which in practice might not be true). In conclusion, PRF can be useful for target prediction models in particular for data where class boundaries overlap with the measurement uncertainty, and where a substantial part of the training data is located close to the classification threshold.
Collapse
Affiliation(s)
- Lewis H Mervin
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK.
| | - Maria-Anna Trapotsi
- Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK
| | - Avid M Afzal
- Data Sciences & Quantitative Biology, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK
| | - Ian P Barrett
- Data Sciences & Quantitative Biology, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK
| | - Andreas Bender
- Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK
| | - Ola Engkvist
- Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden.,Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden
| |
Collapse
|
28
|
Sousa VK, Pedro JAF, Kumagai PS, Lopes JLS. Effect of setting data collection parameters on the reliability of a circular dichroism spectrum. Eur Biophys J 2021; 50:687-97. [PMID: 33538870 DOI: 10.1007/s00249-021-01499-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/18/2020] [Revised: 11/12/2020] [Accepted: 01/13/2021] [Indexed: 10/22/2022]
Abstract
Circular dichroism (CD) spectroscopy is a well-established biophysical technique used to investigate the structure of molecules. The analysis of a protein CD spectrum depends on the quality of the original CD data, which can be affected by the sample purity, background absorption of the additives/solvent/buffer, the choice of the parameters used for data collection, etc. In this paper, the CD spectrum of myoglobin was used as a model to exploit how variations on each data collection parameter could affect the final protein CD spectrum and, the subsequent effect of them on the quantitative analysis of protein secondary structure. Bioinformatics analysis carried out with SESCA package and PDBMD2CD server predicted a theoretical myoglobin CD spectrum, and a Monte Carlo-like model was implemented to estimate the uncertainty in secondary structure predictions performed with CDSSTR, Selcon 3 and ContinLL algorithms. An inappropriate choice of data collection parameters can lead to a misinterpretation of the CD data in terms of the protein structural content.
Collapse
|
29
|
Petit O, Thome N, Soler L. Iterative confidence relabeling with deep ConvNets for organ segmentation with partial labels. Comput Med Imaging Graph 2021; 91:101938. [PMID: 34153879 DOI: 10.1016/j.compmedimag.2021.101938] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2020] [Revised: 03/22/2021] [Accepted: 04/27/2021] [Indexed: 11/16/2022]
Abstract
Training deep ConvNets requires large labeled datasets. However, collecting pixel-level labels for medical image segmentation is very expensive and requires a high level of expertise. In addition, most existing segmentation masks provided by clinical experts focus on specific anatomical structures. In this paper, we propose a method dedicated to handle such partially labeled medical image datasets. We propose a strategy to identify pixels for which labels are correct, and to train Fully Convolutional Neural Networks with a multi-label loss adapted to this context. In addition, we introduce an iterative confidence self-training approach inspired by curriculum learning to relabel missing pixel labels, which relies on selecting the most confident prediction with a specifically designed confidence network that learns an uncertainty measure which is leveraged in our relabeling process. Our approach, INERRANT for Iterative coNfidencE Relabeling of paRtial ANnoTations, is thoroughly evaluated on two public datasets (TCAI and LITS), and one internal dataset with seven abdominal organ classes. We show that INERRANT robustly deals with partial labels, performing similarly to a model trained on all labels even for large missing label proportions. We also highlight the importance of our iterative learning scheme and the proposed confidence measure for optimal performance. Finally we show a practical use case where a limited number of completely labeled data are enriched by publicly available but partially labeled data.
Collapse
Affiliation(s)
- Olivier Petit
- CEDRIC, Conservatoire National des Arts et Metiers, 292 rue Saint-Martin, Paris, 75003, France; Visible Patient, 8 rue Gustave Adolphe Hirn, Strasbourg, 67000, France.
| | - Nicolas Thome
- CEDRIC, Conservatoire National des Arts et Metiers, 292 rue Saint-Martin, Paris, 75003, France
| | - Luc Soler
- Visible Patient, 8 rue Gustave Adolphe Hirn, Strasbourg, 67000, France
| |
Collapse
|
30
|
Calderon-Ramirez S, Yang S, Moemeni A, Colreavy-Donnelly S, Elizondo DA, Oala L, Rodriguez-Capitan J, Jimenez-Navarro M, Lopez-Rubio E, Molina-Cabello MA. Improving Uncertainty Estimation With Semi-Supervised Deep Learning for COVID-19 Detection Using Chest X-Ray Images. IEEE Access 2021; 9:85442-85454. [PMID: 34812397 PMCID: PMC8545186 DOI: 10.1109/access.2021.3085418] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/14/2021] [Accepted: 05/24/2021] [Indexed: 05/02/2023]
Abstract
In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.
Collapse
Affiliation(s)
- Saul Calderon-Ramirez
- School of Computer Science and InformaticsDe Montfort University Leicester LE1 9BH U.K
- Instituto Tecnologico de Costa Rica Cartago 30101 Costa Rica
| | - Shengxiang Yang
- School of Computer Science and InformaticsDe Montfort University Leicester LE1 9BH U.K
| | - Armaghan Moemeni
- School of Computer ScienceUniversity of Nottingham Nottingham NG8 1BB U.K
| | | | - David A Elizondo
- School of Computer Science and InformaticsDe Montfort University Leicester LE1 9BH U.K
| | - Luis Oala
- XAI GroupArtificial Intelligence DepartmentFraunhofer Heinrich Hertz Institute 10587 Berlin Germany
| | - Jorge Rodriguez-Capitan
- CIBERCVHospital Universitario Virgen de la Victoria 29010 Málaga Spain
- Instituto de Investigación Biomédica de Mñlaga (IBIMA) 29010 Málaga Spain
| | - Manuel Jimenez-Navarro
- CIBERCVHospital Universitario Virgen de la Victoria 29010 Málaga Spain
- Instituto de Investigación Biomédica de Mñlaga (IBIMA) 29010 Málaga Spain
| | - Ezequiel Lopez-Rubio
- Department of Computer Languages and Computer ScienceUniversity of Málaga 29071 Málaga Spain
- Instituto de Investigación Biomédica de Mñlaga (IBIMA) 29010 Málaga Spain
| | - Miguel A Molina-Cabello
- Department of Computer Languages and Computer ScienceUniversity of Málaga 29071 Málaga Spain
- Instituto de Investigación Biomédica de Mñlaga (IBIMA) 29010 Málaga Spain
| |
Collapse
|
31
|
Wang H, Lu K, Zhao Y, Zhang J, Hua J, Lin X. Multi-model ensemble simulated non-point source pollution based on Bayesian model averaging method and model uncertainty analysis. Environ Sci Pollut Res Int 2020; 27:44482-44493. [PMID: 32772284 DOI: 10.1007/s11356-020-10336-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/27/2020] [Accepted: 07/30/2020] [Indexed: 06/11/2023]
Abstract
Watershed models are cost-effective and powerful tools for evaluating and controlling non-point source pollution (NPSP), while the reliability of watershed models in a management context depends largely on inherent uncertainties in model predictions. The objective of this study is to present the use of multi-model ensemble applied to streamflow, total nitrogen (TN), and total phosphorus (TP) simulation and quantify the uncertainty resulting from model structure. In this study, three watershed models, which have different structures in simulating NPSP, were selected to conduct watershed monthly streamflow, TN load, and TP load ensemble simulation and 90% credible intervals based on Bayesian model averaging (BMA) method. The result using the observed data of the Yixunhe watershed revealed that the coefficient of determination and Nash-Sutcliffe coefficient of the BMA model simulate streamflow, TN load, and TP load were better than that of the single model. The higher the efficiency of a single model is, the greater the weight during the BMA ensemble simulation is. The 90% credible interval of BMA has a high coverage of measured values in this study. This indicates that the BMA method can not only provide simulation with better precision through ensemble simulation but also provide quantitative evaluation of the model structure through interval, which could offer rich information of the NPSP simulation and management.
Collapse
Affiliation(s)
- Huiliang Wang
- College of Water Conservancy Engineering, Zhengzhou University, Zhengzhou, 450001, Henan, People's Republic of China
| | - Keyu Lu
- College of Water Conservancy Engineering, Zhengzhou University, Zhengzhou, 450001, Henan, People's Republic of China
| | - Yulong Zhao
- College of Water Conservancy Engineering, Zhengzhou University, Zhengzhou, 450001, Henan, People's Republic of China
| | - Jinxia Zhang
- Zhengzhou Hydrology and Water Resource Survey Bureau, Zhengzhou, 450003, Henan, People's Republic of China
| | - Jianli Hua
- Henan GRG Metrology &Test Co, LTD, Zhengzhou, 450001, Henan, People's Republic of China
| | - Xiaoying Lin
- College of Water Conservancy Engineering, Zhengzhou University, Zhengzhou, 450001, Henan, People's Republic of China.
| |
Collapse
|
32
|
Molina C, Andrade C, Manzano CA, Richard Toro A, Verma V, Leiva-Guzmán MA. Dithiothreitol-based oxidative potential for airborne particulate matter: an estimation of the associated uncertainty. Environ Sci Pollut Res Int 2020; 27:29672-29680. [PMID: 32500499 DOI: 10.1007/s11356-020-09508-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/04/2020] [Accepted: 05/28/2020] [Indexed: 05/23/2023]
Abstract
Oxidative stress is considered as one of the main mechanisms by which airborne particles produce adverse health effects. Several methods to estimate the oxidative potential (OP) of particulate matter (PM) have been proposed. Among them, the dithiothreitol (DTT) assay has gained popularity due to its simplicity and overall low implementation cost. Usually, the estimations of OPDTT are based on n-replicates of a set of samples and their associated standard deviation. However, interlaboratory comparisons of OPDTT can be difficult and lead to misinterpretations. This work presents an estimation of the total uncertainty for the OPDTT measurement of PM10 and PM2.5 samples collected in Santiago (Chile), based on recommendations by the Joint Committee for Guides in Metrology and Eurachem. The expanded uncertainty expressed as a percentage of the mass-normalized OPDTT measurements was 18.0% and 16.3% for PM10 and PM2.5 samples respectively. The dominating contributor to the total uncertainty was identified (i.e., DTT consumption rate, related to the regression and repeatability of experimental data), while the volumetric operations (i.e., pipettes) were also important. The results showed that, although the OP measured following the DTT assay has been successfully used to estimate the potential health impacts of airborne PM, uncertainty estimations must be considered before interpreting the results.
Collapse
Affiliation(s)
- Carolina Molina
- Department of Chemistry, Faculty of Science, Universidad de Chile, Las Palmeras 3425, Ñuñoa, Santiago, RM, Chile
| | - Catalina Andrade
- Department of Chemistry, Faculty of Science, Universidad de Chile, Las Palmeras 3425, Ñuñoa, Santiago, RM, Chile
| | - Carlos A Manzano
- Department of Chemistry, Faculty of Science, Universidad de Chile, Las Palmeras 3425, Ñuñoa, Santiago, RM, Chile
- School of Public Health, San Diego State University, 5500 Campanile Dr, San Diego, CA, 92182, USA
| | - A Richard Toro
- Department of Chemistry, Faculty of Science, Universidad de Chile, Las Palmeras 3425, Ñuñoa, Santiago, RM, Chile
| | - Vishal Verma
- Civil and Environmental Engineering, University of Illinois at Urbana-Champaign, Champaign, IL, 61820, USA
| | - Manuel A Leiva-Guzmán
- Department of Chemistry, Faculty of Science, Universidad de Chile, Las Palmeras 3425, Ñuñoa, Santiago, RM, Chile.
| |
Collapse
|
33
|
Poureh A, Nobakhti A. Robust control design for an industrial wind turbine with HIL simulations. ISA Trans 2020; 103:252-265. [PMID: 32444213 DOI: 10.1016/j.isatra.2020.05.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/16/2019] [Revised: 04/08/2020] [Accepted: 05/04/2020] [Indexed: 06/11/2023]
Abstract
This paper describes the design and implementation of a H∞-based robust controller for a commercial 2MW variable-speed variable-pitch wind turbine. The single controller is able to deliver specification performance for the entire full load region. Various aspects of modeling and design procedures including reduced order model validation, torsional mode damping of drivetrain and uncertainty estimation are explained in detail. To make the design more reliable and industrially attractive, simple routines for the derivation of required weighting functions are introduced. To investigate the benefits of the suggested design, its closed-loop performance is compared with the wind turbine's baseline controller and an alternative state-space controller proposed in the literature. This is first evaluated using a FAST-based simulator under IEC-61400 compatible scenarios. It is then verified by a real-life hardware in the loop simulator using an industrial PLC.
Collapse
Affiliation(s)
- Ali Poureh
- Power Plant Monitoring and Control Department, Niroo Research Institute, Dadman Blvd., Tehran, P.O. Box 14686-17151, Iran.
| | - Amin Nobakhti
- Electrical Engineering Department, Sharif University of Technology, Azadi Ave, Tehran, P.O. Box 11365-9363, Iran.
| |
Collapse
|
34
|
Luo M, Pan C, Liu C. Modeling study on the time-varying process of sediment trapping in vegetative filter strips. Sci Total Environ 2020; 725:138361. [PMID: 32302837 DOI: 10.1016/j.scitotenv.2020.138361] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/01/2020] [Revised: 03/29/2020] [Accepted: 03/30/2020] [Indexed: 06/11/2023]
Abstract
Vegetative filter strips (VFS) play an important role in reducing erosion, retaining runoff, and trapping sediment. The bed surface of a VFS is dynamic during continuous sediment deposition, which makes it difficult to determine the sediment transport capacity of overland flow in real time. This study described this process from a systematic perspective. Based on self-feedback theory, an ordinary differential equation was established with a self-inhibition correction factor and its analytical solution was obtained. A sediment-trapping-process model of VFS (STPMOD-VFS) was proposed. Then, the sediment trapping processes of three experiments under different conditions were predicted using the STPMOD-VFS, and the prediction was considered highly satisfactory. The uncertainty estimation results showed the STPMOD-VFS had significant 'equifinality' performance. The sensitivity of different parameters of the STPMOD-VFS was found significantly different. The parameters related to the sediment delivery rate of silt-laden inflow and those that control the attenuation coefficients of the instantaneous sediment trapping efficiency of the VFS were sensitive, while those parameters that control the initial sediment outflow rate were less sensitive. Finally, an equation describing the sediment trapping process by a VFS under a dynamic sediment inflow rate was built and solved, and a general expression for the VFS sediment trapping time-varying process was given. The findings of this study could help in evaluation of sediment processes on grassed hillslopes.
Collapse
Affiliation(s)
- Mingjie Luo
- Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, College of Water Sciences, Beijing Normal University, No. 19 Xinjiekouwai Street, Beijing 100875, PR China.
| | - Chengzhong Pan
- Key Laboratory of Water Sediment Sciences, College of Water Sciences, Beijing Normal University, No. 19 Xinjiekouwai Street, Beijing 100875, PR China.
| | - Chunlei Liu
- College of Water Sciences, Beijing Normal University, No. 19 Xinjiekouwai Street, Beijing 100875, PR China
| |
Collapse
|
35
|
Xia Y, Yang D, Yu Z, Liu F, Cai J, Yu L, Zhu Z, Xu D, Yuille A, Roth H. Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation. Med Image Anal 2020; 65:101766. [PMID: 32623276 DOI: 10.1016/j.media.2020.101766] [Citation(s) in RCA: 60] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2019] [Revised: 04/23/2020] [Accepted: 06/22/2020] [Indexed: 10/24/2022]
Abstract
Although having achieved great success in medical image segmentation, deep learning-based approaches usually require large amounts of well-annotated data, which can be extremely expensive in the field of medical image analysis. Unlabeled data, on the other hand, is much easier to acquire. Semi-supervised learning and unsupervised domain adaptation both take the advantage of unlabeled data, and they are closely related to each other. In this paper, we propose uncertainty-aware multi-view co-training (UMCT), a unified framework that addresses these two tasks for volumetric medical image segmentation. Our framework is capable of efficiently utilizing unlabeled data for better performance. We firstly rotate and permute the 3D volumes into multiple views and train a 3D deep network on each view. We then apply co-training by enforcing multi-view consistency on unlabeled data, where an uncertainty estimation of each view is utilized to achieve accurate labeling. Experiments on the NIH pancreas segmentation dataset and a multi-organ segmentation dataset show state-of-the-art performance of the proposed framework on semi-supervised medical image segmentation. Under unsupervised domain adaptation settings, we validate the effectiveness of this work by adapting our multi-organ segmentation model to two pathological organs from the Medical Segmentation Decathlon Datasets. Additionally, we show that our UMCT-DA model can even effectively handle the challenging situation where labeled source data is inaccessible, demonstrating strong potentials for real-world applications.
Collapse
Affiliation(s)
- Yingda Xia
- Johns Hopkins Unversity, Baltimore, MD, 21218, USA
| | - Dong Yang
- NVIDIA Corporation, Bethesda, MD, 20814, USA
| | - Zhiding Yu
- NVIDIA Corporation, Bethesda, MD, 20814, USA
| | - Fengze Liu
- Johns Hopkins Unversity, Baltimore, MD, 21218, USA
| | - Jinzheng Cai
- University of Florida, Gainesville, FL, 32611, USA
| | - Lequan Yu
- The Chinese University of Hong Kong, Hong Kong, China
| | - Zhuotun Zhu
- Johns Hopkins Unversity, Baltimore, MD, 21218, USA
| | - Daguang Xu
- NVIDIA Corporation, Bethesda, MD, 20814, USA
| | - Alan Yuille
- Johns Hopkins Unversity, Baltimore, MD, 21218, USA
| | - Holger Roth
- NVIDIA Corporation, Bethesda, MD, 20814, USA.
| |
Collapse
|
36
|
Wang G, Li W, Aertsen M, Deprest J, Ourselin S, Vercauteren T. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing 2019; 335:34-45. [PMID: 31595105 PMCID: PMC6783308 DOI: 10.1016/j.neucom.2019.01.103] [Citation(s) in RCA: 136] [Impact Index Per Article: 27.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks at both pixel level and structure level. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different transformations of the input image on the segmentation output. Test-time augmentation has been previously used to improve segmentation accuracy, yet not been formulated in a consistent mathematical framework. Hence, we also propose a theoretical formulation of test-time augmentation, where a distribution of the prediction is estimated by Monte Carlo simulation with prior distributions of parameters in an image acquisition model that involves image transformations and noise. We compare and combine our proposed aleatoric uncertainty with model uncertainty. Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images (MRI) showed that 1) the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating the test-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions, and 2) our test-time augmentation outperforms a single-prediction baseline and dropout-based multiple predictions.
Collapse
Affiliation(s)
- Guotai Wang
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK
- School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Wenqi Li
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK
| | - Michael Aertsen
- Department of Radiology, University Hospitals Leuven, Leuven, Belgium
| | - Jan Deprest
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK
- Department of Radiology, University Hospitals Leuven, Leuven, Belgium
- Institute for Women’s Health, University College London, London, UK
- Department of Obstetrics and Gynaecology, University Hospitals Leuven, Leuven, Belgium
| | - Sébastien Ourselin
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK
| | - Tom Vercauteren
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK
- Department of Obstetrics and Gynaecology, University Hospitals Leuven, Leuven, Belgium
| |
Collapse
|
37
|
Buyukada M. Investigation of thermal conversion characteristics and performance evaluation of co-combustion of pine sawdust and lignite coal using TGA, artificial neural network modeling and likelihood method. Bioresour Technol 2019; 287:121461. [PMID: 31121444 DOI: 10.1016/j.biortech.2019.121461] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/25/2019] [Revised: 05/08/2019] [Accepted: 05/10/2019] [Indexed: 06/09/2023]
Abstract
(Co-)combustion of pine sawdust (PS) and lignite coal (LC) were investigated using artificial neural networks (ANN), particle swarm optimization (PSO), and Monte Carlo simulation (MC) as a function of blend ratio, heating rate, and temperature via thermal conversion characteristics. The order of degraded compounds in terms of hemi-cellulosic and lignin-based compounds demonstrated the main oxidation and degradation mechanism of co-combustion of PS and LC. The best prediction (R2 of 99.99%) was obtained by ANN28 model. Operating conditions of 90LC10PS, 425 °C, and 19 °C min-1 were determined by PSO as optimum levels with TG value of 67.5%. Once three-replicated validation experiments were performed under PSO-optimized conditions, mean TG values ware observed as 67.5% with a standard deviation of ±0.4%. Consequently, MC was used to identify the stochastic variability and uncertainty associated with ANN models that were derived to predict TG values.
Collapse
Affiliation(s)
- Musa Buyukada
- Department of Chemical Engineering, Bolu Abant Izzet Baysal University, 14030 Bolu, Turkey.
| |
Collapse
|
38
|
Sokooti H, Saygili G, Glocker B, Lelieveldt BPF, Staring M. Quantitative error prediction of medical image registration using regression forests. Med Image Anal 2019; 56:110-121. [PMID: 31226661 DOI: 10.1016/j.media.2019.05.005] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2018] [Revised: 04/25/2019] [Accepted: 05/10/2019] [Indexed: 11/17/2022]
Abstract
Predicting registration error can be useful for evaluation of registration procedures, which is important for the adoption of registration techniques in the clinic. In addition, quantitative error prediction can be helpful in improving the registration quality. The task of predicting registration error is demanding due to the lack of a ground truth in medical images. This paper proposes a new automatic method to predict the registration error in a quantitative manner, and is applied to chest CT scans. A random regression forest is utilized to predict the registration error locally. The forest is built with features related to the transformation model and features related to the dissimilarity after registration. The forest is trained and tested using manually annotated corresponding points between pairs of chest CT scans in two experiments: SPREAD (trained and tested on SPREAD) and inter-database (including three databases SPREAD, DIR-Lab-4DCT and DIR-Lab-COPDgene). The results show that the mean absolute errors of regression are 1.07 ± 1.86 and 1.76 ± 2.59 mm for the SPREAD and inter-database experiment, respectively. The overall accuracy of classification in three classes (correct, poor and wrong registration) is 90.7% and 75.4%, for SPREAD and inter-database respectively. The good performance of the proposed method enables important applications such as automatic quality control in large-scale image analysis.
Collapse
Affiliation(s)
- Hessam Sokooti
- Leiden University Medical Center, Leiden, the Netherlands.
| | - Gorkem Saygili
- Leiden University Medical Center, Leiden, the Netherlands
| | | | - Boudewijn P F Lelieveldt
- Leiden University Medical Center, Leiden, the Netherlands; Delft University of Technology, Delft, the Netherlands
| | - Marius Staring
- Leiden University Medical Center, Leiden, the Netherlands; Delft University of Technology, Delft, the Netherlands
| |
Collapse
|
39
|
Guichard N, Rudaz S, Bonnabry P, Fleury-Souverain S. Validation and uncertainty estimation for trace amounts determination of 25 drugs used in hospital chemotherapy compounding units. J Pharm Biomed Anal 2019; 172:139-148. [PMID: 31035095 DOI: 10.1016/j.jpba.2019.04.042] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2019] [Revised: 04/09/2019] [Accepted: 04/20/2019] [Indexed: 11/25/2022]
Abstract
The validation and uncertainty assessment of the analytical method developed for the simultaneous determination of 25 anticancer drugs commonly handled in hospital pharmacy was reported. Selected compounds were 5-fluorouracil, cytarabine, fludarabine phosphate, ganciclovir, gemcitabine, dacarbazine, methotrexate, pemetrexed, busulfan, raltitrexed, etoposide phosphate, topotecan, ifosfamide, cyclophosphamide, irinotecan, doxorubicin, epirubicin, daunorubicin, idarubicin, vincristine, vinblastine, vinorelbine, docetaxel and paclitaxel. Accuracy and uncertainty profiles were obtained for all compounds. Quantitative performances were satisfactory in term of specificity, sensitivity, precision and accuracy. Repeatability (1.9-25.4%) and intermediate precision (2.7-29%) were determined for all target compounds. Lower limits of quantification between 1 and 25 ng/mL were obtained. Uncertainty associated to measurement of routine samples was evaluated. The multi-targeted method was specific and reliable and was successfully applied to wipe samples from hospital pharmacy chemotherapy compounding unit and to the determination of outside contamination of vials from pharmaceutical manufacturers.
Collapse
Affiliation(s)
- Nicolas Guichard
- School of Pharmaceutical Sciences, University of Geneva, University of Lausanne, CMU - Rue Michel Servet 1, 1211, Geneva 4, Switzerland; Pharmacy, Geneva University Hospitals (HUG), Geneva, Switzerland.
| | - Serge Rudaz
- School of Pharmaceutical Sciences, University of Geneva, University of Lausanne, CMU - Rue Michel Servet 1, 1211, Geneva 4, Switzerland
| | - Pascal Bonnabry
- School of Pharmaceutical Sciences, University of Geneva, University of Lausanne, CMU - Rue Michel Servet 1, 1211, Geneva 4, Switzerland; Pharmacy, Geneva University Hospitals (HUG), Geneva, Switzerland
| | - Sandrine Fleury-Souverain
- School of Pharmaceutical Sciences, University of Geneva, University of Lausanne, CMU - Rue Michel Servet 1, 1211, Geneva 4, Switzerland; Pharmacy, Geneva University Hospitals (HUG), Geneva, Switzerland
| |
Collapse
|
40
|
Adler TJ, Ardizzone L, Vemuri A, Ayala L, Gröhl J, Kirchner T, Wirkert S, Kruse J, Rother C, Köthe U, Maier-Hein L. Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks. Int J Comput Assist Radiol Surg 2019; 14:997-1007. [PMID: 30903566 DOI: 10.1007/s11548-019-01939-9] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2019] [Accepted: 03/07/2019] [Indexed: 10/27/2022]
Abstract
PURPOSE Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral reflectance measurements to underlying tissue parameters, such as oxygenation. Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed. METHODS We present a novel approach to the assessment of optical imaging modalities, which is sensitive to the different types of uncertainties that may occur when inferring tissue parameters. Based on the concept of invertible neural networks, our framework goes beyond point estimates and maps each multispectral measurement to a full posterior probability distribution which is capable of representing ambiguity in the solution via multiple modes. Performance metrics for a hardware setup can then be computed from the characteristics of the posteriors. RESULTS Application of the assessment framework to the specific use case of camera selection for physiological parameter estimation yields the following insights: (1) estimation of tissue oxygenation from multispectral images is a well-posed problem, while (2) blood volume fraction may not be recovered without ambiguity. (3) In general, ambiguity may be reduced by increasing the number of spectral bands in the camera. CONCLUSION Our method could help to optimize optical camera design in an application-specific manner.
Collapse
Affiliation(s)
- Tim J Adler
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany. .,Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany.
| | | | - Anant Vemuri
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany
| | - Leonardo Ayala
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany
| | - Janek Gröhl
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany.,Medical Faculty, Heidelberg University, Heidelberg, Germany
| | - Thomas Kirchner
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany.,Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany
| | - Sebastian Wirkert
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany
| | - Jakob Kruse
- Visual Learning Lab, Heidelberg University, Heidelberg, Germany
| | - Carsten Rother
- Visual Learning Lab, Heidelberg University, Heidelberg, Germany
| | - Ullrich Köthe
- Visual Learning Lab, Heidelberg University, Heidelberg, Germany
| | - Lena Maier-Hein
- Computer Assisted Medical Interventions, Deutsches Krebsforschungszentrum, Im Neuenheimer Feld 223, 69120, Heidelberg, Germany
| |
Collapse
|
41
|
Rocha WFC, Sheen DA, Bearden DW. Classification of samples from NMR-based metabolomics using principal components analysis and partial least squares with uncertainty estimation. Anal Bioanal Chem 2018; 410:6305-19. [PMID: 30043113 DOI: 10.1007/s00216-018-1240-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2018] [Revised: 06/14/2018] [Accepted: 07/02/2018] [Indexed: 12/18/2022]
Abstract
Recent progress in metabolomics has been aided by the development of analysis techniques such as gas and liquid chromatography coupled with mass spectrometry (GC-MS and LC-MS) and nuclear magnetic resonance (NMR) spectroscopy. The vast quantities of data produced by these techniques has resulted in an increase in the use of machine algorithms that can aid in the interpretation of this data, such as principal components analysis (PCA) and partial least squares (PLS). Techniques such as these can be applied to biomarker discovery, interlaboratory comparison, and clinical diagnoses. However, there is a lingering question whether the results of these studies can be applied to broader sets of clinical data, usually taken from different data sources. In this work, we address this question by creating a metabolomics workflow that combines a previously published consensus analysis procedure ( https://doi.org/10.1016/j.chemolab.2016.12.010 ) with PCA and PLS models using uncertainty analysis based on bootstrapping. This workflow is applied to NMR data that come from an interlaboratory comparison study using synthetic and biologically obtained metabolite mixtures. The consensus analysis identifies trusted laboratories, whose data are used to create classification models that are more reliable than without. With uncertainty analysis, the reliability of the classification can be rigorously quantified, both for data from the original set and from new data that the model is analyzing. Graphical abstract ᅟ.
Collapse
|
42
|
Terán-Baamonde J, Soto-Ferreiro RM, Carlosena A, Andrade JM, Prada D. Determination of cadmium in sediments by diluted HCI extraction and isotope dilution ICP-MS. Talanta 2018; 186:272-278. [PMID: 29784360 DOI: 10.1016/j.talanta.2018.04.054] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2017] [Revised: 04/17/2018] [Accepted: 04/19/2018] [Indexed: 10/17/2022]
Abstract
Isotope dilution ICP-MS is proposed to measure the mass fraction of Cd extracted by diluted HCl in marine sediments, using a fast and simple extraction procedure based on ultrasonic probe agitation. The 111Cd isotope was added before the extraction to achieve isotope equilibration with native Cd solubilized from the sample. The parameters affecting trueness and precision of isotope ratio measurements were evaluated carefully and subsequently corrected in order to minimize errors; they were: detector dead time, spectral interferences, mass discrimination factor and optimum sample/spike ratio. The mass fraction of Cd extracted was compared with the sum of the certified contents of the three steps of the sequential extraction procedure of the Standards, Measurements and Testing Programme (SM&T) analysing the BCR 701 sediment to validate the method. The certified and measured values agreed, giving a measured / certified mass fraction ratio of 1.05. Further, the extraction procedure itself was studied by adding the enriched isotope after the extraction step, which allowed verifying that analyte losses occurred during this process. Two additional reference sediments with certified total cadmium contents were also analysed. The method provided very good precision (0.9%, RSD) and a low detection limit, 1.8 ng g-1. The procedural uncertainty budget was estimated following the EURACHEM Guide by means of the 'GUM Workbench' software, obtaining a relative expanded uncertainty of 1.5%. The procedure was applied to determine the bioaccessible mass fraction of Cd in sediments from two environmentally and economically important areas of Galicia (rias of Arousa and Vigo, NW of Spain).
Collapse
Affiliation(s)
- Javier Terán-Baamonde
- Grupo Química Analítica Aplicada (QANAP), Instituto Universitario de Medio Ambiente (IUMA), Centro de Investigacións Científicas Avanzadas (CICA), Facultad de Ciencias, Universidade da Coruña, 15071 A Coruña, Spain
| | - Rosa-María Soto-Ferreiro
- Grupo Química Analítica Aplicada (QANAP), Instituto Universitario de Medio Ambiente (IUMA), Centro de Investigacións Científicas Avanzadas (CICA), Facultad de Ciencias, Universidade da Coruña, 15071 A Coruña, Spain.
| | - Alatzne Carlosena
- Grupo Química Analítica Aplicada (QANAP), Instituto Universitario de Medio Ambiente (IUMA), Centro de Investigacións Científicas Avanzadas (CICA), Facultad de Ciencias, Universidade da Coruña, 15071 A Coruña, Spain
| | - José-Manuel Andrade
- Grupo Química Analítica Aplicada (QANAP), Instituto Universitario de Medio Ambiente (IUMA), Centro de Investigacións Científicas Avanzadas (CICA), Facultad de Ciencias, Universidade da Coruña, 15071 A Coruña, Spain
| | - Darío Prada
- Grupo Química Analítica Aplicada (QANAP), Instituto Universitario de Medio Ambiente (IUMA), Centro de Investigacións Científicas Avanzadas (CICA), Facultad de Ciencias, Universidade da Coruña, 15071 A Coruña, Spain
| |
Collapse
|
43
|
Petrarca MH, Rosa MA, Queiroz SCN, Godoy HT. Simultaneous determination of acrylamide and 4-hydroxy-2,5-dimethyl-3(2H)-furanone in baby food by liquid chromatography-tandem mass spectrometry. J Chromatogr A 2017; 1522:62-69. [PMID: 28985902 DOI: 10.1016/j.chroma.2017.09.052] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2017] [Revised: 08/24/2017] [Accepted: 09/22/2017] [Indexed: 11/16/2022]
Abstract
A liquid chromatography triple quadrupole mass spectrometry method was developed and validated for the simultaneous determination of acrylamide and 4-hydroxy-2,5-dimethyl-3(2H)-furanone (HDMF) in baby food. The sample preparation involves acetonitrile-based extraction combined with dispersive primary secondary amine (PSA) cleanup and cation-exchange solid-phase extraction (SPE), which promotes efficient removal of matrix interferences. Analytical selectivity and sensitivity were achieved for the quantification of acrylamide and HDMF in complex matrices such as fruit, cereal and milk-based baby foods; furthermore, adequate linearity (range 10-300μgkg-1) in solvent and matrix-matched calibration curves, and appropriate recoveries (94-110%) and precision (RSD≤10%), under repeatability and within-laboratory reproducibility conditions, were also obtained. Expanded measurement uncertainty was estimated at the 20μgkg-1 level (limit of quantification) on the basis of data obtained from in-house validation, with values of 25.5 and 16.5% for acrylamide and HDMF, respectively. The fitness for purpose of developed method was verified by analyzing 15 commercial baby foods available in the Brazilian market. Acrylamide was detected in one plum-based baby food (35μgkg-1) while HDMF in 67% of the samples analyzed (levels between 25 and 262μgkg-1).
Collapse
Affiliation(s)
- Mateus Henrique Petrarca
- Department of Food Science, Faculty of Food Engineering, University of Campinas (UNICAMP), 13083-862 Campinas, SP, Brazil.
| | - Maria Aparecida Rosa
- Laboratory of Residues and Contaminants, Brazilian Agricultural Research Corporation, EMBRAPA Environment, 13820-000 Jaguariúna, SP, Brazil
| | - Sonia Claudia Nascimento Queiroz
- Laboratory of Residues and Contaminants, Brazilian Agricultural Research Corporation, EMBRAPA Environment, 13820-000 Jaguariúna, SP, Brazil
| | - Helena Teixeira Godoy
- Department of Food Science, Faculty of Food Engineering, University of Campinas (UNICAMP), 13083-862 Campinas, SP, Brazil
| |
Collapse
|
44
|
Ceccatelli A, Dybdal A, Fajgelj A, Pitois A. Calculation spreadsheet for uncertainty estimation of measurement results in gamma-ray spectrometry and its validation for quality assurance purpose. Appl Radiat Isot 2017; 124:7-15. [PMID: 28314164 DOI: 10.1016/j.apradiso.2017.03.002] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2016] [Revised: 12/20/2016] [Accepted: 03/02/2017] [Indexed: 10/20/2022]
Abstract
An Excel calculation spreadsheet has been developed to estimate the uncertainty of measurement results in γ-ray spectrometry. It considers all relevant uncertainty components and calculates the combined standard uncertainty of the measurement result. The calculation spreadsheet has been validated using two independent open access software and is available for download free of charge at: https://nucleus.iaea.org/rpst/ReferenceProducts/Analytical_Methods/index.htm. It provides a simple and easy-to-use template for estimating the uncertainty of γ-ray spectrometry measurement results and supports the radioanalytical laboratories seeking accreditation for their measurements using γ-ray spectrometry.
Collapse
Affiliation(s)
- Alessia Ceccatelli
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria.
| | - Ashild Dybdal
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| | - Ales Fajgelj
- Office of the Deputy Director General, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| | - Aurelien Pitois
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| |
Collapse
|
45
|
Chaudhary A, Hantush MM. Bayesian Monte Carlo and maximum likelihood approach for uncertainty estimation and risk management: Application to lake oxygen recovery model. Water Res 2017; 108:301-311. [PMID: 27836170 PMCID: PMC6192273 DOI: 10.1016/j.watres.2016.11.012] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2016] [Revised: 10/12/2016] [Accepted: 11/02/2016] [Indexed: 05/16/2023]
Abstract
Model uncertainty estimation and risk assessment is essential to environmental management and informed decision making on pollution mitigation strategies. In this study, we apply a probabilistic methodology, which combines Bayesian Monte Carlo simulation and Maximum Likelihood estimation (BMCML) to calibrate a lake oxygen recovery model. We first derive an analytical solution of the differential equation governing lake-averaged oxygen dynamics as a function of time-variable wind speed. Statistical inferences on model parameters and predictive uncertainty are then drawn by Bayesian conditioning of the analytical solution on observed daily wind speed and oxygen concentration data obtained from an earlier study during two recovery periods on a eutrophic lake in upper state New York. The model is calibrated using oxygen recovery data for one year and statistical inferences were validated using recovery data for another year. Compared with essentially two-step, regression and optimization approach, the BMCML results are more comprehensive and performed relatively better in predicting the observed temporal dissolved oxygen levels (DO) in the lake. BMCML also produced comparable calibration and validation results with those obtained using popular Markov Chain Monte Carlo technique (MCMC) and is computationally simpler and easier to implement than the MCMC. Next, using the calibrated model, we derive an optimal relationship between liquid film-transfer coefficient for oxygen and wind speed and associated 95% confidence band, which are shown to be consistent with reported measured values at five different lakes. Finally, we illustrate the robustness of the BMCML to solve risk-based water quality management problems, showing that neglecting cross-correlations between parameters could lead to improper required BOD load reduction to achieve the compliance criteria of 5 mg/L.
Collapse
Affiliation(s)
- Abhishek Chaudhary
- Institute of Food, Nutrition and Health, ETH Zurich, 8092 Zürich, Switzerland.
| | - Mohamed M Hantush
- National Risk Management Research Laboratory, ORD, USEPA, Cincinnati, OH 45268, USA
| |
Collapse
|
46
|
Ebrahimkhani S. Robust fractional order sliding mode control of doubly-fed induction generator (DFIG)-based wind turbines. ISA Trans 2016; 63:343-354. [PMID: 27018145 DOI: 10.1016/j.isatra.2016.03.003] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/23/2015] [Revised: 02/12/2016] [Accepted: 03/07/2016] [Indexed: 06/05/2023]
Abstract
Wind power plants have nonlinear dynamics and contain many uncertainties such as unknown nonlinear disturbances and parameter uncertainties. Thus, it is a difficult task to design a robust reliable controller for this system. This paper proposes a novel robust fractional-order sliding mode (FOSM) controller for maximum power point tracking (MPPT) control of doubly fed induction generator (DFIG)-based wind energy conversion system. In order to enhance the robustness of the control system, uncertainties and disturbances are estimated using a fractional order uncertainty estimator. In the proposed method a continuous control strategy is developed to achieve the chattering free fractional order sliding-mode control, and also no knowledge of the uncertainties and disturbances or their bound is assumed. The boundedness and convergence properties of the closed-loop signals are proven using Lyapunov׳s stability theory. Simulation results in the presence of various uncertainties were carried out to evaluate the effectiveness and robustness of the proposed control scheme.
Collapse
Affiliation(s)
- Sadegh Ebrahimkhani
- Department of Electrical and Robotics Engineering, Shahrood University, 36199-95161, Shahrood, Iran.
| |
Collapse
|
47
|
Eskelinen R, Ronkanen AK, Marttila H, Kløve B. Assessment of uncertainty in constructed wetland treatment performance and load estimation methods. Environ Monit Assess 2016; 188:365. [PMID: 27220504 DOI: 10.1007/s10661-016-5381-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/11/2015] [Accepted: 05/17/2016] [Indexed: 06/05/2023]
Abstract
Constructed wetlands (CWs) are commonly established to reduce pollution load from different sources. In environmental permits, the load remaining after CW purification is typically estimated through concentration and flow measurements. This load monitoring is often carried out using long water quality sampling intervals, which causes uncertainty in load estimation. In this study, a large suspended solids (SSs) and dissolved organic carbon (DOC) dataset was used to quantify the uncertainty in load estimation at the inlet and outlet of a CW with different sampling frequencies (sampling every 1, 2, 3 or 4 weeks). A method to reduce the uncertainty by dividing the CW flow duration curve (FDC) into four equal categories and assigning mean/median concentration for each category according to the measured concentrations was also tested. The results showed that estimated SS load was associated with considerable uncertainty and that this uncertainty increased with lower sampling frequency. The FDC method was able to decrease the uncertainty, but much still remained, especially when concentrations of the measured variable showed great variation. In such cases, sensor technology might be a feasible option for further reducing the uncertainty.
Collapse
Affiliation(s)
- Riku Eskelinen
- Water Resources and Environmental Engineering Research Group, University of Oulu, P.O. Box 4300, FI-90014, Oulu, Finland.
- Thule Institute, P.O. Box 7300, FI-90014, Oulu, Finland.
| | - Anna-Kaisa Ronkanen
- Water Resources and Environmental Engineering Research Group, University of Oulu, P.O. Box 4300, FI-90014, Oulu, Finland
| | - Hannu Marttila
- Water Resources and Environmental Engineering Research Group, University of Oulu, P.O. Box 4300, FI-90014, Oulu, Finland
| | - Bjørn Kløve
- Water Resources and Environmental Engineering Research Group, University of Oulu, P.O. Box 4300, FI-90014, Oulu, Finland
| |
Collapse
|
48
|
Iurian AR, Pitois A, Kis-Benedek G, Migliori A, Padilla-Alvarez R, Ceccatelli A. Assessment of measurement result uncertainty in determination of (210)Pb with the focus on matrix composition effect in gamma-ray spectrometry. Appl Radiat Isot 2015; 109:61-69. [PMID: 26653212 DOI: 10.1016/j.apradiso.2015.11.067] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2015] [Accepted: 11/24/2015] [Indexed: 12/01/2022]
Abstract
Reference materials were used to assess measurement result uncertainty in determination of (210)Pb by gamma-ray spectrometry, liquid scintillation counting, or indirectly by alpha-particle spectrometry, using its daughter (210)Po in radioactive equilibrium. Combined standard uncertainties of (210)Pb massic activities obtained by liquid scintillation counting are in the range 2-12%, depending on matrices and massic activity values. They are in the range 1-3% for the measurement of its daughter (210)Po using alpha-particle spectrometry. Three approaches (direct computation of counting efficiency and efficiency transfer approaches based on the computation and, respectively, experimental determination of the efficiency transfer factors) were applied for the evaluation of (210)Pb using gamma-ray spectrometry. Combined standard uncertainties of gamma-ray spectrometry results were found in the range 2-17%. The effect of matrix composition on self-attenuation was investigated and a detailed assessment of uncertainty components was performed.
Collapse
Affiliation(s)
- A R Iurian
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria.
| | - A Pitois
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| | - G Kis-Benedek
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| | - A Migliori
- Nuclear Science and Instrumentation Laboratory, Division of Physical and Chemical Sciences, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| | - R Padilla-Alvarez
- Nuclear Science and Instrumentation Laboratory, Division of Physical and Chemical Sciences, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| | - A Ceccatelli
- Terrestrial Environment Laboratory, IAEA Environment Laboratories, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna International Centre, PO Box 100, 1400 Vienna, Austria
| |
Collapse
|
49
|
Paoloni A, Alunni S, Pelliccia A, Pecorelli I. Rapid determination of residues of pesticides in honey by µGC-ECD and GC-MS/MS: Method validation and estimation of measurement uncertainty according to document No. SANCO/12571/2013. J Environ Sci Health B 2015; 51:133-142. [PMID: 26671720 DOI: 10.1080/03601234.2015.1108748] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
A simple and straightforward method for simultaneous determination of residues of 13 pesticides in honey samples (acrinathrin, bifenthrin, bromopropylate, cyhalothrin-lambda, cypermethrin, chlorfenvinphos, chlorpyrifos, coumaphos, deltamethrin, fluvalinate-tau, malathion, permethrin and tetradifon) from different pesticide classes has been developed and validated. The analytical method provides dissolution of honey in water and an extraction of pesticide residues by n-Hexane followed by clean-up on a Florisil SPE column. The extract was evaporated and taken up by a solution of an injection internal standard (I-IS), ethion, and finally analyzed by capillary gas chromatography with electron capture detection (GC-µECD). Identification for qualitative purpose was conducted by gas chromatography with triple quadrupole mass spectrometer (GC-MS/MS). A matrix-matched calibration curve was performed for quantitative purposes by plotting the area ratio (analyte/I-IS) against concentration using a GC-µECD instrument. According to document No. SANCO/12571/2013, the method was validated by testing the following parameters: linearity, matrix effect, specificity, precision, trueness (bias) and measurement uncertainty. The analytical process was validated analyzing blank honey samples spiked at levels equal to and greater than 0.010 mg/kg (limit of quantification). All parameters were satisfactorily compared with the values established by document No. SANCO/12571/2013. The analytical performance was verified by participating in eight multi-residue proficiency tests organized by BIPEA, obtaining satisfactory z-scores in all 70 determinations. Measurement uncertainty was estimated according to the top-down approaches described in Appendix C of the SANCO document using the within-laboratory reproducibility relative standard deviation combined with laboratory bias using the proficiency test data.
Collapse
Affiliation(s)
- Angela Paoloni
- a Environmental Contaminants Laboratory, Istituto Zooprofilattico Sperimentale dell'Umbria e delle Marche , Perugia , Italy
| | - Sabrina Alunni
- a Environmental Contaminants Laboratory, Istituto Zooprofilattico Sperimentale dell'Umbria e delle Marche , Perugia , Italy
| | - Alessandro Pelliccia
- a Environmental Contaminants Laboratory, Istituto Zooprofilattico Sperimentale dell'Umbria e delle Marche , Perugia , Italy
| | - Ivan Pecorelli
- a Environmental Contaminants Laboratory, Istituto Zooprofilattico Sperimentale dell'Umbria e delle Marche , Perugia , Italy
| |
Collapse
|
50
|
Borecka M, Siedlewicz G, Haliński ŁP, Sikora K, Pazdro K, Stepnowski P, Białk-Bielińska A. Contamination of the southern Baltic Sea waters by the residues of selected pharmaceuticals: Method development and field studies. Mar Pollut Bull 2015; 94:62-71. [PMID: 25817309 DOI: 10.1016/j.marpolbul.2015.03.008] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/08/2014] [Revised: 02/23/2015] [Accepted: 03/03/2015] [Indexed: 05/26/2023]
Abstract
In this study the occurrence of thirteen pharmaceuticals in seawaters collected from southern Baltic Sea was evaluated for the first time. It was performed by applying newly developed analytical procedure. The method was characterized in terms of its basic validation parameters as well as matrix effects, extraction efficiency and absolute recovery. The results were expressed as result ± expanded uncertainty, which was estimated according to the Guide to the Expression of Uncertainty in Measurement. Additionally, in order to verify the influence of variable parameters of the analyzed samples on method performance parameters, chemometric analysis was carried out. The obtained results revealed that residues of pharmaceuticals were present in seawaters at a concentration level of ng L(-1). Trimethoprim, sulfamethoxazole and enrofloxacin were most frequently detected compounds. The highest concentration was determined for ketoprofen (135.0 ± 10.9 ng L(-1)). Marine pollution potential hotspots were found in enclosed or semi-enclosed bodies of water.
Collapse
Affiliation(s)
- Marta Borecka
- Department of Environmental Analysis, Faculty of Chemistry, University of Gdańsk, ul. Wita Stwosza 63, 80-308 Gdańsk, Poland
| | - Grzegorz Siedlewicz
- Institute of Oceanology, Polish Academy of Sciences, ul. Powstańców Warszawy 55, 81-712 Sopot, Poland
| | - Łukasz P Haliński
- Department of Environmental Analysis, Faculty of Chemistry, University of Gdańsk, ul. Wita Stwosza 63, 80-308 Gdańsk, Poland
| | - Kinga Sikora
- Physicochemical Laboratories, Faculty of Chemistry, University of Gdańsk, ul. Wita Stwosza 63, 80-308 Gdańsk, Poland
| | - Ksenia Pazdro
- Institute of Oceanology, Polish Academy of Sciences, ul. Powstańców Warszawy 55, 81-712 Sopot, Poland
| | - Piotr Stepnowski
- Department of Environmental Analysis, Faculty of Chemistry, University of Gdańsk, ul. Wita Stwosza 63, 80-308 Gdańsk, Poland
| | - Anna Białk-Bielińska
- Department of Environmental Analysis, Faculty of Chemistry, University of Gdańsk, ul. Wita Stwosza 63, 80-308 Gdańsk, Poland.
| |
Collapse
|