1
|
Tappeiner E, Welk M, Schubert R. Tackling the class imbalance problem of deep learning-based head and neck organ segmentation. Int J Comput Assist Radiol Surg 2022; 17:2103-2111. [PMID: 35578086 PMCID: PMC9515025 DOI: 10.1007/s11548-022-02649-5] [Citation(s) in RCA: 2] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2022] [Accepted: 04/20/2022] [Indexed: 12/03/2022]
Abstract
Purpose The segmentation of organs at risk (OAR) is a required precondition for the cancer treatment with image- guided radiation therapy. The automation of the segmentation task is therefore of high clinical relevance. Deep learning (DL)-based medical image segmentation is currently the most successful approach, but suffers from the over-presence of the background class and the anatomically given organ size difference, which is most severe in the head and neck (HAN) area. Methods To tackle the HAN area-specific class imbalance problem, we first optimize the patch size of the currently best performing general-purpose segmentation framework, the nnU-Net, based on the introduced class imbalance measurement, and second introduce the class adaptive Dice loss to further compensate for the highly imbalanced setting. Results Both the patch size and the loss function are parameters with direct influence on the class imbalance, and their optimization leads to a 3% increase in the Dice score and 22% reduction in the 95% Hausdorff distance compared to the baseline, finally reaching \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$0.8\pm 0.15$$\end{document}0.8±0.15 and \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$3.17\pm 1.7$$\end{document}3.17±1.7 mm for the segmentation of seven HAN organs using a single and simple neural network. Conclusion The patch size optimization and the class adaptive Dice loss are both simply integrable in current DL-based segmentation approaches and allow to increase the performance for class imbalance segmentation tasks.
Collapse
Affiliation(s)
- Elias Tappeiner
- Department for Biomedical Computer Science and Mechatronics, UMIT-Private University for Health Sciences, Medical Informatics and Technology, Eduard-Wallnöfer-Zentrum 1, 6060, Hall in Tyrol, Tyrol, Austria.
| | - Martin Welk
- Department for Biomedical Computer Science and Mechatronics, UMIT-Private University for Health Sciences, Medical Informatics and Technology, Eduard-Wallnöfer-Zentrum 1, 6060, Hall in Tyrol, Tyrol, Austria
| | - Rainer Schubert
- Department for Biomedical Computer Science and Mechatronics, UMIT-Private University for Health Sciences, Medical Informatics and Technology, Eduard-Wallnöfer-Zentrum 1, 6060, Hall in Tyrol, Tyrol, Austria
| |
Collapse
|
2
|
Pröll SM, Tappeiner E, Hofbauer S, Kolbitsch C, Schubert R, Fritscher KD. Heart rate estimation from ballistocardiographic signals using deep learning. Physiol Meas 2021; 42. [PMID: 34198282 DOI: 10.1088/1361-6579/ac10aa] [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] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2021] [Accepted: 06/24/2021] [Indexed: 11/11/2022]
Abstract
Objective.Ballistocardiography (BCG) is an unobtrusive approach for cost-effective and patient-friendly health monitoring. In this work, deep learning methods are used for heart rate estimation from BCG signals and are compared against five digital signal processing methods found in literature.Approach.The models are evaluated on a dataset featuring BCG recordings from 42 patients, acquired with a pneumatic system. Several different deep learning architectures, including convolutional, recurrent and a combination of both are investigated. Besides model performance, we are also concerned about model size and specifically investigate less complex and smaller networks.Main results.Deep learning models outperform traditional methods by a large margin. Across 14 patients in a held-out testing set, an architecture with stacked convolutional and recurrent layers achieves an average mean absolute error (MAE) of 2.07 beat min-1, whereas the best-performing traditional method reaches 4.24 beat min-1. Besides smaller errors, deep learning models show more consistent performance across different patients, indicating the ability to better deal with inter-patient variability, a prevalent issue in BCG analysis. In addition, we develop a smaller version of the best-performing architecture, that only features 8283 parameters, yet still achieves an average MAE of 2.32 beat min-1on the testing set.Significance.This is the first study that applies and compares different deep learning architectures to heart rate estimation from bed-based BCG signals. Compared to signal processing algorithms, deep learning models show dramatically smaller errors and more consistent results across different individuals. The results show that using smaller models instead of excessively large ones can lead to sufficient performance for specific biosignal processing applications. Additionally, we investigate the use of fully convolutional networks for 1D signal processing, which is rarely applied in literature.
Collapse
Affiliation(s)
- Samuel M Pröll
- Institute for Biomedical Image Analysis, UMIT-Private University for Health Sciences, Medical Informatics and Technology, A-6060 Hall in Tirol, Austria
| | - Elias Tappeiner
- Institute for Biomedical Image Analysis, UMIT-Private University for Health Sciences, Medical Informatics and Technology, A-6060 Hall in Tirol, Austria
| | - Stefan Hofbauer
- Department of Anaesthesia and Intensive Care Medicine, Medical University Innsbruck (MUI), A-6020 Innsbruck, Austria
| | - Christian Kolbitsch
- Department of Anaesthesia and Intensive Care Medicine, Medical University Innsbruck (MUI), A-6020 Innsbruck, Austria
| | - Rainer Schubert
- Institute for Biomedical Image Analysis, UMIT-Private University for Health Sciences, Medical Informatics and Technology, A-6060 Hall in Tirol, Austria
| | - Karl D Fritscher
- Institute for Biomedical Image Analysis, UMIT-Private University for Health Sciences, Medical Informatics and Technology, A-6060 Hall in Tirol, Austria
| |
Collapse
|
3
|
Tappeiner E, Pröll S, Hönig M, Raudaschl PF, Zaffino P, Spadea MF, Sharp GC, Schubert R, Fritscher K. Multi-organ segmentation of the head and neck area: an efficient hierarchical neural networks approach. Int J Comput Assist Radiol Surg 2019; 14:745-754. [PMID: 30847761 DOI: 10.1007/s11548-019-01922-4] [Citation(s) in RCA: 31] [Impact Index Per Article: 6.2] [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: 08/17/2018] [Accepted: 02/04/2019] [Indexed: 12/01/2022]
Abstract
PURPOSE In radiation therapy, a key step for a successful cancer treatment is image-based treatment planning. One objective of the planning phase is the fast and accurate segmentation of organs at risk and target structures from medical images. However, manual delineation of organs, which is still the gold standard in many clinical environments, is time-consuming and prone to inter-observer variations. Consequently, many automated segmentation methods have been developed. METHODS In this work, we train two hierarchical 3D neural networks to segment multiple organs at risk in the head and neck area. First, we train a coarse network on size-reduced medical images to locate the organs of interest. Second, a subsequent fine network on full-resolution images is trained for a final accurate segmentation. The proposed method is purely deep learning based; accordingly, no pre-registration or post-processing is required. RESULTS The approach has been applied on a publicly available computed tomography dataset, created for the MICCAI 2015 Auto-Segmentation challenge. In an extensive evaluation process, the best configurations for the trained networks have been determined. Compared to the existing methods, the presented approach shows state-of-the-art performance for the segmentation of seven different structures in the head and neck area. CONCLUSION We conclude that 3D neural networks outperform the most existing model- and atlas-based methods for the segmentation of organs at risk in the head and neck area. The ease of use, high accuracy and the test time efficiency of the method make it promising for image-based treatment planning in clinical practice.
Collapse
Affiliation(s)
- Elias Tappeiner
- Department of Biomedical Computer Science and Mechatronics, University for Health Sciences, Medical Informatics and Technology, 6060, Hall, Tyrol, Austria.
| | - Samuel Pröll
- Department of Biomedical Computer Science and Mechatronics, University for Health Sciences, Medical Informatics and Technology, 6060, Hall, Tyrol, Austria
| | - Markus Hönig
- Department of Biomedical Computer Science and Mechatronics, University for Health Sciences, Medical Informatics and Technology, 6060, Hall, Tyrol, Austria
| | - Patrick F Raudaschl
- Department of Biomedical Computer Science and Mechatronics, University for Health Sciences, Medical Informatics and Technology, 6060, Hall, Tyrol, Austria
| | - Paolo Zaffino
- Department of Experimental and Clinical Medicine, Magna Graecia University of Catanzaro, 88100, Catanzaro, Italy
| | - Maria F Spadea
- Department of Experimental and Clinical Medicine, Magna Graecia University of Catanzaro, 88100, Catanzaro, Italy
| | - Gregory C Sharp
- Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, 02114, USA
| | - Rainer Schubert
- Department of Biomedical Computer Science and Mechatronics, University for Health Sciences, Medical Informatics and Technology, 6060, Hall, Tyrol, Austria
| | - Karl Fritscher
- Department of Biomedical Computer Science and Mechatronics, University for Health Sciences, Medical Informatics and Technology, 6060, Hall, Tyrol, Austria
| |
Collapse
|
4
|
Abstract
Summary Recently, a number of powerful computational tools for dissecting tumor-immune cell interactions from next-generation sequencing data have been developed. However, the assembly of analytical pipelines and execution of multi-step workflows are laborious and involve a large number of intermediate steps with many dependencies and parameter settings. Here we present TIminer, an easy-to-use computational pipeline for mining tumor-immune cell interactions from next-generation sequencing data. TIminer enables integrative immunogenomic analyses, including: human leukocyte antigens typing, neoantigen prediction, characterization of immune infiltrates and quantification of tumor immunogenicity. Availability and implementation TIminer is freely available at http://icbi.i-med.ac.at/software/timiner/timiner.shtml. Supplementary information Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Elias Tappeiner
- Division of Bioinformatics, Biocenter, Medical University of Innsbruck, 6020 Innsbruck, Austria
| | - Francesca Finotello
- Division of Bioinformatics, Biocenter, Medical University of Innsbruck, 6020 Innsbruck, Austria
| | - Pornpimol Charoentong
- Division of Bioinformatics, Biocenter, Medical University of Innsbruck, 6020 Innsbruck, Austria
| | - Clemens Mayer
- Division of Bioinformatics, Biocenter, Medical University of Innsbruck, 6020 Innsbruck, Austria
| | - Dietmar Rieder
- Division of Bioinformatics, Biocenter, Medical University of Innsbruck, 6020 Innsbruck, Austria
| | - Zlatko Trajanoski
- Division of Bioinformatics, Biocenter, Medical University of Innsbruck, 6020 Innsbruck, Austria
| |
Collapse
|