1
|
Ger RB, Wei L, Naqa IE, Wang J. The Promise and Future of Radiomics for Personalized Radiotherapy Dosing and Adaptation. Semin Radiat Oncol 2023; 33:252-261. [PMID: 37331780 DOI: 10.1016/j.semradonc.2023.03.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/20/2023]
Abstract
Quantitative image analysis, also known as radiomics, aims to analyze large-scale quantitative features extracted from acquired medical images using hand-crafted or machine-engineered feature extraction approaches. Radiomics has great potential for a variety of clinical applications in radiation oncology, an image-rich treatment modality that utilizes computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) for treatment planning, dose calculation, and image guidance. A promising application of radiomics is in predicting treatment outcomes after radiotherapy such as local control and treatment-related toxicity using features extracted from pretreatment and on-treatment images. Based on these individualized predictions of treatment outcomes, radiotherapy dose can be sculpted to meet the specific needs and preferences of each patient. Radiomics can aid in tumor characterization for personalized targeting, especially for identifying high-risk regions within a tumor that cannot be easily discerned based on size or intensity alone. Radiomics-based treatment response prediction can aid in developing personalized fractionation and dose adjustments. In order to make radiomics models more applicable across different institutions with varying scanners and patient populations, further efforts are needed to harmonize and standardize the acquisition protocols by minimizing uncertainties within the imaging data.
Collapse
Affiliation(s)
- Rachel B Ger
- Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Medicine, Baltimore, MD
| | - Lise Wei
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI
| | - Issam El Naqa
- Department of Machine Learning, Moffitt Cancer Center and Research Institute, Tampa, FL
| | - Jing Wang
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX..
| |
Collapse
|
2
|
Basran PS, Porter I. Radiomics in veterinary medicine: Overview, methods, and applications. Vet Radiol Ultrasound 2022; 63 Suppl 1:828-839. [PMID: 36514226 DOI: 10.1111/vru.13156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2021] [Revised: 09/24/2021] [Accepted: 11/10/2021] [Indexed: 12/15/2022] Open
Abstract
Radiomics, or quantitative image analysis from radiographic image data, borrows the suffix from other emerging -omics fields of study, such as genomics, proteomics, and metabolomics. This report provides an overview of the general principles of how radiomic features are computed, describes major types of morphological, first order, and texture features, and the applications, challenges, and opportunities of radiomics as applied in veterinary medicine. Some advantages radiomics has over traditional semantic radiological features include standardized methodology in computing semantic features, the ability to compute features in multi-dimensional images, their newfound associations with genomic and pathological abnormalities, and the number of perceptible and imperceptible features available for regression or classification modeling. Some challenges in deploying radiomics in a clinical setting include sensitivity to image acquisition settings and image artifacts, pre- and post-image reconstruction and calculation settings, variability in feature estimates stemming from inter- and intra-observer contouring errors, and challenges with software and data harmonization and generalizability of findings given the challenges of small sample size and patient selection bias in veterinary medicine. Despite this, radiomics has enormous potential in patient-centric diagnostics, prognosis, and theragnostics. Fully leveraging the utility of radiomics in veterinary medicine will require inter-institutional collaborations, data harmonization, and data sharing strategies amongst institutions, transparent and robust model development, and multi-disciplinary efforts within and outside the veterinary medical imaging community.
Collapse
Affiliation(s)
- Parminder S Basran
- Department of Clinical Sciences, College of Veterinary Medicine, Cornell University, Ithaca, New York, USA
| | - Ian Porter
- Department of Clinical Sciences, College of Veterinary Medicine, Cornell University, Ithaca, New York, USA
| |
Collapse
|
3
|
Liu Y, Wen T, Sun W, Liu Z, Song X, He X, Zhang S, Wu Z. Graph-Based Motion Artifacts Detection Method from Head Computed Tomography Images. SENSORS (BASEL, SWITZERLAND) 2022; 22:5666. [PMID: 35957222 PMCID: PMC9371218 DOI: 10.3390/s22155666] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Revised: 07/26/2022] [Accepted: 07/27/2022] [Indexed: 06/15/2023]
Abstract
Computed tomography (CT) images play an important role due to effectiveness and accessibility, however, motion artifacts may obscure or simulate pathology and dramatically degrade the diagnosis accuracy. In recent years, convolutional neural networks (CNNs) have achieved state-of-the-art performance in medical imaging due to the powerful learning ability with the help of the advanced hardware technology. Unfortunately, CNNs have significant overhead on memory usage and computational resources and are labeled 'black-box' by scholars for their complex underlying structures. To this end, an interpretable graph-based method has been proposed for motion artifacts detection from head CT images in this paper. From a topological perspective, the artifacts detection problem has been reformulated as a complex network classification problem based on the network topological characteristics of the corresponding complex networks. A motion artifacts detection method based on complex networks (MADM-CN) has been proposed. Firstly, the graph of each CT image is constructed based on the theory of complex networks. Secondly, slice-to-slice relationship has been explored by multiple graph construction. In addition, network topological characteristics are investigated locally and globally, consistent topological characteristics including average degree, average clustering coefficient have been utilized for classification. The experimental results have demonstrated that the proposed MADM-CN has achieved better performance over conventional machine learning and deep learning methods on a real CT dataset, reaching up to 98% of the accuracy and 97% of the sensitivity.
Collapse
Affiliation(s)
- Yiwen Liu
- School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China;
| | - Tao Wen
- School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China;
- Department of Computer Science and Technology, Dalian Neusoft University of Information, Dalian 116023, China; (Z.L.); (X.S.)
| | - Wei Sun
- School of Computer Science, Neusoft Institute Guangdong, Foshan 528225, China;
| | - Zhenyu Liu
- Department of Computer Science and Technology, Dalian Neusoft University of Information, Dalian 116023, China; (Z.L.); (X.S.)
| | - Xiaoying Song
- Department of Computer Science and Technology, Dalian Neusoft University of Information, Dalian 116023, China; (Z.L.); (X.S.)
| | - Xuan He
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110819, China;
| | - Shuo Zhang
- School of Information Science and Engineering, Northeastern University, Shenyang 110819, China; (S.Z.); (Z.W.)
| | - Zhenning Wu
- School of Information Science and Engineering, Northeastern University, Shenyang 110819, China; (S.Z.); (Z.W.)
| |
Collapse
|
4
|
Qiu B, Guo J, Kraeima J, Glas HH, Zhang W, Borra RJH, Witjes MJH, van Ooijen PMA. Recurrent Convolutional Neural Networks for 3D Mandible Segmentation in Computed Tomography. J Pers Med 2021; 11:jpm11060492. [PMID: 34072714 PMCID: PMC8229770 DOI: 10.3390/jpm11060492] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Revised: 05/26/2021] [Accepted: 05/28/2021] [Indexed: 12/24/2022] Open
Abstract
Purpose: Classic encoder–decoder-based convolutional neural network (EDCNN) approaches cannot accurately segment detailed anatomical structures of the mandible in computed tomography (CT), for instance, condyles and coronoids of the mandible, which are often affected by noise and metal artifacts. The main reason is that EDCNN approaches ignore the anatomical connectivity of the organs. In this paper, we propose a novel CNN-based 3D mandible segmentation approach that has the ability to accurately segment detailed anatomical structures. Methods: Different from the classic EDCNNs that need to slice or crop the whole CT scan into 2D slices or 3D patches during the segmentation process, our proposed approach can perform mandible segmentation on complete 3D CT scans. The proposed method, namely, RCNNSeg, adopts the structure of the recurrent neural networks to form a directed acyclic graph in order to enable recurrent connections between adjacent nodes to retain their connectivity. Each node then functions as a classic EDCNN to segment a single slice in the CT scan. Our proposed approach can perform 3D mandible segmentation on sequential data of any varied lengths and does not require a large computation cost. The proposed RCNNSeg was evaluated on 109 head and neck CT scans from a local dataset and 40 scans from the PDDCA public dataset. The final accuracy of the proposed RCNNSeg was evaluated by calculating the Dice similarity coefficient (DSC), average symmetric surface distance (ASD), and 95% Hausdorff distance (95HD) between the reference standard and the automated segmentation. Results: The proposed RCNNSeg outperforms the EDCNN-based approaches on both datasets and yields superior quantitative and qualitative performances when compared to the state-of-the-art approaches on the PDDCA dataset. The proposed RCNNSeg generated the most accurate segmentations with an average DSC of 97.48%, ASD of 0.2170 mm, and 95HD of 2.6562 mm on 109 CT scans, and an average DSC of 95.10%, ASD of 0.1367 mm, and 95HD of 1.3560 mm on the PDDCA dataset. Conclusions: The proposed RCNNSeg method generated more accurate automated segmentations than those of the other classic EDCNN segmentation techniques in terms of quantitative and qualitative evaluation. The proposed RCNNSeg has potential for automatic mandible segmentation by learning spatially structured information.
Collapse
Affiliation(s)
- Bingjiang Qiu
- 3D Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands; (B.Q.); (J.K.); (H.H.G.); (M.J.H.W.)
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands;
- Data Science Center in Health (DASH), University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands
| | - Jiapan Guo
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands;
- Data Science Center in Health (DASH), University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands
- Correspondence:
| | - Joep Kraeima
- 3D Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands; (B.Q.); (J.K.); (H.H.G.); (M.J.H.W.)
- Department of Oral and Maxillofacial Surgery, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands
| | - Haye Hendrik Glas
- 3D Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands; (B.Q.); (J.K.); (H.H.G.); (M.J.H.W.)
- Department of Oral and Maxillofacial Surgery, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands
| | - Weichuan Zhang
- Institute for Integrated and Intelligent System, Griffith University, Nathan, QLD 4111, Australia;
- CSIRO Data61, Epping, NSW 1710, Australia
| | - Ronald J. H. Borra
- Medical Imaging Center (MIC), University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands;
| | - Max Johannes Hendrikus Witjes
- 3D Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands; (B.Q.); (J.K.); (H.H.G.); (M.J.H.W.)
- Department of Oral and Maxillofacial Surgery, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands
| | - Peter M. A. van Ooijen
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands;
- Data Science Center in Health (DASH), University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713GZ Groningen, The Netherlands
| |
Collapse
|
5
|
Oh JH, Apte AP, Katsoulakis E, Riaz N, Hatzoglou V, Yu Y, Mahmood U, Veeraraghavan H, Pouryahya M, Iyer A, Shukla-Dave A, Tannenbaum A, Lee NY, Deasy JO. Reproducibility of radiomic features using network analysis and its application in Wasserstein k-means clustering. J Med Imaging (Bellingham) 2021; 8:031904. [PMID: 33954225 PMCID: PMC8085581 DOI: 10.1117/1.jmi.8.3.031904] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2020] [Accepted: 04/02/2021] [Indexed: 12/24/2022] Open
Abstract
Purpose: The goal of this study is to develop innovative methods for identifying radiomic features that are reproducible over varying image acquisition settings. Approach: We propose a regularized partial correlation network to identify reliable and reproducible radiomic features. This approach was tested on two radiomic feature sets generated using two different reconstruction methods on computed tomography (CT) scans from a cohort of 47 lung cancer patients. The largest common network component between the two networks was tested on phantom data consisting of five cancer samples. To further investigate whether radiomic features found can identify phenotypes, we propose a k -means clustering algorithm coupled with the optimal mass transport theory. This approach following the regularized partial correlation network analysis was tested on CT scans from 77 head and neck squamous cell carcinoma (HNSCC) patients in the Cancer Imaging Archive (TCIA) and validated using an independent dataset. Results: A set of common radiomic features was found in relatively large network components between the resultant two partial correlation networks resulting from a cohort of lung cancer patients. The reliability and reproducibility of those radiomic features were further validated on phantom data using the Wasserstein distance. Further analysis using the network-based Wasserstein k -means algorithm on the TCIA HNSCC data showed that the resulting clusters separate tumor subsites as well as HPV status, and this was validated on an independent dataset. Conclusion: We showed that a network-based analysis enables identifying reproducible radiomic features and use of the selected set of features can enhance clustering results.
Collapse
Affiliation(s)
- Jung Hun Oh
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Aditya P Apte
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Evangelia Katsoulakis
- Veterans Affairs, James A Haley, Department of Radiation Oncology, Tampa, Florida, United States
| | - Nadeem Riaz
- Memorial Sloan Kettering Cancer Center, Department of Radiation Oncology, New York, United States
| | - Vaios Hatzoglou
- Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, United States
| | - Yao Yu
- Memorial Sloan Kettering Cancer Center, Department of Radiation Oncology, New York, United States
| | - Usman Mahmood
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Harini Veeraraghavan
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Maryam Pouryahya
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Aditi Iyer
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Amita Shukla-Dave
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| | - Allen Tannenbaum
- Stony Brook University, Department of Computer Science, Stony Brook, New York, United States.,Stony Brook University, Department of Applied Mathematics and Statistics, Stony Brook, New York, United States
| | - Nancy Y Lee
- Memorial Sloan Kettering Cancer Center, Department of Radiation Oncology, New York, United States
| | - Joseph O Deasy
- Memorial Sloan Kettering Cancer Center, Department of Medical Physics, New York, United States
| |
Collapse
|
6
|
Arrowsmith C, Reiazi R, Welch ML, Kazmierski M, Patel T, Rezaie A, Tadic T, Bratman S, Haibe-Kains B. Automated detection of dental artifacts for large-scale radiomic analysis in radiation oncology. PHYSICS & IMAGING IN RADIATION ONCOLOGY 2021; 18:41-47. [PMID: 34258406 PMCID: PMC8254196 DOI: 10.1016/j.phro.2021.04.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/23/2020] [Revised: 02/09/2021] [Accepted: 04/06/2021] [Indexed: 11/30/2022]
Abstract
Background and purpose Computed tomography (CT) is one of the most common medical imaging modalities in radiation oncology and radiomics research, the computational voxel-level analysis of medical images. Radiomics is vulnerable to the effects of dental artifacts (DA) caused by metal implants or fillings and can hamper future reproducibility on new datasets. In this study we seek to better understand the robustness of quantitative radiomic features to DAs. Furthermore, we propose a novel method of detecting DAs in order to safeguard radiomic studies and improve reproducibility. Materials and methods We analyzed the correlations between radiomic features and the location of dental artifacts in a new dataset containing 3D CT scans from 3211 patients. We then combined conventional image processing techniques with a pre-trained convolutional neural network to create a three-class patient-level DA classifier and slice-level DA locator. Finally, we demonstrated its utility in reducing the correlations between the location of DAs and certain radiomic features. Results We found that when strong DAs were present, the proximity of the tumour to the mouth was highly correlated with 36 radiomic features. We predicted the correct DA magnitude yielding a Matthews correlation coefficient of 0.73 and location of DAs achieving the same level of agreement as human labellers. Conclusions Removing radiomic features or CT slices containing DAs could reduce the unwanted correlations between the location of DAs and radiomic features. Automated DA detection can be used to improve the reproducibility of radiomic studies; an important step towards creating effective radiomic models for use in clinical radiation oncology.
Collapse
Affiliation(s)
- Colin Arrowsmith
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Reza Reiazi
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - Mattea L Welch
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Michal Kazmierski
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada
| | - Tirth Patel
- Techna Institute, University Health Network, Toronto, Ontario, Canada
| | - Aria Rezaie
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | - Tony Tadic
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - Scott Bratman
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada
| | - Benjamin Haibe-Kains
- Radiation Medicine Program, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada.,Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada.,Department of Computer Science, University of Toronto, Toronto, Ontario, Canada.,Ontario Institute for Cancer Research, Toronto, Ontario, Canada.,Vector Institute, Toronto, Ontario, Canada
| |
Collapse
|
7
|
Hernandez S, Sjogreen C, Gay SS, Nguyen C, Netherton T, Olanrewaju A, Zhang LJ, Rhee DJ, Méndez JD, Court LE, Cardenas CE. Development and dosimetric assessment of an automatic dental artifact classification tool to guide artifact management techniques in a fully automated treatment planning workflow. Comput Med Imaging Graph 2021; 90:101907. [PMID: 33845433 PMCID: PMC8180493 DOI: 10.1016/j.compmedimag.2021.101907] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2020] [Revised: 02/05/2021] [Accepted: 03/14/2021] [Indexed: 12/03/2022]
Abstract
Purpose: We conducted our study to develop a tool capable of automatically detecting dental artifacts in a CT scan on a slice-by-slice basis and to assess the dosimetric impact of implementing the tool into the Radiation Planning Assistant (RPA), a web-based platform designed to fully automate the radiation therapy treatment planning process. Methods: We developed an automatic dental artifact identification tool and assessed the dosimetric impact of its use in the RPA. Three users manually annotated 83,676 head-and-neck (HN) CT slices (549 patients). Majority-voting was applied to the individual annotations to determine the presence or absence of dental artifacts. The patients were divided into train, cross-validation, and test data sets (ratio: 3:1:1, respectively). A random subset of images without dental artifacts was used to balance classes (1:1) in the training data set. The Inception-V3 deep learning model was trained with the binary cross-entropy loss function. With use of this model, we automatically identified artifacts on 15 RPA HN plans on a slice-by-slice basis and investigated three dental artifact management methods applied before and after volumetric modulated arc therapy (VMAT) plan optimization. The resulting dose distributions and target coverage were quantified. Results: Per-slice accuracy, sensitivity, and specificity were 99 %, 91 %, and 99 %, respectively. The model identified all patients with artifacts. Small dosimetric differences in total plan dose were observed between the various density-override methods (±1 Gy). For the pre- and post-optimized plans, 90 % and 99 %, respectively, of dose comparisons resulted in normal structure dose differences of ±1 Gy. Differences in the volume of structures receiving 95 % of the prescribed dose (V95[%]) were ≤0.25 % for 100 % of plans. Conclusion: The dosimetric impact of applying dental artifact management before and after artifact plan optimization was minor. Our results suggest that not accounting for dental artifacts in the current RPA workflow (where only post-optimization dental artifact management is possible) may result in minor dosimetric differences. If RPA users choose to override CT densities as a solution to managing dental artifacts, our results suggest segmenting the volume of the artifact and overriding its density to water is a safe option.
Collapse
Affiliation(s)
- Soleil Hernandez
- The University of Texas MD Anderson Cancer Center Graduate School of Biomedical Sciences, Houston, TX, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA.
| | - Carlos Sjogreen
- The University of Texas MD Anderson Cancer Center Graduate School of Biomedical Sciences, Houston, TX, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Skylar S Gay
- The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Callistus Nguyen
- The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Tucker Netherton
- The University of Texas MD Anderson Cancer Center Graduate School of Biomedical Sciences, Houston, TX, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Adenike Olanrewaju
- The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Lifei Joy Zhang
- The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Dong Joo Rhee
- The University of Texas MD Anderson Cancer Center Graduate School of Biomedical Sciences, Houston, TX, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - José David Méndez
- The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Laurence E Court
- The University of Texas MD Anderson Cancer Center Graduate School of Biomedical Sciences, Houston, TX, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| | - Carlos E Cardenas
- The University of Texas MD Anderson Cancer Center Graduate School of Biomedical Sciences, Houston, TX, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX, USA
| |
Collapse
|
8
|
Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Intracranial Hemorrhage. J Am Coll Radiol 2021; 18:1143-1152. [PMID: 33819478 DOI: 10.1016/j.jacr.2021.03.005] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2023]
Abstract
OBJECTIVE To determine the institutional diagnostic accuracy of an artificial intelligence (AI) decision support systems (DSS), Aidoc, in diagnosing intracranial hemorrhage (ICH) on noncontrast head CTs and to assess the potential generalizability of an AI DSS. METHODS This retrospective study included 3,605 consecutive, emergent, adult noncontrast head CT scans performed between July 1, 2019, and December 30, 2019, at our institution (51% female subjects, mean age of 61 ± 21 years). Each scan was evaluated for ICH by both a certificate of added qualification certified neuroradiologist and Aidoc. We determined the diagnostic accuracy of the AI model and performed a failure mode analysis with quantitative CT radiomic image characterization. RESULTS Of the 3,605 scans, 349 cases of ICH (9.7% of studies) were identified. The neuroradiologist and Aidoc interpretations were concordant in 96.9% of cases and the overall sensitivity, specificity, positive predictive value, and negative predictive value were 92.3%, 97.7%, 81.3%, and 99.2%, respectively, with positive predictive values unexpectedly lower than in previously reported studies. Prior neurosurgery, type of ICH, and number of ICHs were significantly associated with decreased model performance. Quantitative image characterization with CT radiomics failed to reveal significant differences between concordant and discordant studies. DISCUSSION This study revealed decreased diagnostic accuracy of an AI DSS at our institution. Despite extensive evaluation, we were unable to identify the source of this discrepancy, raising concerns about the generalizability of these tools with indeterminate failure modes. These results further highlight the need for standardized study design to allow for rigorous and reproducible site-to-site comparison of emerging deep learning technologies.
Collapse
|
9
|
Utility of CT texture analysis to differentiate olfactory neuroblastoma from sinonasal squamous cell carcinoma. Sci Rep 2021; 11:4679. [PMID: 33633160 PMCID: PMC7907098 DOI: 10.1038/s41598-021-84048-5] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2020] [Accepted: 02/11/2021] [Indexed: 01/06/2023] Open
Abstract
The purpose of this study was to examine differences in texture features between olfactory neuroblastoma (ONB) and sinonasal squamous cell carcinoma (SCC) on contrast-enhanced CT (CECT) images, and to evaluate the predictive accuracy of texture analysis compared to radiologists’ interpretations. Forty-three patients with pathologically-diagnosed primary nasal and paranasal tumor (17 ONB and 26 SCC) were included. We extracted 42 texture features from tumor regions on CECT images obtained before treatment. In univariate analysis, each texture features were compared, with adjustment for multiple comparisons. In multivariate analysis, the elastic net was used to select useful texture features and to construct a texture-based prediction model with leave-one-out cross-validation. The prediction accuracy was compared with two radiologists’ visual interpretations. In univariate analysis, significant differences were observed for 28 of 42 texture features between ONB and SCC, with areas under the receiver operating characteristic curve between 0.68 and 0.91 (median: 0.80). In multivariate analysis, the elastic net model selected 18 texture features that contributed to differentiation. It tended to show slightly higher predictive accuracy than radiologists’ interpretations (86% and 74%, respectively; P = 0.096). In conclusion, several texture features contributed to differentiation of ONB from SCC, and the texture-based prediction model was considered useful.
Collapse
|
10
|
Interpretable Machine Learning Model for Locoregional Relapse Prediction in Oropharyngeal Cancers. Cancers (Basel) 2020; 13:cancers13010057. [PMID: 33379188 PMCID: PMC7795920 DOI: 10.3390/cancers13010057] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2020] [Revised: 12/21/2020] [Accepted: 12/21/2020] [Indexed: 01/06/2023] Open
Abstract
BACKGROUND There is no evidence to support surgery or radiotherapy as the best treatment for resectable oropharyngeal cancers with a negative HPV status. Predictive algorithms may help to decide which strategy to choose, but they will only be accepted by caregivers and European authorities if they are interpretable. As a proof of concept, we developed a predictive and interpretable algorithm to predict locoregional relapse at 18 months for oropharyngeal cancers as a first step towards that goal. METHODS The model was based on clinical and Pyradiomics features extracted from the dosimetric CT scan. Intraclass correlation was used to filter out features dependant on delineation. Correlated redundant features were also removed. An XGBoost model was cross-validated and optimised on the HN1 cohort (79 patients), and performances were assessed on the ART ORL cohort (45 patients). The Shapley Values were used to provide an overall and local explanation of the model. RESULTS On the ART ORL cohort, the model trained on HN1 yielded a precision-or predictive positive value-of 0.92, a recall of 0.42, an area under the curve of the receiver operating characteristic of 0.68 and an accuracy of 0.64. The most contributory features were shape Voxel Volume, grey level size zone matrix Small Area Emphasis (glszmSAE), gldm Dependence Non Uniformity Normalized (gldmDNUN), Sex and Age. CONCLUSIONS We developed an interpretable and generalizable model that could yield a good precision-positive predictive value-for relapse at 18 months on a different test cohort.
Collapse
|
11
|
Haider SP, Sharaf K, Zeevi T, Baumeister P, Reichel C, Forghani R, Kann BH, Petukhova A, Judson BL, Prasad ML, Liu C, Burtness B, Mahajan A, Payabvash S. Prediction of post-radiotherapy locoregional progression in HPV-associated oropharyngeal squamous cell carcinoma using machine-learning analysis of baseline PET/CT radiomics. Transl Oncol 2020; 14:100906. [PMID: 33075658 PMCID: PMC7568193 DOI: 10.1016/j.tranon.2020.100906] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2020] [Revised: 09/27/2020] [Accepted: 09/28/2020] [Indexed: 12/15/2022] Open
Abstract
Radiomics quantitatively captures visually inappreciable imaging features. PET/CT radiomics provides wholistic metabolic and structural tumor characterization. Machine-learning algorithms can generate radiomics-based biomarkers for OPSCC. PET/CT radiomics can predict post-radiotherapy locoregional progression in HPV-associated OPSCC. Such biomarkers may improve patient selection for treatment de-intensification trials.
Locoregional failure remains a therapeutic challenge in oropharyngeal squamous cell carcinoma (OPSCC). We aimed to devise novel objective imaging biomarkers for prediction of locoregional progression in HPV-associated OPSCC. Following manual lesion delineation, 1037 PET and 1037 CT radiomic features were extracted from each primary tumor and metastatic cervical lymph node on baseline PET/CT scans. Applying random forest machine-learning algorithms, we generated radiomic models for censoring-aware locoregional progression prognostication (evaluated by Harrell's C-index) and risk stratification (evaluated in Kaplan-Meier analysis). A total of 190 patients were included; an optimized model yielded a median (interquartile range) C-index of 0.76 (0.66-0.81; p = 0.01) in prognostication of locoregional progression, using combined PET/CT radiomic features from primary tumors. Radiomics-based risk stratification reliably identified patients at risk for locoregional progression within 2-, 3-, 4-, and 5-year follow-up intervals, with log-rank p-values of p = 0.003, p = 0.001, p = 0.02, p = 0.006 in Kaplan-Meier analysis, respectively. Our results suggest PET/CT radiomic biomarkers can predict post-radiotherapy locoregional progression in HPV-associated OPSCC. Pending validation in large, independent cohorts, such objective biomarkers may improve patient selection for treatment de-intensification trials in this prognostically favorable OPSCC entity, and eventually facilitate personalized therapy.
Collapse
Affiliation(s)
- Stefan P Haider
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, PO Box 208042, New Haven, CT 06519, United States; Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany
| | - Kariem Sharaf
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany
| | - Tal Zeevi
- Center for Translational Imaging Analysis and Machine Learning, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06510, United States
| | - Philipp Baumeister
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany
| | - Christoph Reichel
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany
| | - Reza Forghani
- Department of Diagnostic Radiology and Augmented Intelligence & Precision Health Laboratory (AIPHL), McGill University Health Centre & Research Institute, 1650 Cedar Avenue, Montreal, Quebec QC H3G 1A4, Canada
| | - Benjamin H Kann
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Harvard Medical School, 450 Brookline Avenue, Boston, MA 02215, United States
| | - Alexandra Petukhova
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, PO Box 208042, New Haven, CT 06519, United States
| | - Benjamin L Judson
- Division of Otolaryngology, Department of Surgery, Yale School of Medicine, 330 Cedar Street, New Haven, CT 06520, United States
| | - Manju L Prasad
- Department of Pathology, Yale School of Medicine, 310 Cedar Street, New Haven, CT 06520, United States
| | - Chi Liu
- Division of Bioimaging Sciences, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06510, United States
| | - Barbara Burtness
- Section of Medical Oncology, Department of Internal Medicine, Yale School of Medicine and Yale Cancer Center, 25 York Street, New Haven, CT 06520, United States
| | - Amit Mahajan
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, PO Box 208042, New Haven, CT 06519, United States
| | - Seyedmehdi Payabvash
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, PO Box 208042, New Haven, CT 06519, United States.
| |
Collapse
|
12
|
Basran PS, Gao J, Palmer S, Reesink HL. A radiomics platform for computing imaging features from µCT images of Thoroughbred racehorse proximal sesamoid bones: Benchmark performance and evaluation. Equine Vet J 2020; 53:277-286. [PMID: 32654167 DOI: 10.1111/evj.13321] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2020] [Revised: 06/08/2020] [Accepted: 07/02/2020] [Indexed: 11/27/2022]
Abstract
BACKGROUND Proximal sesamoid bone (PSB) fractures are the most common fatal musculoskeletal injury in North American racehorses. Computed tomography has the potential to detect morphological changes in bone structure but can be challenging to analyse reliably and quantitatively. OBJECTIVES To develop a radiomics platform that allows the comparison of features from micro-CTs (µCT) of PSBs in horses that sustained catastrophic fractures with horses that did not. To compare features calculated with a radiomics approach with features calculated from a previously published study that used quantitative µCT in the same specimens. STUDY DESIGN Retrospective study of cadaver specimens of µCT images of PSBs using prospectively applied radiomics. METHODS Radiomics features were computed on standardised CT datasets to benchmark the software. Features from µCT images of PSBs from eight horses that sustained PSB fracture and eight controls were computed using the contralateral, intact forelimb from horses sustaining PSB fracture (cases, n = 19) and all available forelimbs for controls (n = 30). Two-hundred and fifteen radiomic features were calculated, and similar or comparable features were compared with those reported in a previous study that used the same specimens. RESULTS Morphologic features computed with the radiomics approach, such as volume, minor axis dimensions and anisotropy were highly correlated with previously published data. A high number of imperceptible radiomic features, such as entropy, coarseness and histogram features were also found to be significantly different (P < .01). The extent of the differences in image features for the cases and controls PSBs depends on radiomic calculation settings. MAIN LIMITATIONS Only datasets obtained from cadaver specimens were included in the study. CONCLUSIONS A radiomics approach for analysing µCT images of PSBs was able to identify and reproduce differences in image features in cases and controls. Furthermore, radiomics revealed many more imperceptible image features between cases and control PSBs.
Collapse
Affiliation(s)
| | - Jonathan Gao
- Clinical Sciences, Cornell University, Ithaca, NY, USA
| | - Scott Palmer
- Population Medicine and Diagnostic Sciences, Cornell University, Ithaca, NY, USA
| | - Heidi L Reesink
- Clinical Sciences, Cornell University, Ithaca, NY, USA.,Equine and Farm Animal Hospital, Cornell University, Ithaca, NY, USA
| |
Collapse
|
13
|
Haider SP, Zeevi T, Baumeister P, Reichel C, Sharaf K, Forghani R, Kann BH, Judson BL, Prasad ML, Burtness B, Mahajan A, Payabvash S. Potential Added Value of PET/CT Radiomics for Survival Prognostication beyond AJCC 8th Edition Staging in Oropharyngeal Squamous Cell Carcinoma. Cancers (Basel) 2020; 12:cancers12071778. [PMID: 32635216 PMCID: PMC7407414 DOI: 10.3390/cancers12071778] [Citation(s) in RCA: 32] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Revised: 06/29/2020] [Accepted: 06/30/2020] [Indexed: 12/18/2022] Open
Abstract
Accurate risk-stratification can facilitate precision therapy in oropharyngeal squamous cell carcinoma (OPSCC). We explored the potential added value of baseline positron emission tomography (PET)/computed tomography (CT) radiomic features for prognostication and risk stratification of OPSCC beyond the American Joint Committee on Cancer (AJCC) 8th edition staging scheme. Using institutional and publicly available datasets, we included OPSCC patients with known human papillomavirus (HPV) status, without baseline distant metastasis and treated with curative intent. We extracted 1037 PET and 1037 CT radiomic features quantifying lesion shape, imaging intensity, and texture patterns from primary tumors and metastatic cervical lymph nodes. Utilizing random forest algorithms, we devised novel machine-learning models for OPSCC progression-free survival (PFS) and overall survival (OS) using “radiomics” features, “AJCC” variables, and the “combined” set as input. We designed both single- (PET or CT) and combined-modality (PET/CT) models. Harrell’s C-index quantified survival model performance; risk stratification was evaluated in Kaplan–Meier analysis. A total of 311 patients were included. In HPV-associated OPSCC, the best “radiomics” model achieved an average C-index ± standard deviation of 0.62 ± 0.05 (p = 0.02) for PFS prediction, compared to 0.54 ± 0.06 (p = 0.32) utilizing “AJCC” variables. Radiomics-based risk-stratification of HPV-associated OPSCC was significant for PFS and OS. Similar trends were observed in HPV-negative OPSCC. In conclusion, radiomics imaging features extracted from pre-treatment PET/CT may provide complimentary information to the current AJCC staging scheme for survival prognostication and risk-stratification of HPV-associated OPSCC.
Collapse
Affiliation(s)
- Stefan P. Haider
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, New Haven, CT 06519, USA; (S.P.H.); (A.M.)
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany; (P.B.); (C.R.); (K.S.)
| | - Tal Zeevi
- Center for Translational Imaging Analysis and Machine Learning, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06510, USA;
| | - Philipp Baumeister
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany; (P.B.); (C.R.); (K.S.)
| | - Christoph Reichel
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany; (P.B.); (C.R.); (K.S.)
| | - Kariem Sharaf
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Marchioninistrasse 15, 81377 Munich, Germany; (P.B.); (C.R.); (K.S.)
| | - Reza Forghani
- Department of Diagnostic Radiology and Augmented Intelligence & Precision Health Laboratory, McGill University Health Centre & Research Institute, 1650 Cedar Avenue, Montreal, QC H3G 1A4, Canada;
| | - Benjamin H. Kann
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Harvard Medical School, 450 Brookline Avenue, Boston, MA 02215, USA;
| | - Benjamin L. Judson
- Division of Otolaryngology, Department of Surgery, Yale School of Medicine, 330 Cedar Street, New Haven, CT 06520, USA;
| | - Manju L. Prasad
- Department of Pathology, Yale School of Medicine, 310 Cedar Street, New Haven, CT 06520, USA;
| | - Barbara Burtness
- Section of Medical Oncology, Department of Internal Medicine, Yale School of Medicine, 25 York Street, New Haven, CT 06520, USA;
| | - Amit Mahajan
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, New Haven, CT 06519, USA; (S.P.H.); (A.M.)
| | - Seyedmehdi Payabvash
- Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, 789 Howard Ave, New Haven, CT 06519, USA; (S.P.H.); (A.M.)
- Correspondence: ; Tel.: +1-(203)-214-4650
| |
Collapse
|
14
|
Katsoulakis E, Yu Y, Apte AP, Leeman JE, Katabi N, Morris L, Deasy JO, Chan TA, Lee NY, Riaz N, Hatzoglou V, Oh JH. Radiomic analysis identifies tumor subtypes associated with distinct molecular and microenvironmental factors in head and neck squamous cell carcinoma. Oral Oncol 2020; 110:104877. [PMID: 32619927 DOI: 10.1016/j.oraloncology.2020.104877] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2019] [Revised: 06/17/2020] [Accepted: 06/22/2020] [Indexed: 01/03/2023]
Abstract
PURPOSE To identify whether radiomic features from pre-treatment computed tomography (CT) scans can predict molecular differences between head and neck squamous cell carcinoma (HNSCC) using The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). METHODS 77 patients from the TCIA with HNSCC had imaging suitable for analysis. Radiomic features were extracted and unsupervised consensus clustering was performed to identify subtypes. Genomic data was extracted from the matched patients in the TCGA database. We explored relationships between radiomic features and molecular profiles of tumors, including the tumor immune microenvironment. A machine learning method was used to build a model predictive of CD8 + T-cells. An independent cohort of 83 HNSCC patients was used to validate the radiomic clusters. RESULTS We initially extracted 104 two-dimensional radiomic features, and after feature stability tests and removal of volume dependent features, reduced this to 67 features for subsequent analysis. Consensus clustering based on these features resulted in two distinct clusters. The radiomic clusters differed by primary tumor subsite (p = 0.0096), HPV status (p = 0.0127), methylation-based clustering results (p = 0.0025), and tumor immune microenvironment. A random forest model using radiomic features predicted CD8 + T-cells independent of HPV status with R2 = 0.30 (p < 0.0001) on cross validation. Consensus clustering on the validation cohort resulted in two distinct clusters that differ in tumor subsite (p = 1.3 × 10-7) and HPV status (p = 4.0 × 10-7). CONCLUSION Radiomic analysis can identify biologic features of tumors such as HPV status and T-cell infiltration and may be able to provide other information in the near future to help with patient stratification.
Collapse
Affiliation(s)
- Evangelia Katsoulakis
- Department of Radiation Oncology, Veterans Affairs, James A Haley, Tampa, FL 33612, USA
| | - Yao Yu
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Aditya P Apte
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Jonathan E Leeman
- Department of Radiation Oncology, Dana Farber Cancer Institute/Brigham and Women's Hospital, Boston, MA 02189, USA
| | - Nora Katabi
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Luc Morris
- Immunogenomics and Precision Oncology Platform, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Joseph O Deasy
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Timothy A Chan
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; Immunogenomics and Precision Oncology Platform, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; Human Oncology and Pathogenesis Program, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Nancy Y Lee
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Nadeem Riaz
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; Immunogenomics and Precision Oncology Platform, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Vaios Hatzoglou
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
| | - Jung Hun Oh
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
| |
Collapse
|
15
|
Radiomic biomarkers for head and neck squamous cell carcinoma. Strahlenther Onkol 2020; 196:868-878. [PMID: 32495038 DOI: 10.1007/s00066-020-01638-4] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2020] [Accepted: 05/13/2020] [Indexed: 12/22/2022]
Abstract
Tumor heterogeneity is a well-known prognostic factor in head and neck squamous cell carcinoma (HNSCC). A major limitation of tissue- and blood-derived tumor markers is the lack of spatial resolution to image tumor heterogeneity. Tissue markers derived from tumor biopsies usually represent only a small tumor subregion at a single timepoint and are therefore often not representative of the tumors' biology or the biological alterations during and after treatment. Similarly, liquid biopsies give an overall picture of the tumors' secreted factors but completely lack any spatial resolution. Radiomics has the potential to give complete three-dimensional information about the tumor. We conducted a comprehensive literature search to assess the correlation of radiomics to tumor biology and treatment outcome in HNSCC and to assess current limitations of the radiomic biomarkers. In total, 25 studies that explored the ability of radiomics to predict tumor biology and phenotype in HNSCC and 28 studies that explored radiomics to predict post-treatment events were identified. Out of these 53 studies, only three failed to show a significant correlation. The major technical challenges are currently artifacts due to metal implants, non-standardized contrast injection, and delineation uncertainties. All studies to date were retrospective and none of the above-mentioned radiomics signatures have been validated in an independent cohort using an independent software implementation, which shows that transferability due to the numerous technical challenges is currently a major limitation. However, radiomics is a very young field and these studies hopefully pave the way for clinical implementation of radiomics for HNSCC in the future.
Collapse
|
16
|
PET/CT radiomics signature of human papilloma virus association in oropharyngeal squamous cell carcinoma. Eur J Nucl Med Mol Imaging 2020; 47:2978-2991. [DOI: 10.1007/s00259-020-04839-2] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2020] [Accepted: 04/24/2020] [Indexed: 01/02/2023]
|
17
|
Cupping artifacts correction for polychromatic X-ray cone-beam computed tomography based on projection compensation and hardening behavior. Biomed Signal Process Control 2020. [DOI: 10.1016/j.bspc.2019.101823] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
18
|
Welch ML, McIntosh C, Traverso A, Wee L, Purdie TG, Dekker A, Haibe-Kains B, Jaffray DA. External validation and transfer learning of convolutional neural networks for computed tomography dental artifact classification. Phys Med Biol 2020; 65:035017. [PMID: 31851961 DOI: 10.1088/1361-6560/ab63ba] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Quality assurance of data prior to use in automated pipelines and image analysis would assist in safeguarding against biases and incorrect interpretation of results. Automation of quality assurance steps would further improve robustness and efficiency of these methods, motivating widespread adoption of techniques. Previous work by our group demonstrated the ability of convolutional neural networks (CNN) to efficiently classify head and neck (H&N) computed-tomography (CT) images for the presence of dental artifacts (DA) that obscure visualization of structures and the accuracy of Hounsfield units. In this work we demonstrate the generalizability of our previous methodology by validating CNNs on six external datasets, and the potential benefits of transfer learning with fine-tuning on CNN performance. 2112 H&N CT images from seven institutions were scored as DA positive or negative. 1538 images from a single institution were used to train three CNNs with resampling grid sizes of 643, 1283 and 2563. The remaining six external datasets were used in five-fold cross-validation with a data split of 20% training/fine-tuning and 80% validation. The three pre-trained models were each validated using the five-folds of the six external datasets. The pre-trained models also underwent transfer learning with fine-tuning using the 20% training/fine-tuning data, and validated using the corresponding validation datasets. The highest micro-averaged AUC for our pre-trained models across all external datasets occurred with a resampling grid of 2563 (AUC = 0.91 ± 0.01). Transfer learning with fine-tuning improved generalizability when utilizing a resampling grid of 2563 to a micro-averaged AUC of 0.92 ± 0.01. Despite these promising results, transfer learning did not improve AUC when utilizing small resampling grids or small datasets. Our work demonstrates the potential of our previously developed automated quality assurance methods to generalize to external datasets. Additionally, we showed that transfer learning with fine-tuning using small portions of external datasets can be used to fine-tune models for improved performance when large variations in images are present.
Collapse
Affiliation(s)
- Mattea L Welch
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada. Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada. The Techna Institute for the Advancement of Technology for Health, Toronto, Ontario, Canada. Author to whom any correspondence should be addressed
| | | | | | | | | | | | | | | |
Collapse
|
19
|
Welch ML, McIntosh C, Purdie TG, Wee L, Traverso A, Dekker A, Haibe-Kains B, Jaffray DA. Automatic classification of dental artifact status for efficient image veracity checks: effects of image resolution and convolutional neural network depth. Phys Med Biol 2020; 65:015005. [PMID: 31683260 DOI: 10.1088/1361-6560/ab5427] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
Enabling automated pipelines, image analysis and big data methodology in cancer clinics requires thorough understanding of the data. Automated quality assurance steps could improve the efficiency and robustness of these methods by verifying possible data biases. In particular, in head and neck (H&N) computed-tomography (CT) images, dental artifacts (DA) obscure visualization of structures and the accuracy of Hounsfield units; a challenge for image analysis tasks, including radiomics, where poor image quality can lead to systemic biases. In this work we analyze the performance of three-dimensional convolutional neural networks (CNN) trained to classify DA statuses. 1538 patient images were scored by a single observer as DA positive or negative. Stratified five-fold cross validation was performed to train and test CNNs using various isotropic resampling grids (643, 1283 and 2563), with CNN depths designed to produce 323, 163, and 83 machine generated features. These parameters were selected to determine if more computationally efficient CNNs could be utilized to achieve the same performance. The area under the precision recall curve (PR-AUC) was used to assess CNN performance. The highest PR-AUC (0.92 ± 0.03) was achieved with a CNN depth = 5, resampling grid = 256. The CNN performance with 2563 resampling grid size is not significantly better than 643 and 1283 after 20 epochs, which had PR-AUC = 0.89 ± 0.03 (p -value = 0.28) and 0.91 ± 0.02 (p -value = 0.93) at depths of 3 and 4, respectively. Our experiments demonstrate the potential to automate specific quality assurance tasks required for unbiased and robust automated pipeline and image analysis research. Additionally, we determined that there is an opportunity to simplify CNNs with smaller resampling grids to make the process more amenable to very large datasets that will be available in the future.
Collapse
Affiliation(s)
- Mattea L Welch
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada. The Techna Institute for the Advancement of Technology for Health, Toronto, Ontario, Canada. Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
| | | | | | | | | | | | | | | |
Collapse
|
20
|
Combined CT radiomics of primary tumor and metastatic lymph nodes improves prediction of loco-regional control in head and neck cancer. Sci Rep 2019; 9:15198. [PMID: 31645603 PMCID: PMC6811564 DOI: 10.1038/s41598-019-51599-7] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2019] [Accepted: 10/02/2019] [Indexed: 12/20/2022] Open
Abstract
Loco-regional control (LRC) is a major clinical endpoint after definitive radiochemotherapy (RCT) of head and neck cancer (HNC). Radiomics has been shown a promising biomarker in cancer research, however closer related to primary tumor control than composite endpoints. Radiomics studies often focus on the analysis of primary tumor (PT). We hypothesize that the combination of PT and lymph nodes (LN) radiomics better predicts LRC in HNC treated with RCT. Radiomics analysis was performed in CT images of 128 patients using Z-Rad implementation (training n = 77, validation n = 51). 285 features were extracted from PT and involved LN. Features were preselected with the maximum relevance minimum redundancy method and the multivariate Cox model was trained using least absolute shrinkage and selection operator. The mixed model was based on the combination of PT and LN radiomics, whereas the PT model included only the PT features. The mixed model showed significantly higher performance than the PT model (p < 0.01), c-index of 0.67 and 0.63, respectively; and better risk group stratification. The clinical nodal status was not a significant predictor in the combination with PT radiomics. This study shows that the LRC can be better predicted by expansion of radiomics analysis with LN features.
Collapse
|
21
|
Ger RB, Zhou S, Elgohari B, Elhalawani H, Mackin DM, Meier JG, Nguyen CM, Anderson BM, Gay C, Ning J, Fuller CD, Li H, Howell RM, Layman RR, Mawlawi O, Stafford RJ, Aerts H, Court LE. Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients. PLoS One 2019; 14:e0222509. [PMID: 31536526 PMCID: PMC6752873 DOI: 10.1371/journal.pone.0222509] [Citation(s) in RCA: 43] [Impact Index Per Article: 8.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2019] [Accepted: 08/31/2019] [Indexed: 12/22/2022] Open
Abstract
Radiomics studies require many patients in order to power them, thus patients are often combined from different institutions and using different imaging protocols. Various studies have shown that imaging protocols affect radiomics feature values. We examined whether using data from cohorts with controlled imaging protocols improved patient outcome models. We retrospectively reviewed 726 CT and 686 PET images from head and neck cancer patients, who were divided into training or independent testing cohorts. For each patient, radiomics features with different preprocessing were calculated and two clinical variables—HPV status and tumor volume—were also included. A Cox proportional hazards model was built on the training data by using bootstrapped Lasso regression to predict overall survival. The effect of controlled imaging protocols on model performance was evaluated by subsetting the original training and independent testing cohorts to include only patients whose images were obtained using the same imaging protocol and vendor. Tumor volume, HPV status, and two radiomics covariates were selected for the CT model, resulting in an AUC of 0.72. However, volume alone produced a higher AUC, whereas adding radiomics features reduced the AUC. HPV status and one radiomics feature were selected as covariates for the PET model, resulting in an AUC of 0.59, but neither covariate was significantly associated with survival. Limiting the training and independent testing to patients with the same imaging protocol reduced the AUC for CT patients to 0.55, and no covariates were selected for PET patients. Radiomics features were not consistently associated with survival in CT or PET images of head and neck patients, even within patients with the same imaging protocol.
Collapse
Affiliation(s)
- Rachel B. Ger
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- * E-mail:
| | - Shouhao Zhou
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Baher Elgohari
- Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Hesham Elhalawani
- Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Dennis M. Mackin
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
| | - Joseph G. Meier
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Callistus M. Nguyen
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Brian M. Anderson
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Casey Gay
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Jing Ning
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Clifton D. Fuller
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Heng Li
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
| | - Rebecca M. Howell
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
| | - Rick R. Layman
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Osama Mawlawi
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - R. Jason Stafford
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| | - Hugo Aerts
- Department of Radiation Oncology, Dana Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, United States of America
| | - Laurence E. Court
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
- MD Anderson Cancer Center UTHealth Science Center at Houston Graduate School of Biomedical Sciences, Houston, Texas, United States of America
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, United States of America
| |
Collapse
|
22
|
Cozzi L, Franzese C, Fogliata A, Franceschini D, Navarria P, Tomatis S, Scorsetti M. Predicting survival and local control after radiochemotherapy in locally advanced head and neck cancer by means of computed tomography based radiomics. Strahlenther Onkol 2019; 195:805-818. [PMID: 31222468 DOI: 10.1007/s00066-019-01483-0] [Citation(s) in RCA: 32] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2019] [Accepted: 06/06/2019] [Indexed: 12/31/2022]
Abstract
PURPOSE To appraise the ability of a radiomics signature to predict clinical outcome after definitive radiochemotherapy (RCT) of stage III-IV head and neck cancer. METHODS A cohort of 110 patients was included in a retrospective analysis. Radiomics texture features were extracted from the gross tumor volumes contoured on planning computed tomography (CT) images. The cohort of patients was randomly divided into a training (70 patients) and a validation (40 patients) cohorts. Textural features were correlated to survival and control data to build predictive models. All the significant predictors of the univariate analysis were included in a multivariate model. The quality of the models was appraised by means of the concordance index (CI). RESULTS A signature with 3 features was identified as predictive of overall survival (OS) with CI = 0.88 and 0.90 for the training and validation cohorts, respectively. A signature with 2 features was identified for progression-free survival (PFS; CI = 0.72 and 0.80); 2 features also characterized the signature for local control (LC; CI = 0.72 and 0.82). In all cases, the stratification in high- and low-risk groups for the training and validation cohorts led to significant differences in the actuarial curves. In the validation cohort the mean OS times (in months) were 78.9 ± 2.1 vs 67.4 ± 6.0 in the low- and high-risk groups, respectively, the PFS was 73.1 ± 3.7 and 50.7 ± 7.2, while the LC was 78.7 ± 2.1 and 63.9 ± 6.5. CONCLUSION CT-based radiomic signatures that correlate with survival and control after RCT were identified and allow low- and high-risk groups of patients to be identified.
Collapse
Affiliation(s)
- Luca Cozzi
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele (Milan), Italy. .,Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy.
| | - Ciro Franzese
- Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy
| | - Antonella Fogliata
- Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy
| | - Davide Franceschini
- Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy
| | - Pierina Navarria
- Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy
| | - Stefano Tomatis
- Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy
| | - Marta Scorsetti
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele (Milan), Italy.,Radiotherapy and Radiosurgery, Humanitas Clinical and Research Center, Rozzano (Milan), Italy
| |
Collapse
|
23
|
Wei L, Rosen B, Vallières M, Chotchutipan T, Mierzwa M, Eisbruch A, El Naqa I. Automatic recognition and analysis of metal streak artifacts in head and neck computed tomography for radiomics modeling. PHYSICS & IMAGING IN RADIATION ONCOLOGY 2019; 10:49-54. [PMID: 33458268 PMCID: PMC7807651 DOI: 10.1016/j.phro.2019.05.001] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/24/2019] [Revised: 05/23/2019] [Accepted: 05/23/2019] [Indexed: 12/27/2022]
Abstract
Background and purpose Computed tomography (CT) radiomics of head and neck cancer (HNC) images is susceptible to dental implant artifacts. This work devised and validated an automated algorithm to detect CT metal artifacts and investigate their impact on subsequent radiomics analyses. A new method based on features from total variation, gradient directional distribution, and Hough transform was developed and evaluated. Materials and methods Two HNC datasets were analyzed: a training set of 131 patients for developing the detection algorithm and a testing set of 220 patients. Seven designated features were extracted from ROIs (regions of interest) and machine learning with random forests was used for building the artifact detection algorithm. Performance was assessed using the area under the receiver operating characteristics curve (AUC). Results The testing results of artifacts detection yielded a cross-validated AUC of 0.91 (95% CI: 0.89–0.94), and a test AUC of 0.89. External testing validation yielded an accuracy of 0.82. For radiomics model prediction, training with artifacts yielded an AUC of 0.64 (95% CI: 0.63–0.65), while training on images without artifacts improved the AUC to 0.75 (95% CI: 0.74–0.76). This was compared to visual inspection of artifacts (AUC = 0.71 [95% CI: 0.69–0.73]). Conclusion We developed a new method for automated and efficient detection of streak artifacts. We also showed that such streak artifacts in HNC CT images can worsen the performance of radiomics modeling.
Collapse
Affiliation(s)
- Lise Wei
- Applied Physics Program, University of Michigan, Ann Arbor, MI, United States
| | - Benjamin Rosen
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States
| | - Martin Vallières
- Medical Physics Unit, McGill University, Cedars Cancer Centre, McGill University Health Centre - Glen Site, 1001 Boulevard D́ecarie, Montreal, QC H4A 3J1, Canada
| | - Thong Chotchutipan
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States
| | - Michelle Mierzwa
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States
| | - Avraham Eisbruch
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States
| | - Issam El Naqa
- Applied Physics Program, University of Michigan, Ann Arbor, MI, United States.,Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, United States
| |
Collapse
|