1
|
Gooding MJ, Aluwini S, Guerrero Urbano T, McQuinlan Y, Om D, Staal FHE, Perennec T, Azzarouali S, Cardenas CE, Carver A, Korreman SS, Bibault JE. Fully automated radiotherapy treatment planning: A scan to plan challenge. Radiother Oncol 2024; 200:110513. [PMID: 39222848 DOI: 10.1016/j.radonc.2024.110513] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2024] [Revised: 08/19/2024] [Accepted: 08/26/2024] [Indexed: 09/04/2024]
Abstract
BACKGROUND AND PURPOSE Over the past decade, tools for automation of various sub-tasks in radiotherapy planning have been introduced, such as auto-contouring and auto-planning. The purpose of this study was to benchmark what degree of automation is possible. MATERIALS AND METHODS A challenge to perform automated treatment planning for prostate and prostate bed radiotherapy was set up. Participants were provided with simulation CTs and a treatment prescription and were asked to use automated tools to produce a deliverable radiotherapy treatment plan with as little human intervention as possible. Plans were scored for their adherence to the protocol when assessed using consensus expert contours. RESULTS Thirteen entries were received. The top submission adhered to 81.8% of the minimum objectives across all cases using the consensus contour, meeting all objectives in one of the ten cases. The same system met 89.5% of objectives when assessed with their own auto-contours, meeting all objectives in four of the ten cases. The majority of systems used in the challenge had regulatory clearance (Auto-contouring: 82.5%, Auto-planning: 77%). Despite the 'hard' rule that participants should not check or edit contours or plans, 69% reported looking at their results before submission. CONCLUSIONS Automation of the full planning workflow from simulation CT to deliverable treatment plan is possible for prostate and prostate bed radiotherapy. While many generated plans were found to require none or minor adjustment to be regarded as clinically acceptable, the result indicated there is still a lack of trust in such systems preventing full automation.
Collapse
Affiliation(s)
- Mark J Gooding
- Inpictura Ltd, 5 The Chambers, Vineyard, Abingdon OX14 3PX, United Kingdom; Division of Cancer Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, M20 4BX Manchester, United Kingdom.
| | - Shafak Aluwini
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
| | - Teresa Guerrero Urbano
- Department of Clinical Oncology Guy's and St Thomas' NHS Foundation Trust School of Cancer and Pharmaceutical Sciences King's College London, London, United Kingdom.
| | - Yasmin McQuinlan
- Mirada Medical Ltd, Barclay House, 234 Botley Road OX2 0HP, United Kingdom.
| | - Deborah Om
- Department of Medical Physics, Hôpital Européen Georges Pompidou, Université Paris Cité, 75015 Paris, France.
| | - Floor H E Staal
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
| | - Tanguy Perennec
- Département de radiothérapie, Institut de Cancérologie de l'Ouest, Nantes, France.
| | - Sana Azzarouali
- Radiation Oncology, Amsterdam UMC location Vrije Universiteit Amsterdam, De Boelelaan 1117, Amsterdam, The Netherlands.
| | - Carlos E Cardenas
- Department of Radiation Oncology, The University of Alabama at Birmingham, Birmingham, AL, USA.
| | - Antony Carver
- Department of Medical Physics, University Hospitals Birmingham NHS Foundation Trust, Birmingham, United Kingdom.
| | - Stine Sofia Korreman
- Department of Clinical Medicine, Aarhus University, 8000 Aarhus, Denmark; Danish Center for Particle Therapy, Aarhus University Hospital, 8200 Aarhus N, Denmark.
| | - Jean-Emmanuel Bibault
- Department of Radiation Oncology, Hôpital Européen Georges-Pompidou, Université Paris Cité, 75015 Paris, France.
| |
Collapse
|
2
|
Boulogne LH, Lorenz J, Kienzle D, Schön R, Ludwig K, Lienhart R, Jégou S, Li G, Chen C, Wang Q, Shi D, Maniparambil M, Müller D, Mertes S, Schröter N, Hellmann F, Elia M, Dirks I, Bossa MN, Berenguer AD, Mukherjee T, Vandemeulebroucke J, Sahli H, Deligiannis N, Gonidakis P, Huynh ND, Razzak I, Bouadjenek R, Verdicchio M, Borrelli P, Aiello M, Meakin JA, Lemm A, Russ C, Ionasec R, Paragios N, van Ginneken B, Revel MP. The STOIC2021 COVID-19 AI challenge: Applying reusable training methodologies to private data. Med Image Anal 2024; 97:103230. [PMID: 38875741 DOI: 10.1016/j.media.2024.103230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Revised: 01/11/2024] [Accepted: 06/03/2024] [Indexed: 06/16/2024]
Abstract
Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains absent. This study implements the Type Three (T3) challenge format, which allows for training solutions on private data and guarantees reusable training methodologies. With T3, challenge organizers train a codebase provided by the participants on sequestered training data. T3 was implemented in the STOIC2021 challenge, with the goal of predicting from a computed tomography (CT) scan whether subjects had a severe COVID-19 infection, defined as intubation or death within one month. STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects. The organizers successfully trained six of the eight Final phase submissions. The submitted codebases for training and running inference were released publicly. The winning solution obtained an area under the receiver operating characteristic curve for discerning between severe and non-severe COVID-19 of 0.815. The Final phase solutions of all finalists improved upon their Qualification phase solutions.
Collapse
Affiliation(s)
- Luuk H Boulogne
- Radboud university medical center, P.O. Box 9101, 6500HB Nijmegen, The Netherlands.
| | - Julian Lorenz
- University of Augsburg, Universitätsstraße 2, 86159 Augsburg, Germany.
| | - Daniel Kienzle
- University of Augsburg, Universitätsstraße 2, 86159 Augsburg, Germany
| | - Robin Schön
- University of Augsburg, Universitätsstraße 2, 86159 Augsburg, Germany
| | - Katja Ludwig
- University of Augsburg, Universitätsstraße 2, 86159 Augsburg, Germany
| | - Rainer Lienhart
- University of Augsburg, Universitätsstraße 2, 86159 Augsburg, Germany
| | | | - Guang Li
- Keya medical technology co. ltd, Floor 20, Building A, 1 Ronghua South Road, Yizhuang Economic Development Zone, Daxing District, Beijing, PR China.
| | - Cong Chen
- Keya medical technology co. ltd, Floor 20, Building A, 1 Ronghua South Road, Yizhuang Economic Development Zone, Daxing District, Beijing, PR China
| | - Qi Wang
- Keya medical technology co. ltd, Floor 20, Building A, 1 Ronghua South Road, Yizhuang Economic Development Zone, Daxing District, Beijing, PR China
| | - Derik Shi
- Keya medical technology co. ltd, Floor 20, Building A, 1 Ronghua South Road, Yizhuang Economic Development Zone, Daxing District, Beijing, PR China
| | - Mayug Maniparambil
- ML-Labs, Dublin City University, N210, Marconi building, Dublin City University, Glasnevin, Dublin 9, Ireland.
| | - Dominik Müller
- University of Augsburg, Universitätsstraße 2, 86159 Augsburg, Germany; Faculty of Applied Computer Science, University of Augsburg, Germany
| | - Silvan Mertes
- Faculty of Applied Computer Science, University of Augsburg, Germany
| | - Niklas Schröter
- Faculty of Applied Computer Science, University of Augsburg, Germany
| | - Fabio Hellmann
- Faculty of Applied Computer Science, University of Augsburg, Germany
| | - Miriam Elia
- Faculty of Applied Computer Science, University of Augsburg, Germany.
| | - Ine Dirks
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium.
| | - Matías Nicolás Bossa
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | - Abel Díaz Berenguer
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | - Tanmoy Mukherjee
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | - Jef Vandemeulebroucke
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | - Hichem Sahli
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | - Nikos Deligiannis
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | - Panagiotis Gonidakis
- Vrije Universiteit Brussel, Department of Electronics and Informatics, Pleinlaan 2, 1050 Brussels, Belgium; imec, Kapeldreef 75, 3001 Leuven, Belgium
| | | | - Imran Razzak
- University of New South Wales, Sydney, Australia.
| | | | | | | | | | - James A Meakin
- Radboud university medical center, P.O. Box 9101, 6500HB Nijmegen, The Netherlands
| | - Alexander Lemm
- Amazon Web Services, Marcel-Breuer-Str. 12, 80807 München, Germany
| | - Christoph Russ
- Amazon Web Services, Marcel-Breuer-Str. 12, 80807 München, Germany
| | - Razvan Ionasec
- Amazon Web Services, Marcel-Breuer-Str. 12, 80807 München, Germany
| | - Nikos Paragios
- Keya medical technology co. ltd, Floor 20, Building A, 1 Ronghua South Road, Yizhuang Economic Development Zone, Daxing District, Beijing, PR China; TheraPanacea, 75004, Paris, France
| | - Bram van Ginneken
- Radboud university medical center, P.O. Box 9101, 6500HB Nijmegen, The Netherlands
| | - Marie-Pierre Revel
- Department of Radiology, Université de Paris, APHP, Hôpital Cochin, 27 rue du Fg Saint Jacques, 75014 Paris, France
| |
Collapse
|
3
|
Yoshimura T, Kondo K, Hashimoto T, Nishioka K, Mori T, Kanehira T, Matsuura T, Takao S, Tamura H, Matsumoto T, Sutherland K, Aoyama H. Geometric target margin strategy of proton craniospinal irradiation for pediatric medulloblastoma. JOURNAL OF RADIATION RESEARCH 2024; 65:676-688. [PMID: 39278649 PMCID: PMC11420849 DOI: 10.1093/jrr/rrae066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/16/2024] [Revised: 04/23/2024] [Indexed: 09/18/2024]
Abstract
In proton craniospinal irradiation (CSI) for skeletally immature pediatric patients, a treatment plan should be developed to ensure that the dose is uniformly delivered to all vertebrae, considering the effects on bone growth balance. The technical (t) clinical target volume (CTV) is conventionally set by manually expanding the CTV from the entire intracranial space and thecal sac, based on the physician's experience. However, there are differences in contouring methods among physicians. Therefore, we aimed to propose a new geometric target margin strategy. Nine pediatric patients with medulloblastoma who underwent proton CSI were enrolled. We measured the following water equivalent lengths for each vertebra in each patient: body surface to the dorsal spinal canal, vertebral limbus, ventral spinal canal and spinous processes. A simulated tCTV (stCTV) was created by assigning geometric margins to the spinal canal using the measurement results such that the vertebral limb and dose distribution coincided with a margin assigned to account for the uncertainty of the proton beam range. The stCTV with a growth factor (correlation between body surface area and age) and tCTV were compared and evaluated. The median values of each index for cervical, thoracic and lumber spine were: the Hausdorff distance, 9.14, 9.84 and 9.77 mm; mean distance-to-agreement, 3.26, 2.65 and 2.64 mm; Dice coefficient, 0.84, 0.81 and 0.82 and Jaccard coefficient, 0.50, 0.60 and 0.62, respectively. The geometric target margin setting method used in this study was useful for creating an stCTV to ensure consistent and uniform planning.
Collapse
Affiliation(s)
- Takaaki Yoshimura
- Department of Health Sciences and Technology, Faculty of Health Sciences, Hokkaido University, Sapporo 060-0812, Japan
- Department of Medical Physics, Hokkaido University Hospital, Sapporo 060-8648, Japan
- Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, Japan
| | - Keigo Kondo
- Department of Health Sciences, School of Medicine, Hokkaido University, Sapporo 060-0812, Japan
| | - Takayuki Hashimoto
- Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, Japan
| | - Kentaro Nishioka
- Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, Japan
| | - Takashi Mori
- Department of Radiation Oncology, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, Japan
| | - Takahiro Kanehira
- Department of Medical Physics, Hokkaido University Hospital, Sapporo 060-8648, Japan
| | - Taeko Matsuura
- Department of Medical Physics, Hokkaido University Hospital, Sapporo 060-8648, Japan
- Faculty of Engineering, Hokkaido University, Sapporo 060-8638, Japan
| | - Seishin Takao
- Department of Medical Physics, Hokkaido University Hospital, Sapporo 060-8648, Japan
- Faculty of Engineering, Hokkaido University, Sapporo 060-8638, Japan
| | - Hiroshi Tamura
- Department of Radiation Technology, Hokkaido University Hospital, Sapporo 060-8648, Japan
| | - Takuya Matsumoto
- Department of Medical Physics, Hokkaido University Hospital, Sapporo 060-8648, Japan
| | - Kenneth Sutherland
- Global Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, Japan
| | - Hidefumi Aoyama
- Department of Radiation Oncology, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, Japan
| |
Collapse
|
4
|
Lin H, Zhao M, Zhu L, Pei X, Wu H, Zhang L, Li Y. Gaussian filter facilitated deep learning-based architecture for accurate and efficient liver tumor segmentation for radiation therapy. Front Oncol 2024; 14:1423774. [PMID: 38966060 PMCID: PMC11222586 DOI: 10.3389/fonc.2024.1423774] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2024] [Accepted: 06/06/2024] [Indexed: 07/06/2024] Open
Abstract
Purpose Addressing the challenges of unclear tumor boundaries and the confusion between cysts and tumors in liver tumor segmentation, this study aims to develop an auto-segmentation method utilizing Gaussian filter with the nnUNet architecture to effectively distinguish between tumors and cysts, enhancing the accuracy of liver tumor auto-segmentation. Methods Firstly, 130 cases of liver tumorsegmentation challenge 2017 (LiTS2017) were used for training and validating nnU-Net-based auto-segmentation model. Then, 14 cases of 3D-IRCADb dataset and 25 liver cancer cases retrospectively collected in our hospital were used for testing. The dice similarity coefficient (DSC) was used to evaluate the accuracy of auto-segmentation model by comparing with manual contours. Results The nnU-Net achieved an average DSC value of 0.86 for validation set (20 LiTS cases) and 0.82 for public testing set (14 3D-IRCADb cases). For clinical testing set, the standalone nnU-Net model achieved an average DSC value of 0.75, which increased to 0.81 after post-processing with the Gaussian filter (P<0.05), demonstrating its effectiveness in mitigating the influence of liver cysts on liver tumor segmentation. Conclusion Experiments show that Gaussian filter is beneficial to improve the accuracy of liver tumor segmentation in clinic.
Collapse
Affiliation(s)
- Hongyu Lin
- Department of Oncology, First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Min Zhao
- Department of Oncology, First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Lingling Zhu
- Department of Oncology, First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Xi Pei
- Technology Development Department, Anhui Wisdom Technology Co., Ltd., Hefei, China
| | - Haotian Wu
- Technology Development Department, Anhui Wisdom Technology Co., Ltd., Hefei, China
| | - Lian Zhang
- Department of Oncology, First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Ying Li
- Department of Oncology, First Hospital of Hebei Medical University, Shijiazhuang, China
| |
Collapse
|
5
|
Liu X, Qu L, Xie Z, Zhao J, Shi Y, Song Z. Towards more precise automatic analysis: a systematic review of deep learning-based multi-organ segmentation. Biomed Eng Online 2024; 23:52. [PMID: 38851691 PMCID: PMC11162022 DOI: 10.1186/s12938-024-01238-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 04/11/2024] [Indexed: 06/10/2024] Open
Abstract
Accurate segmentation of multiple organs in the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy. In the past few years, with a data-driven feature extraction approach and end-to-end training, automatic deep learning-based multi-organ segmentation methods have far outperformed traditional methods and become a new research topic. This review systematically summarizes the latest research in this field. We searched Google Scholar for papers published from January 1, 2016 to December 31, 2023, using keywords "multi-organ segmentation" and "deep learning", resulting in 327 papers. We followed the PRISMA guidelines for paper selection, and 195 studies were deemed to be within the scope of this review. We summarized the two main aspects involved in multi-organ segmentation: datasets and methods. Regarding datasets, we provided an overview of existing public datasets and conducted an in-depth analysis. Concerning methods, we categorized existing approaches into three major classes: fully supervised, weakly supervised and semi-supervised, based on whether they require complete label information. We summarized the achievements of these methods in terms of segmentation accuracy. In the discussion and conclusion section, we outlined and summarized the current trends in multi-organ segmentation.
Collapse
Affiliation(s)
- Xiaoyu Liu
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 138 Yixueyuan Road, Shanghai, 200032, People's Republic of China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai, 200032, China
| | - Linhao Qu
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 138 Yixueyuan Road, Shanghai, 200032, People's Republic of China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai, 200032, China
| | - Ziyue Xie
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 138 Yixueyuan Road, Shanghai, 200032, People's Republic of China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai, 200032, China
| | - Jiayue Zhao
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 138 Yixueyuan Road, Shanghai, 200032, People's Republic of China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai, 200032, China
| | - Yonghong Shi
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 138 Yixueyuan Road, Shanghai, 200032, People's Republic of China.
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai, 200032, China.
| | - Zhijian Song
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 138 Yixueyuan Road, Shanghai, 200032, People's Republic of China.
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai, 200032, China.
| |
Collapse
|
6
|
Temple SWP, Rowbottom CG. Gross failure rates and failure modes for a commercial AI-based auto-segmentation algorithm in head and neck cancer patients. J Appl Clin Med Phys 2024; 25:e14273. [PMID: 38263866 PMCID: PMC11163497 DOI: 10.1002/acm2.14273] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 12/15/2023] [Accepted: 12/20/2023] [Indexed: 01/25/2024] Open
Abstract
PURPOSE Artificial intelligence (AI) based commercial software can be used to automatically delineate organs at risk (OAR), with potential for efficiency savings in the radiotherapy treatment planning pathway, and reduction of inter- and intra-observer variability. There has been little research investigating gross failure rates and failure modes of such systems. METHOD 50 head and neck (H&N) patient data sets with "gold standard" contours were compared to AI-generated contours to produce expected mean and standard deviation values for the Dice Similarity Coefficient (DSC), for four common H&N OARs (brainstem, mandible, left and right parotid). An AI-based commercial system was applied to 500 H&N patients. AI-generated contours were compared to manual contours, outlined by an expert human, and a gross failure was set at three standard deviations below the expected mean DSC. Failures were inspected to assess reason for failure of the AI-based system with failures relating to suboptimal manual contouring censored. True failures were classified into 4 sub-types (setup position, anatomy, image artefacts and unknown). RESULTS There were 24 true failures of the AI-based commercial software, a gross failure rate of 1.2%. Fifteen failures were due to patient anatomy, four were due to dental image artefacts, three were due to patient position and two were unknown. True failure rates by OAR were 0.4% (brainstem), 2.2% (mandible), 1.4% (left parotid) and 0.8% (right parotid). CONCLUSION True failures of the AI-based system were predominantly associated with a non-standard element within the CT scan. It is likely that these non-standard elements were the reason for the gross failure, and suggests that patient datasets used to train the AI model did not contain sufficient heterogeneity of data. Regardless of the reasons for failure, the true failure rate for the AI-based system in the H&N region for the OARs investigated was low (∼1%).
Collapse
Affiliation(s)
- Simon W. P. Temple
- Medical Physics DepartmentThe Clatterbridge Cancer Centre NHS Foundation TrustLiverpoolUK
| | - Carl G. Rowbottom
- Medical Physics DepartmentThe Clatterbridge Cancer Centre NHS Foundation TrustLiverpoolUK
- Department of PhysicsUniversity of LiverpoolLiverpoolUK
| |
Collapse
|
7
|
Li Z, Gan G, Guo J, Zhan W, Chen L. Accurate object localization facilitates automatic esophagus segmentation in deep learning. Radiat Oncol 2024; 19:55. [PMID: 38735947 PMCID: PMC11088757 DOI: 10.1186/s13014-024-02448-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Accepted: 05/01/2024] [Indexed: 05/14/2024] Open
Abstract
BACKGROUND Currently, automatic esophagus segmentation remains a challenging task due to its small size, low contrast, and large shape variation. We aimed to improve the performance of esophagus segmentation in deep learning by applying a strategy that involves locating the object first and then performing the segmentation task. METHODS A total of 100 cases with thoracic computed tomography scans from two publicly available datasets were used in this study. A modified CenterNet, an object location network, was employed to locate the center of the esophagus for each slice. Subsequently, the 3D U-net and 2D U-net_coarse models were trained to segment the esophagus based on the predicted object center. A 2D U-net_fine model was trained based on the updated object center according to the 3D U-net model. The dice similarity coefficient and the 95% Hausdorff distance were used as quantitative evaluation indexes for the delineation performance. The characteristics of the automatically delineated esophageal contours by the 2D U-net and 3D U-net models were summarized. Additionally, the impact of the accuracy of object localization on the delineation performance was analyzed. Finally, the delineation performance in different segments of the esophagus was also summarized. RESULTS The mean dice coefficient of the 3D U-net, 2D U-net_coarse, and 2D U-net_fine models were 0.77, 0.81, and 0.82, respectively. The 95% Hausdorff distance for the above models was 6.55, 3.57, and 3.76, respectively. Compared with the 2D U-net, the 3D U-net has a lower incidence of delineating wrong objects and a higher incidence of missing objects. After using the fine object center, the average dice coefficient was improved by 5.5% in the cases with a dice coefficient less than 0.75, while that value was only 0.3% in the cases with a dice coefficient greater than 0.75. The dice coefficients were lower for the esophagus between the orifice of the inferior and the pulmonary bifurcation compared with the other regions. CONCLUSION The 3D U-net model tended to delineate fewer incorrect objects but also miss more objects. Two-stage strategy with accurate object location could enhance the robustness of the segmentation model and significantly improve the esophageal delineation performance, especially for cases with poor delineation results.
Collapse
Affiliation(s)
- Zhibin Li
- Department of Radiation Oncology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Guanghui Gan
- Department of Radiation Oncology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Jian Guo
- Department of Radiation Oncology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Wei Zhan
- Department of Radiation Oncology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Long Chen
- Department of Radiation Oncology, The First Affiliated Hospital of Soochow University, Suzhou, China.
| |
Collapse
|
8
|
Koitka S, Baldini G, Kroll L, van Landeghem N, Pollok OB, Haubold J, Pelka O, Kim M, Kleesiek J, Nensa F, Hosch R. SAROS: A dataset for whole-body region and organ segmentation in CT imaging. Sci Data 2024; 11:483. [PMID: 38729970 PMCID: PMC11087485 DOI: 10.1038/s41597-024-03337-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Accepted: 05/01/2024] [Indexed: 05/12/2024] Open
Abstract
The Sparsely Annotated Region and Organ Segmentation (SAROS) dataset was created using data from The Cancer Imaging Archive (TCIA) to provide a large open-access CT dataset with high-quality annotations of body landmarks. In-house segmentation models were employed to generate annotation proposals on randomly selected cases from TCIA. The dataset includes 13 semantic body region labels (abdominal/thoracic cavity, bones, brain, breast implant, mediastinum, muscle, parotid/submandibular/thyroid glands, pericardium, spinal cord, subcutaneous tissue) and six body part labels (left/right arm/leg, head, torso). Case selection was based on the DICOM series description, gender, and imaging protocol, resulting in 882 patients (438 female) for a total of 900 CTs. Manual review and correction of proposals were conducted in a continuous quality control cycle. Only every fifth axial slice was annotated, yielding 20150 annotated slices from 28 data collections. For the reproducibility on downstream tasks, five cross-validation folds and a test set were pre-defined. The SAROS dataset serves as an open-access resource for training and evaluating novel segmentation models, covering various scanner vendors and diseases.
Collapse
Affiliation(s)
- Sven Koitka
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - Giulia Baldini
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - Lennard Kroll
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
| | - Natalie van Landeghem
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
| | - Olivia B Pollok
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - Johannes Haubold
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
| | - Obioma Pelka
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
- Data Integration Center, Central IT Department, University Hospital Essen, Essen, Germany
| | - Moon Kim
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - Jens Kleesiek
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - Felix Nensa
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - René Hosch
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany.
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany.
| |
Collapse
|
9
|
Du W, Guo H, Chen B, Cui M, Zhang T, Sun D, Ma H. Cascaded-TOARNet: A cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation. Med Phys 2024; 51:3405-3420. [PMID: 38063140 DOI: 10.1002/mp.16881] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2023] [Revised: 10/20/2023] [Accepted: 11/19/2023] [Indexed: 05/08/2024] Open
Abstract
BACKGROUND Accurate and automated segmentation of thoracic organs-at-risk (OARs) is critical for radiotherapy treatment planning of thoracic cancers. However, this has remained a challenging task for four major reasons: (1) thoracic OARs have diverse morphologies; (2) thoracic OARs have low contrast with the background; (3) boundaries of thoracic OARs are blurry; (4) class imbalance issue caused by small organs. PURPOSE To overcome the above challenges and achieve accurate and automated segmentation of thoracic OARs on thoracic CT. METHODS A novel cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation, called Cascaded-TOARNet. This cascaded framework comprises two stages: localization and segmentation. During the localization stage, TOARNet locates each organ to crop the regions of interest (ROIs). During the segmentation stage, TOARNet accurately segments the ROIs, and the segmentation results are merged into a complete result. RESULTS We evaluated our proposed method and other common segmentation methods on two public datasets: the AAPM Thoracic Auto-Segmentation Challenge dataset and the Segmentation of Thoracic Organs at Risk (SegTHOR) dataset. Our method demonstrated superior performance, achieving a mean Dice score of 92.6% on the SegTHOR dataset and 90.8% on the AAPM dataset. CONCLUSIONS This segmentation method holds great promise as an essential tool for enhancing the efficiency of thoracic radiotherapy planning.
Collapse
Affiliation(s)
- Wu Du
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China
| | - Huimin Guo
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China
| | - Boyang Chen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China
| | - Ming Cui
- Gastrointestinal and Urinary and Musculoskeletal Cancer, Cancer Hospital of Dalian University of Technology, Shenyang, Liaoning, China
| | - Teng Zhang
- Gastrointestinal and Urinary and Musculoskeletal Cancer, Cancer Hospital of Dalian University of Technology, Shenyang, Liaoning, China
| | - Deyu Sun
- Gastrointestinal and Urinary and Musculoskeletal Cancer, Cancer Hospital of Dalian University of Technology, Shenyang, Liaoning, China
| | - He Ma
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Shenyang, Liaoning, China
| |
Collapse
|
10
|
Rong Y, Chen Q, Fu Y, Yang X, Al-Hallaq HA, Wu QJ, Yuan L, Xiao Y, Cai B, Latifi K, Benedict SH, Buchsbaum JC, Qi XS. NRG Oncology Assessment of Artificial Intelligence Deep Learning-Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions. Int J Radiat Oncol Biol Phys 2024; 119:261-280. [PMID: 37972715 PMCID: PMC11023777 DOI: 10.1016/j.ijrobp.2023.10.033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Revised: 09/16/2023] [Accepted: 10/14/2023] [Indexed: 11/19/2023]
Abstract
Deep learning neural networks (DLNN) in Artificial intelligence (AI) have been extensively explored for automatic segmentation in radiotherapy (RT). In contrast to traditional model-based methods, data-driven AI-based models for auto-segmentation have shown high accuracy in early studies in research settings and controlled environment (single institution). Vendor-provided commercial AI models are made available as part of the integrated treatment planning system (TPS) or as a stand-alone tool that provides streamlined workflow interacting with the main TPS. These commercial tools have drawn clinics' attention thanks to their significant benefit in reducing the workload from manual contouring and shortening the duration of treatment planning. However, challenges occur when applying these commercial AI-based segmentation models to diverse clinical scenarios, particularly in uncontrolled environments. Contouring nomenclature and guideline standardization has been the main task undertaken by the NRG Oncology. AI auto-segmentation holds the potential clinical trial participants to reduce interobserver variations, nomenclature non-compliance, and contouring guideline deviations. Meanwhile, trial reviewers could use AI tools to verify contour accuracy and compliance of those submitted datasets. In recognizing the growing clinical utilization and potential of these commercial AI auto-segmentation tools, NRG Oncology has formed a working group to evaluate the clinical utilization and potential of commercial AI auto-segmentation tools. The group will assess in-house and commercially available AI models, evaluation metrics, clinical challenges, and limitations, as well as future developments in addressing these challenges. General recommendations are made in terms of the implementation of these commercial AI models, as well as precautions in recognizing the challenges and limitations.
Collapse
Affiliation(s)
- Yi Rong
- Mayo Clinic Arizona, Phoenix, AZ
| | - Quan Chen
- City of Hope Comprehensive Cancer Center Duarte, CA
| | - Yabo Fu
- Memorial Sloan Kettering Cancer Center, Commack, NY
| | | | | | | | - Lulin Yuan
- Virginia Commonwealth University, Richmond, VA
| | - Ying Xiao
- University of Pennsylvania/Abramson Cancer Center, Philadelphia, PA
| | - Bin Cai
- The University of Texas Southwestern Medical Center, Dallas, TX
| | | | - Stanley H Benedict
- University of California Davis Comprehensive Cancer Center, Sacramento, CA
| | | | - X Sharon Qi
- University of California Los Angeles, Los Angeles, CA
| |
Collapse
|
11
|
Lin W, Gao Z, Liu H, Zhang H. A Deformable Constraint Transport Network for Optimal Aortic Segmentation From CT Images. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:1462-1475. [PMID: 38048241 DOI: 10.1109/tmi.2023.3339142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/06/2023]
Abstract
Aortic segmentation from computed tomography (CT) is crucial for facilitating aortic intervention, as it enables clinicians to visualize aortic anatomy for diagnosis and measurement. However, aortic segmentation faces the challenge of variable geometry in space, as the geometric diversity of different diseases and the geometric transformations that occur between raw and measured images. Existing constraint-based methods can potentially solve the challenge, but they are hindered by two key issues: inaccurate definition of properties and inappropriate topology of transformation in space. In this paper, we propose a deformable constraint transport network (DCTN). The DCTN adaptively extracts aortic features to define intra-image constrained properties and guides topological implementation in space to constrain inter-image geometric transformation between raw and curved planar reformation (CPR) images. The DCTN contains a deformable attention extractor, a geometry-aware decoder and an optimal transport guider. The extractor generates variable patches that preserve semantic integrity and long-range dependency in long-sequence images. The decoder enhances the perception of geometric texture and semantic features, particularly for low-intensity aortic coarctation and false lumen, which removes background interference. The guider explores the geometric discrepancies between raw and CPR images, constructs probability distributions of discrepancies, and matches them with inter-image transformation to guide geometric topology in space. Experimental studies on 267 aortic subjects and four public datasets show the superiority of our DCTN over 23 methods. The results demonstrate DCTN's advantages in aortic segmentation for different types of aortic disease, for different aortic segments, and in the measurement of clinical indexes.
Collapse
|
12
|
Dwivedi K, Sharkey M, Alabed S, Langlotz CP, Swift AJ, Bluethgen C. External validation, radiological evaluation, and development of deep learning automatic lung segmentation in contrast-enhanced chest CT. Eur Radiol 2024; 34:2727-2737. [PMID: 37775589 PMCID: PMC10957646 DOI: 10.1007/s00330-023-10235-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Revised: 06/25/2023] [Accepted: 07/24/2023] [Indexed: 10/01/2023]
Abstract
OBJECTIVES There is a need for CT pulmonary angiography (CTPA) lung segmentation models. Clinical translation requires radiological evaluation of model outputs, understanding of limitations, and identification of failure points. This multicentre study aims to develop an accurate CTPA lung segmentation model, with evaluation of outputs in two diverse patient cohorts with pulmonary hypertension (PH) and interstitial lung disease (ILD). METHODS This retrospective study develops an nnU-Net-based segmentation model using data from two specialist centres (UK and USA). Model was trained (n = 37), tested (n = 12), and clinically evaluated (n = 176) on a diverse 'real-world' cohort of 225 PH patients with volumetric CTPAs. Dice score coefficient (DSC) and normalised surface distance (NSD) were used for testing. Clinical evaluation of outputs was performed by two radiologists who assessed clinical significance of errors. External validation was performed on heterogenous contrast and non-contrast scans from 28 ILD patients. RESULTS A total of 225 PH and 28 ILD patients with diverse demographic and clinical characteristics were evaluated. Mean accuracy, DSC, and NSD scores were 0.998 (95% CI 0.9976, 0.9989), 0.990 (0.9840, 0.9962), and 0.983 (0.9686, 0.9972) respectively. There were no segmentation failures. On radiological review, 82% and 71% of internal and external cases respectively had no errors. Eighteen percent and 25% respectively had clinically insignificant errors. Peripheral atelectasis and consolidation were common causes for suboptimal segmentation. One external case (0.5%) with patulous oesophagus had a clinically significant error. CONCLUSION State-of-the-art CTPA lung segmentation model provides accurate outputs with minimal clinical errors on evaluation across two diverse cohorts with PH and ILD. CLINICAL RELEVANCE Clinical translation of artificial intelligence models requires radiological review and understanding of model limitations. This study develops an externally validated state-of-the-art model with robust radiological review. Intended clinical use is in techniques such as lung volume or parenchymal disease quantification. KEY POINTS • Accurate, externally validated CT pulmonary angiography (CTPA) lung segmentation model tested in two large heterogeneous clinical cohorts (pulmonary hypertension and interstitial lung disease). • No segmentation failures and robust review of model outputs by radiologists found 1 (0.5%) clinically significant segmentation error. • Intended clinical use of this model is a necessary step in techniques such as lung volume, parenchymal disease quantification, or pulmonary vessel analysis.
Collapse
Affiliation(s)
- Krit Dwivedi
- Department of Infection, Immunity & Cardiovascular Disease, Medical School, University of Sheffield, Sheffield, UK.
- Academic Department of Radiology, Royal Hallamshire Hospital, Glossop Road, Sheffield, S10 2JF, USA.
| | - Michael Sharkey
- 3DLab, Sheffield Teaching Hospitals NHS Trust, Sheffield, UK
| | - Samer Alabed
- Department of Infection, Immunity & Cardiovascular Disease, Medical School, University of Sheffield, Sheffield, UK
| | - Curtis P Langlotz
- Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI), Stanford University, Sheffield, USA
| | - Andy J Swift
- Department of Infection, Immunity & Cardiovascular Disease, Medical School, University of Sheffield, Sheffield, UK
| | - Christian Bluethgen
- Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI), Stanford University, Sheffield, USA
| |
Collapse
|
13
|
Qi H, Wang Z, Qi X, Shi Y, Xie T. Ultrasound image segmentation of renal tumors based on UNet++ with fusion of multiscale residuals and dual attention. Phys Med Biol 2024; 69:075002. [PMID: 38412532 DOI: 10.1088/1361-6560/ad2d7f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 02/27/2024] [Indexed: 02/29/2024]
Abstract
Objective. Laparoscopic renal unit-preserving resection is a routine and effective means of treating renal tumors. Image segmentation is an essential part before tumor resection. The current segmentation method mainly relies on doctors manual delineation, which is time-consuming, labor-intensive, and influenced by their personal experience and ability. And the image quality of segmentation is low, with problems such as blurred edges, unclear size and shape, which are not conducive to clinical diagnosis.Approach. To address these problems, we propose an automated segmentation method, i.e. the UNet++ algorithm fusing multiscale residuals and dual attention (MRDA_UNet++). It replaces two consecutive 3 × 3 convolutions in UNet++ with the 'MultiRes block' module, which incorporates coordinate attention to fuse features from different scales and suppress the impact of background noise. Furthermore, an attention gate is also added at the short connections to enhance the ability of the network to extract features from the target area.Main results. The experimental results show that MRDA_UNet++ achieves 93.18%, 92.87%, 93.66%, and 92.09% on the real-world dataset for MIoU, Dice, Precision, and Recall, respectively. Compared to the baseline model UNet++ on three public datasets, the MIoU, Dice, and Recall metrics improved by 6.00%, 7.90% and 18.09% respectively for BUSI, 0.39%, 0.27% and 1.03% for Dataset C, and 1.37%, 1.75% and 1.30% for DDTI.Significance. The proposed MRDA_UNet++ exhibits obvious advantages in feature extraction, which can not only significantly reduce the workload of doctors, but also further decrease the risk of misdiagnosis. It is of great value to assist doctors diagnosis in the clinic.
Collapse
Affiliation(s)
- Hui Qi
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Zhen Wang
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Xiaobo Qi
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Ying Shi
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Tianwu Xie
- Institute of Radiation Medicine, Fudan University, Shanghai 200032, People's Republic of China
| |
Collapse
|
14
|
Li Y, Shao HC, Liang X, Chen L, Li R, Jiang S, Wang J, Zhang Y. Zero-Shot Medical Image Translation via Frequency-Guided Diffusion Models. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:980-993. [PMID: 37851552 PMCID: PMC11000254 DOI: 10.1109/tmi.2023.3325703] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/20/2023]
Abstract
Recently, the diffusion model has emerged as a superior generative model that can produce high quality and realistic images. However, for medical image translation, the existing diffusion models are deficient in accurately retaining structural information since the structure details of source domain images are lost during the forward diffusion process and cannot be fully recovered through learned reverse diffusion, while the integrity of anatomical structures is extremely important in medical images. For instance, errors in image translation may distort, shift, or even remove structures and tumors, leading to incorrect diagnosis and inadequate treatments. Training and conditioning diffusion models using paired source and target images with matching anatomy can help. However, such paired data are very difficult and costly to obtain, and may also reduce the robustness of the developed model to out-of-distribution testing data. We propose a frequency-guided diffusion model (FGDM) that employs frequency-domain filters to guide the diffusion model for structure-preserving image translation. Based on its design, FGDM allows zero-shot learning, as it can be trained solely on the data from the target domain, and used directly for source-to-target domain translation without any exposure to the source-domain data during training. We evaluated it on three cone-beam CT (CBCT)-to-CT translation tasks for different anatomical sites, and a cross-institutional MR imaging translation task. FGDM outperformed the state-of-the-art methods (GAN-based, VAE-based, and diffusion-based) in metrics of Fréchet Inception Distance (FID), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM), showing its significant advantages in zero-shot medical image translation.
Collapse
|
15
|
Maes D, Gates EDH, Meyer J, Kang J, Nguyen BNT, Lavilla M, Melancon D, Weg ES, Tseng YD, Lim A, Bowen SR. Framework for Radiation Oncology Department-wide Evaluation and Implementation of Commercial Artificial Intelligence Autocontouring. Pract Radiat Oncol 2024; 14:e150-e158. [PMID: 37935308 DOI: 10.1016/j.prro.2023.10.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Revised: 10/19/2023] [Accepted: 10/22/2023] [Indexed: 11/09/2023]
Abstract
PURPOSE Artificial intelligence (AI)-based autocontouring in radiation oncology has potential benefits such as standardization and time savings. However, commercial AI solutions require careful evaluation before clinical integration. We developed a multidimensional evaluation method to test pretrained AI-based automated contouring solutions across a network of clinics. METHODS AND MATERIALS Curated data included 121 patient planning computed tomography (CT) scans with a total of 859 clinically approved contours used for treatment from 4 clinics. Regions of interest (ROIs) were generated with 3 commercial AI-based automated contouring software solutions (AI1, AI2, AI3) spanning the following disease sites: brain, head and neck (H&N), thorax, abdomen, and pelvis. Quantitative agreement between AI-generated and clinical contours was measured by Dice similarity coefficient (DSC) and Hausdorff distance (HD). Qualitative assessment was performed by multiple experts scoring blinded AI-contours using a Likert scale. Workflow and usability surveying was also conducted. RESULTS AI1, AI2, and AI3 contours had high quantitative agreement in 27.8%, 32.8%, and 34.1% of cases (DSC >0.9), performing well in pelvis (median DSC = 0.86/0.88/0.91) and thorax (median DSC = 0.91/0.89/0.91). All 3 solutions had low quantitative agreement in 7.4%, 8.8%, and 6.1% of cases (DSC <0.5), performing worse in brain (median DSC = 0.65/0.78/0.75) and H&N (median DSC = 0.76/0.80/0.81). Qualitatively, AI1 and AI2 contours were acceptable (rated 1-2) with at most minor edits in 70.7% and 74.6% of ROIs (2906 ratings), higher for abdomen (AI1: 79.2%) and thorax (AI2: 90.2%), and lower for H&N (29.0/35.6%). An end-user survey showed strong user preference for full automation and mixed preferences for accuracy versus total number of structures generated. CONCLUSIONS Our evaluation method provided a comprehensive analysis of both quantitative and qualitative measures of commercially available pretrained AI autocontouring algorithms. The evaluation framework served as a roadmap for clinical integration that aligned with user workflow preference.
Collapse
Affiliation(s)
- Dominic Maes
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington; Department of Radiation Oncology, University of Washington, Seattle, Washington.
| | - Evan D H Gates
- Department of Radiation Oncology, University of Washington, Seattle, Washington
| | - Juergen Meyer
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington; Department of Radiation Oncology, University of Washington, Seattle, Washington
| | - John Kang
- Department of Radiation Oncology, University of Washington, Seattle, Washington
| | - Bao-Ngoc Thi Nguyen
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington
| | - Myra Lavilla
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington
| | - Dustin Melancon
- Department of Radiation Oncology, University of Washington, Seattle, Washington
| | - Emily S Weg
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington; Department of Radiation Oncology, University of Washington, Seattle, Washington
| | - Yolanda D Tseng
- Department of Radiation Oncology, University of Washington, Seattle, Washington; Clinical Research Division, Fred Hutchinson Cancer Center, Seattle, Washington
| | - Andrew Lim
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington; Department of Radiation Oncology, University of Washington, Seattle, Washington; Department of Radiation Oncology, University of Southern California, Los Angeles, California
| | - Stephen R Bowen
- Department of Radiation Oncology, Fred Hutchinson Cancer Center, Seattle, Washington; Department of Radiation Oncology, University of Washington, Seattle, Washington; Department of Radiology, University of Washington, Seattle, Washington
| |
Collapse
|
16
|
Bibault JE, Giraud P. Deep learning for automated segmentation in radiotherapy: a narrative review. Br J Radiol 2024; 97:13-20. [PMID: 38263838 PMCID: PMC11027240 DOI: 10.1093/bjr/tqad018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2023] [Revised: 08/10/2023] [Accepted: 10/27/2023] [Indexed: 01/25/2024] Open
Abstract
The segmentation of organs and structures is a critical component of radiation therapy planning, with manual segmentation being a laborious and time-consuming task. Interobserver variability can also impact the outcomes of radiation therapy. Deep neural networks have recently gained attention for their ability to automate segmentation tasks, with convolutional neural networks (CNNs) being a popular approach. This article provides a descriptive review of the literature on deep learning (DL) techniques for segmentation in radiation therapy planning. This review focuses on five clinical sub-sites and finds that U-net is the most commonly used CNN architecture. The studies using DL for image segmentation were included in brain, head and neck, lung, abdominal, and pelvic cancers. The majority of DL segmentation articles in radiation therapy planning have concentrated on normal tissue structures. N-fold cross-validation was commonly employed, without external validation. This research area is expanding quickly, and standardization of metrics and independent validation are critical to benchmarking and comparing proposed methods.
Collapse
Affiliation(s)
- Jean-Emmanuel Bibault
- Radiation Oncology Department, Georges Pompidou European Hospital, Assistance Publique—Hôpitaux de Paris, Université de Paris Cité, Paris, 75015, France
- INSERM UMR 1138, Centre de Recherche des Cordeliers, Paris, 75006, France
| | - Paul Giraud
- INSERM UMR 1138, Centre de Recherche des Cordeliers, Paris, 75006, France
- Radiation Oncology Department, Pitié Salpêtrière Hospital, Assistance Publique—Hôpitaux de Paris, Paris Sorbonne Universités, Paris, 75013, France
| |
Collapse
|
17
|
Reska D, Kretowski M. GPU-accelerated lung CT segmentation based on level sets and texture analysis. Sci Rep 2024; 14:1444. [PMID: 38228773 PMCID: PMC10792028 DOI: 10.1038/s41598-024-51452-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Accepted: 01/05/2024] [Indexed: 01/18/2024] Open
Abstract
This paper presents a novel semi-automatic method for lung segmentation in thoracic CT datasets. The fully three-dimensional algorithm is based on a level set representation of an active surface and integrates texture features to improve its robustness. The method's performance is enhanced by the graphics processing unit (GPU) acceleration. The segmentation process starts with a manual initialisation of 2D contours on a few representative slices of the analysed volume. Next, the starting regions for the active surface are generated according to the probability maps of texture features. The active surface is then evolved to give the final segmentation result. The recent implementation employs features based on grey-level co-occurrence matrices and Gabor filters. The algorithm was evaluated on real medical imaging data from the LCTCS 2017 challenge. The results were also compared with the outcomes of other segmentation methods. The proposed approach provided high segmentation accuracy while offering very competitive performance.
Collapse
Affiliation(s)
- Daniel Reska
- Faculty of Computer Science, Bialystok University of Technology, Białystok, Poland.
| | - Marek Kretowski
- Faculty of Computer Science, Bialystok University of Technology, Białystok, Poland
| |
Collapse
|
18
|
Chen Y, Pahlavian SH, Jacobs P, Neupane T, Forghani-Arani F, Castillo E, Castillo R, Vinogradskiy Y. Systematic Evaluation of the Impact of Lung Segmentation Methods on 4-Dimensional Computed Tomography Ventilation Imaging Using a Large Patient Database. Int J Radiat Oncol Biol Phys 2024; 118:242-252. [PMID: 37607642 PMCID: PMC10842520 DOI: 10.1016/j.ijrobp.2023.08.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2023] [Revised: 08/04/2023] [Accepted: 08/08/2023] [Indexed: 08/24/2023]
Abstract
PURPOSE A novel form of lung functional imaging applied for functional avoidance radiation therapy has been developed that uses 4-dimensional computed tomography (4DCT) data and image processing techniques to calculate lung ventilation (4DCT-ventilation). Lung segmentation is a common step to define a region of interest for 4DCT-ventilation generation. The purpose of this study was to quantitatively evaluate the sensitivity of 4DCT-ventilation imaging using different lung segmentation methods. METHODS AND MATERIALS The 4DCT data of 350 patients from 2 institutions were used. Lung contours were generated using 3 methods: (1) reference segmentations that removed airways and pulmonary vasculature manually (Lung-Manual), (2) standard lung contours used for planning (Lung-RadOnc), and (3) artificial intelligence (AI)-based contours that removed the airways and pulmonary vasculature (Lung-AI). The AI model was based on a residual 3-dimensional U-Net and was trained using the Lung-Manual contours of 279 patients. We compared the Lung-RadOnc or Lung-AI with Lung-Manual contours for the entire 4DCT-ventilation functional avoidance process including lung segmentation (surface Dice similarity coefficient [Surface DSC]), 4DCT-ventilation generation (correlation), and subanalysis of 10 patients on a dosimetric endpoint (percentage of high functional volume of lung receiving ≥20 Gy [fV20{%}]). RESULTS Surface DSC comparing Lung-Manual/Lung-RadOnc and Lung-Manual/Lung-AI contours was 0.40 ± 0.06 and 0.86 ± 0.04, respectively. The correlation between 4DCT-ventilation images generated with Lung-Manual/Lung-RadOnc and Lung-Manual/Lung-AI were 0.48 ± 0.14 and 0.85 ± 0.14, respectively. The difference in fV20[%] between 4DCT-ventilation generated with Lung-Manual/Lung-RadOnc and Lung-Manual/Lung-AI was 2.5% ± 4.1% and 0.3% ± 0.5%, respectively. CONCLUSIONS Our work showed that using standard planning lung contours can result in significantly variable 4DCT-ventilation images. The study demonstrated that AI-based segmentations generate lung contours and 4DCT-ventilation images that are similar to those generated using manual methods. The significance of the study is that it characterizes the lung segmentation sensitivity of the 4DCT-ventilation process and develops methods that can facilitate the integration of this novel imaging in busy clinics.
Collapse
Affiliation(s)
- Yingxuan Chen
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, Pennsylvania
| | | | | | - Taindra Neupane
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, Pennsylvania
| | | | - Edward Castillo
- Department of Biomedical Engineering, University of Texas at Austin, Austin, Texas
| | - Richard Castillo
- Department of Radiation Oncology, Emory University, Atlanta, Georgia
| | - Yevgeniy Vinogradskiy
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, Pennsylvania.
| |
Collapse
|
19
|
Nenoff L, Amstutz F, Murr M, Archibald-Heeren B, Fusella M, Hussein M, Lechner W, Zhang Y, Sharp G, Vasquez Osorio E. Review and recommendations on deformable image registration uncertainties for radiotherapy applications. Phys Med Biol 2023; 68:24TR01. [PMID: 37972540 PMCID: PMC10725576 DOI: 10.1088/1361-6560/ad0d8a] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Revised: 10/30/2023] [Accepted: 11/15/2023] [Indexed: 11/19/2023]
Abstract
Deformable image registration (DIR) is a versatile tool used in many applications in radiotherapy (RT). DIR algorithms have been implemented in many commercial treatment planning systems providing accessible and easy-to-use solutions. However, the geometric uncertainty of DIR can be large and difficult to quantify, resulting in barriers to clinical practice. Currently, there is no agreement in the RT community on how to quantify these uncertainties and determine thresholds that distinguish a good DIR result from a poor one. This review summarises the current literature on sources of DIR uncertainties and their impact on RT applications. Recommendations are provided on how to handle these uncertainties for patient-specific use, commissioning, and research. Recommendations are also provided for developers and vendors to help users to understand DIR uncertainties and make the application of DIR in RT safer and more reliable.
Collapse
Affiliation(s)
- Lena Nenoff
- Department of Radiation Oncology, Massachusetts General Hospital, Boston, MA, United States of America
- Harvard Medical School, Boston, MA, United States of America
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, Dresden Germany
- Helmholtz-Zentrum Dresden—Rossendorf, Institute of Radiooncology—OncoRay, Dresden, Germany
| | - Florian Amstutz
- Department of Physics, ETH Zurich, Switzerland
- Center for Proton Therapy, Paul Scherrer Institute, Villigen PSI, Switzerland
- Division of Medical Radiation Physics and Department of Radiation Oncology, Inselspital, Bern University Hospital, and University of Bern, Bern, Switzerland
| | - Martina Murr
- Section for Biomedical Physics, Department of Radiation Oncology, University of Tübingen, Germany
| | | | - Marco Fusella
- Department of Radiation Oncology, Abano Terme Hospital, Italy
| | - Mohammad Hussein
- Metrology for Medical Physics, National Physical Laboratory, Teddington, United Kingdom
| | - Wolfgang Lechner
- Department of Radiation Oncology, Medical University of Vienna, Austria
| | - Ye Zhang
- Center for Proton Therapy, Paul Scherrer Institute, Villigen PSI, Switzerland
| | - Greg Sharp
- Department of Radiation Oncology, Massachusetts General Hospital, Boston, MA, United States of America
- Harvard Medical School, Boston, MA, United States of America
| | - Eliana Vasquez Osorio
- Division of Cancer Sciences, The University of Manchester, Manchester, United Kingdom
| |
Collapse
|
20
|
Keicher M, Burwinkel H, Bani-Harouni D, Paschali M, Czempiel T, Burian E, Makowski MR, Braren R, Navab N, Wendler T. Multimodal graph attention network for COVID-19 outcome prediction. Sci Rep 2023; 13:19539. [PMID: 37945590 PMCID: PMC10636061 DOI: 10.1038/s41598-023-46625-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Accepted: 11/03/2023] [Indexed: 11/12/2023] Open
Abstract
When dealing with a newly emerging disease such as COVID-19, the impact of patient- and disease-specific factors (e.g., body weight or known co-morbidities) on the immediate course of the disease is largely unknown. An accurate prediction of the most likely individual disease progression can improve the planning of limited resources and finding the optimal treatment for patients. In the case of COVID-19, the need for intensive care unit (ICU) admission of pneumonia patients can often only be determined on short notice by acute indicators such as vital signs (e.g., breathing rate, blood oxygen levels), whereas statistical analysis and decision support systems that integrate all of the available data could enable an earlier prognosis. To this end, we propose a holistic, multimodal graph-based approach combining imaging and non-imaging information. Specifically, we introduce a multimodal similarity metric to build a population graph that shows a clustering of patients. For each patient in the graph, we extract radiomic features from a segmentation network that also serves as a latent image feature encoder. Together with clinical patient data like vital signs, demographics, and lab results, these modalities are combined into a multimodal representation of each patient. This feature extraction is trained end-to-end with an image-based Graph Attention Network to process the population graph and predict the COVID-19 patient outcomes: admission to ICU, need for ventilation, and mortality. To combine multiple modalities, radiomic features are extracted from chest CTs using a segmentation neural network. Results on a dataset collected in Klinikum rechts der Isar in Munich, Germany and the publicly available iCTCF dataset show that our approach outperforms single modality and non-graph baselines. Moreover, our clustering and graph attention increases understanding of the patient relationships within the population graph and provides insight into the network's decision-making process.
Collapse
Affiliation(s)
- Matthias Keicher
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany.
| | - Hendrik Burwinkel
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany
| | - David Bani-Harouni
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany
| | - Magdalini Paschali
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, 94304, USA
| | - Tobias Czempiel
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany
| | - Egon Burian
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Marcus R Makowski
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Rickmer Braren
- Department of Diagnostic and Interventional Radiology, School of Medicine, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany
| | - Nassir Navab
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany
| | - Thomas Wendler
- Computer Aided Medical Procedures and Augmented Reality, School of Computation, Information and Technology, Technical University of Munich, Boltzmannstr. 3, 85748, Garching, Germany
- Department of Diagnostic and Interventional Radiology and Neuroradiology, Clinical Computational Medical Imaging Research, University Hospital Augsburg, Stenglinstr. 2, 86156, Augsburg, Germany
| |
Collapse
|
21
|
Costea M, Zlate A, Serre AA, Racadot S, Baudier T, Chabaud S, Grégoire V, Sarrut D, Biston MC. Evaluation of different algorithms for automatic segmentation of head-and-neck lymph nodes on CT images. Radiother Oncol 2023; 188:109870. [PMID: 37634765 DOI: 10.1016/j.radonc.2023.109870] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Revised: 07/27/2023] [Accepted: 08/20/2023] [Indexed: 08/29/2023]
Abstract
PURPOSE To investigate the performance of 4 atlas-based (multi-ABAS) and 2 deep learning (DL) solutions for head-and-neck (HN) elective nodes (CTVn) automatic segmentation (AS) on CT images. MATERIAL AND METHODS Bilateral CTVn levels of 69 HN cancer patients were delineated on contrast-enhanced planning CT. Ten and 49 patients were used for atlas library and for training a mono-centric DL model, respectively. The remaining 20 patients were used for testing. Additionally, three commercial multi-ABAS methods and one commercial multi-centric DL solution were investigated. Quantitative evaluation was assessed using volumetric Dice Similarity Coefficient (DSC) and 95-percentile Hausdorff distance (HD95%). Blind evaluation was performed for 3 solutions by 4 physicians. One recorded the time needed for manual corrections. A dosimetric study was finally conducted using automated planning. RESULTS Overall DL solutions had better DSC and HD95% results than multi-ABAS methods. No statistically significant difference was found between the 2 DL solutions. However, the contours provided by multi-centric DL solution were preferred by all physicians and were also faster to correct (1.1 min vs 4.17 min, on average). Manual corrections for multi-ABAS contours took on average 6.52 min Overall, decreased contour accuracy was observed from CTVn2 to CTVn3 and to CTVn4. Using the AS contours in treatment planning resulted in underdosage of the elective target volume. CONCLUSION Among all methods, the multi-centric DL method showed the highest delineation accuracy and was better rated by experts. Manual corrections remain necessary to avoid elective target underdosage. Finally, AS contours help reducing the workload of manual delineation task.
Collapse
Affiliation(s)
- Madalina Costea
- Centre Léon Bérard, 28 rue Laennec, LYON 69373 Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France
| | | | | | | | - Thomas Baudier
- Centre Léon Bérard, 28 rue Laennec, LYON 69373 Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France
| | - Sylvie Chabaud
- Unité de Biostatistique et d'Evaluation des Thérapeutiques, Centre Léon Bérard, Lyon 69373, France
| | | | - David Sarrut
- Centre Léon Bérard, 28 rue Laennec, LYON 69373 Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France
| | - Marie-Claude Biston
- Centre Léon Bérard, 28 rue Laennec, LYON 69373 Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France.
| |
Collapse
|
22
|
Maduro Bustos LA, Sarkar A, Doyle LA, Andreou K, Noonan J, Nurbagandova D, Shah SA, Irabor OC, Mourtada F. Feasibility evaluation of novel AI-based deep-learning contouring algorithm for radiotherapy. J Appl Clin Med Phys 2023; 24:e14090. [PMID: 37464581 PMCID: PMC10647981 DOI: 10.1002/acm2.14090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2023] [Revised: 06/09/2023] [Accepted: 06/13/2023] [Indexed: 07/20/2023] Open
Abstract
PURPOSE To evaluate the clinical feasibility of the Siemens Healthineers AI-Rad Companion Organs RT VA30A (Organs-RT) auto-contouring algorithm for organs at risk (OARs) of the pelvis, thorax, and head and neck (H&N). METHODS Computed tomography (CT) datasets from 30 patients (10 pelvis, 10 thorax, and 10 H&N) were collected. Four sets of OARs were generated on each scan, one set by Organs-RT and the others by three experienced users independently. A physician (expert) then evaluated each contour by assigning a score from the following scale: 1-Must Redo, 2-Major Edits, 3-Minor Edits, 4-Clinically usable. Using the highest-scored OAR from the human users as a reference, the contours generated by Organs-RT were evaluated via Dice Similarity Coefficient (DSC), Hausdorff Distance (HDD), Mean Distance to Agreement (mDTA), Volume comparison, and visual inspection. Additionally, each human user recorded the time to delineate each structure set and time-saving efficiency was measured. RESULTS The average DSC obtained for the pelvic OARs ranged between (0.81 ± 0.06)Rectum and (0.94 ± 0.03)Bladder . (0.75 ± 0.09)Esophagus to( 0.96 ± 0.02 ) Rt . Lung ${( {0.96 \pm 0.02} )}_{{\mathrm{Rt}}.{\mathrm{\ Lung}}}$ for the thoracic OARs and (0.66 ± 0.07)Lips to (0.83 ± 0.04)Brainstem for the H&N. The average HDD in cm for the pelvis cohort ranged between (0.95 ± 0.35)Bladder to (3.62 ± 2.50)Rectum , (0.42 ± 0.06)SpinalCord to (2.09 ± 2.00)Esophagus for the thoracic set and( 0.53 ± 0.22 ) Cerv _ SpinalCord ${( {0.53 \pm 0.22} )}_{{\mathrm{Cerv}}\_{\mathrm{SpinalCord}}}$ to (1.50 ± 0.50)Mandible for the H&N region. The time-saving efficiency was 67% for H&N, 83% for pelvis, and 84% for thorax. 72.5%, 82%, and 50% of the pelvis, thorax, and H&N OARs were scored as clinically usable by the expert, respectively. CONCLUSIONS The highest agreement registered between OARs generated by Organs-RT and their respective references was for the bladder, heart, lungs, and femoral heads, with an overall DSC≥0.92. The poorest agreement was for the rectum, esophagus, and lips, with an overall DSC⩽0.81. Nonetheless, Organs-RT serves as a reliable auto-contouring tool by minimizing overall contouring time and increasing time-saving efficiency in radiotherapy treatment planning.
Collapse
Affiliation(s)
- Luis A. Maduro Bustos
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
- Department of Radiation OncologyThomas Jefferson University HospitalPhiladelphiaPennsylvaniaUSA
| | - Abhirup Sarkar
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
| | - Laura A. Doyle
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
- Department of Radiation OncologyThomas Jefferson University HospitalPhiladelphiaPennsylvaniaUSA
| | - Kelly Andreou
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
| | - Jodie Noonan
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
| | - Diana Nurbagandova
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
| | - SunJay A. Shah
- Department of Radiation OncologyChristiana Care Helen F. Graham Cancer CenterNewarkDelawareUSA
| | - Omoruyi Credit Irabor
- Department of Radiation OncologyThomas Jefferson University HospitalPhiladelphiaPennsylvaniaUSA
| | - Firas Mourtada
- Department of Radiation OncologyThomas Jefferson University HospitalPhiladelphiaPennsylvaniaUSA
| |
Collapse
|
23
|
Geng J, Zhu X, Liu Z, Chen Q, Bai L, Wang S, Li Y, Wu H, Yue H, Du Y. Towards deep-learning (DL) based fully automated target delineation for rectal cancer neoadjuvant radiotherapy using a divide-and-conquer strategy: a study with multicenter blind and randomized validation. Radiat Oncol 2023; 18:164. [PMID: 37803462 PMCID: PMC10557242 DOI: 10.1186/s13014-023-02350-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Accepted: 09/13/2023] [Indexed: 10/08/2023] Open
Abstract
PURPOSE Manual clinical target volume (CTV) and gross tumor volume (GTV) delineation for rectal cancer neoadjuvant radiotherapy is pivotal but labor-intensive. This study aims to propose a deep learning (DL)-based workflow towards fully automated clinical target volume (CTV) and gross tumor volume (GTV) delineation for rectal cancer neoadjuvant radiotherapy. MATERIALS & METHODS We retrospectively included 141 patients with Stage II-III mid-low rectal cancer and randomly grouped them into training (n = 121) and testing (n = 20) cohorts. We adopted a divide-and-conquer strategy to address CTV and GTV segmentation using two separate DL models with DpuUnet as backend-one model for CTV segmentation in the CT domain, and the other for GTV in the MRI domain. The workflow was validated using a three-level multicenter-involved blind and randomized evaluation scheme. Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) metrics were calculated in Level 1, four-grade expert scoring was performed in Level 2, and head-to-head Turing test in Level 3. RESULTS For the DL-based CTV contours over the testing cohort, the DSC and 95HD (mean ± SD) were 0.85 ± 0.06 and 7.75 ± 6.42 mm respectively, and 96.4% cases achieved clinical viable scores (≥ 2). The positive rate in the Turing test was 52.3%. For GTV, the DSC and 95HD were 0.87 ± 0.07 and 4.07 ± 1.67 mm respectively, and 100% of the DL-based contours achieved clinical viable scores (≥ 2). The positive rate in the Turing test was 52.0%. CONCLUSION The proposed DL-based workflow exhibited promising accuracy and excellent clinical viability towards automated CTV and GTV delineation for rectal cancer neoadjuvant radiotherapy.
Collapse
Affiliation(s)
- Jianhao Geng
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China
| | - Xianggao Zhu
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China
| | - Zhiyan Liu
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China
| | - Qi Chen
- Research and Development Department, MedMind Technology Co., Ltd, Beijing, 100083, China
| | - Lu Bai
- Research and Development Department, MedMind Technology Co., Ltd, Beijing, 100083, China
| | - Shaobin Wang
- Research and Development Department, MedMind Technology Co., Ltd, Beijing, 100083, China
| | - Yongheng Li
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China
| | - Hao Wu
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China
- Institute of Medical Technology, Peking University Health Science Center, Beijing, 100191, China
| | - Haizhen Yue
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China.
| | - Yi Du
- Key laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, 100142, China.
- Institute of Medical Technology, Peking University Health Science Center, Beijing, 100191, China.
| |
Collapse
|
24
|
Abdulkadir Y, Luximon D, Morris E, Chow P, Kishan AU, Mikaeilian A, Lamb JM. Human factors in the clinical implementation of deep learning-based automated contouring of pelvic organs at risk for MRI-guided radiotherapy. Med Phys 2023; 50:5969-5977. [PMID: 37646527 DOI: 10.1002/mp.16676] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Revised: 03/07/2023] [Accepted: 04/28/2023] [Indexed: 09/01/2023] Open
Abstract
PURPOSE Deep neural nets have revolutionized the science of auto-segmentation and present great promise for treatment planning automation. However, little data exists regarding clinical implementation and human factors. We evaluated the performance and clinical implementation of a novel deep learning-based auto-contouring workflow for 0.35T magnetic resonance imaging (MRI)-guided pelvic radiotherapy, focusing on automation bias and objective measures of workflow savings. METHODS An auto-contouring model was developed using a UNet-derived architecture for the femoral heads, bladder, and rectum in 0.35T MR images. Training data was taken from 75 patients treated with MRI-guided radiotherapy at our institution. The model was tested against 20 retrospective cases outside the training set, and subsequently was clinically implemented. Usability was evaluated on the first 30 clinical cases by computing Dice coefficient (DSC), Hausdorff distance (HD), and the fraction of slices that were used un-modified by planners. Final contours were retrospectively reviewed by an experienced planner and clinical significance of deviations was graded as negligible, low, moderate, and high probability of leading to actionable dosimetric variations. In order to assess whether the use of auto-contouring led to final contours more or less in agreement with an objective standard, 10 pre-treatment and 10 post-treatment blinded cases were re-contoured from scratch by three expert planners to get expert consensus contours (EC). EC was compared to clinically used (CU) contours using DSC. Student's t-test and Levene's statistic were used to test statistical significance of differences in mean and standard deviation, respectively. Finally, the dosimetric significance of the contour differences were assessed by comparing the difference in bladder and rectum maximum point doses between EC and CU before and after the introduction of automation. RESULTS Median (interquartile range) DSC for the retrospective test data were 0.92(0.02), 0.92(0.06), 0.93(0.06), 0.87(0.04) for the post-processed contours for the right and left femoral heads, bladder, and rectum, respectively. Post-implementation median DSC were 1.0(0.0), 1.0(0.0), 0.98(0.04), and 0.98(0.06), respectively. For each organ, 96.2, 95.4, 59.5, and 68.21 percent of slices were used unmodified by the planner. DSC between EC and pre-implementation CU contours were 0.91(0.05*), 0.91*(0.05*), 0.95(0.04), and 0.88(0.04) for right and left femoral heads, bladder, and rectum, respectively. The corresponding DSC for post-implementation CU contours were 0.93(0.02*), 0.93*(0.01*), 0.96(0.01), and 0.85(0.02) (asterisks indicate statistically significant difference). In a retrospective review of contours used for planning, a total of four deviating slices in two patients were graded as low potential clinical significance. No deviations were graded as moderate or high. Mean differences between EC and CU rectum max-doses were 0.1 ± 2.6 Gy and -0.9 ± 2.5 Gy for pre- and post-implementation, respectively. Mean differences between EC and CU bladder/bladder wall max-doses were -0.9 ± 4.1 Gy and 0.0 ± 0.6 Gy for pre- and post-implementation, respectively. These differences were not statistically significant according to Student's t-test. CONCLUSION We have presented an analysis of the clinical implementation of a novel auto-contouring workflow. Substantial workflow savings were obtained. The introduction of auto-contouring into the clinical workflow changed the contouring behavior of planners. Automation bias was observed, but it had little deleterious effect on treatment planning.
Collapse
Affiliation(s)
- Yasin Abdulkadir
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | - Dishane Luximon
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | - Eric Morris
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | - Phillip Chow
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | - Amar U Kishan
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | - Argin Mikaeilian
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | - James M Lamb
- Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| |
Collapse
|
25
|
Vaassen F, Zegers CML, Hofstede D, Wubbels M, Beurskens H, Verheesen L, Canters R, Looney P, Battye M, Gooding MJ, Compter I, Eekers DBP, van Elmpt W. Geometric and dosimetric analysis of CT- and MR-based automatic contouring for the EPTN contouring atlas in neuro-oncology. Phys Med 2023; 114:103156. [PMID: 37813050 DOI: 10.1016/j.ejmp.2023.103156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 09/21/2023] [Accepted: 09/26/2023] [Indexed: 10/11/2023] Open
Abstract
PURPOSE Atlas-based and deep-learning contouring (DLC) are methods for automatic segmentation of organs-at-risk (OARs). The European Particle Therapy Network (EPTN) published a consensus-based atlas for delineation of OARs in neuro-oncology. In this study, geometric and dosimetric evaluation of automatically-segmented neuro-oncological OARs was performed using CT- and MR-models following the EPTN-contouring atlas. METHODS Image and contouring data from 76 neuro-oncological patients were included. Two atlas-based models (CT-atlas and MR-atlas) and one DLC-model (MR-DLC) were created. Manual contours on registered CT-MR-images were used as ground-truth. Results were analyzed in terms of geometrical (volumetric Dice similarity coefficient (vDSC), surface DSC (sDSC), added path length (APL), and mean slice-wise Hausdorff distance (MSHD)) and dosimetrical accuracy. Distance-to-tumor analysis was performed to analyze to which extent the location of the OAR relative to planning target volume (PTV) has dosimetric impact, using Wilcoxon rank-sum tests. RESULTS CT-atlas outperformed MR-atlas for 22/26 OARs. MR-DLC outperformed MR-atlas for all OARs. Highest median (95 %CI) vDSC and sDSC were found for the brainstem in MR-DLC: 0.92 (0.88-0.95) and 0.84 (0.77-0.89) respectively, as well as lowest MSHD: 0.27 (0.22-0.39)cm. Median dose differences (ΔD) were within ± 1 Gy for 24/26(92 %) OARs for all three models. Distance-to-tumor showed a significant correlation for ΔDmax,0.03cc-parameters when splitting the data in ≤ 4 cm and > 4 cm OAR-distance (p < 0.001). CONCLUSION MR-based DLC and CT-based atlas-contouring enable high-quality segmentation. It was shown that a combination of both CT- and MR-autocontouring models results in the best quality.
Collapse
Affiliation(s)
- Femke Vaassen
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands.
| | - Catharina M L Zegers
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - David Hofstede
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - Mart Wubbels
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - Hilde Beurskens
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - Lindsey Verheesen
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - Richard Canters
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | | | | | | | - Inge Compter
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - Daniëlle B P Eekers
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| | - Wouter van Elmpt
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre(+), Maastricht, the Netherlands
| |
Collapse
|
26
|
Muya S, Ndumbalo J, Kutika Nyagabona S, Yusuf S, Rhee DJ, Mushi BP, Li B, Zhang L, Grover S, Feng M, Hsu IC, Mmbaga E, Van Loon K, Court L, Xu M. Feasibility and Clinical Acceptability of Automation-Assisted 3D Conformal Radiotherapy Planning for Patients With Cervical Cancer in a Resource-Constrained Setting. JCO Glob Oncol 2023; 9:e2300050. [PMID: 37725767 PMCID: PMC10581615 DOI: 10.1200/go.23.00050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2023] [Revised: 06/14/2023] [Accepted: 08/01/2023] [Indexed: 09/21/2023] Open
Abstract
PURPOSE The Ocean Road Cancer Institute (ORCI) in Tanzania began offering 3D conformal radiation therapy (3DCRT) in 2018. Steep learning curves, high patient volume, and a limited workforce resulted in long radiation therapy (RT) planning workflows. We aimed to establish the feasibility of implementing an automation-assisted cervical cancer 3DCRT planning system. MATERIALS AND METHODS We performed chart abstractions on 30 patients with cervical cancer treated with 3DCRT at ORCI. The Radiation Planning Assistant (RPA) generated a new automated set of contours and plans on the basis of anonymized computed tomography images. Each were assessed for edit time requirements, dose-volume safety metrics, and clinical acceptability by two ORCI physician investigators. Dice similarity coefficient (DSC) agreement analysis was conducted between original and new contour sets. RESULTS The average time to manually develop treatment plans was 7 days. Applying RPA, automated same-day contours and plans were developed for 29 of 30 patients (97%). Of the 29 evaluable contours, all were approved with <2 minutes of edit time. Agreement between clinical and RPA contours was highest for the rectum (median DSC, 0.72) and bladder (DSC, 0.90). Agreement was lower with the primary tumor clinical target volume (CTVp; DSC, 0.69) and elective nodal clinical target volume (CTVn; DSC, 0.63). All RPA plans were approved with <4 minutes of edit time. RPA target coverage was excellent, covering the CTVp with median V45 Gy 100% and CTVn with median V45 Gy 99.9%. CONCLUSION Automation-assisted 3DCRT contouring yielded high levels of agreement for normal structures. The RPA met all planning safety metrics and sustained high levels of clinical acceptability with minimal edit times. This tool offers the potential to significantly decrease RT planning timelines while maintaining high-quality RT delivery in resource-constrained settings.
Collapse
Affiliation(s)
- Sikudhani Muya
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
- Ocean Road Cancer Institute, Dar es Salaam, Tanzania
| | - Jerry Ndumbalo
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
- Ocean Road Cancer Institute, Dar es Salaam, Tanzania
| | | | - Shaid Yusuf
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
- Ocean Road Cancer Institute, Dar es Salaam, Tanzania
| | | | | | - Benjamin Li
- University of California, San Francisco, Helen Diller Family Comprehensive Cancer Center, San Francisco, CA
| | - Li Zhang
- University of California, San Francisco, Helen Diller Family Comprehensive Cancer Center, San Francisco, CA
| | | | - Mary Feng
- University of California, San Francisco, Helen Diller Family Comprehensive Cancer Center, San Francisco, CA
| | - I-Chow Hsu
- University of California, San Francisco, Helen Diller Family Comprehensive Cancer Center, San Francisco, CA
| | - Elia Mmbaga
- Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
- University of Oslo, Oslo, Norway
| | - Katherine Van Loon
- University of California, San Francisco, Helen Diller Family Comprehensive Cancer Center, San Francisco, CA
| | | | - Melody Xu
- University of California, San Francisco, Helen Diller Family Comprehensive Cancer Center, San Francisco, CA
- Kaiser Permanente Santa Clara, Santa Clara, CA
| |
Collapse
|
27
|
Doolan PJ, Charalambous S, Roussakis Y, Leczynski A, Peratikou M, Benjamin M, Ferentinos K, Strouthos I, Zamboglou C, Karagiannis E. A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy. Front Oncol 2023; 13:1213068. [PMID: 37601695 PMCID: PMC10436522 DOI: 10.3389/fonc.2023.1213068] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Accepted: 07/17/2023] [Indexed: 08/22/2023] Open
Abstract
Purpose/objectives Auto-segmentation with artificial intelligence (AI) offers an opportunity to reduce inter- and intra-observer variability in contouring, to improve the quality of contours, as well as to reduce the time taken to conduct this manual task. In this work we benchmark the AI auto-segmentation contours produced by five commercial vendors against a common dataset. Methods and materials The organ at risk (OAR) contours generated by five commercial AI auto-segmentation solutions (Mirada (Mir), MVision (MV), Radformation (Rad), RayStation (Ray) and TheraPanacea (Ther)) were compared to manually-drawn expert contours from 20 breast, 20 head and neck, 20 lung and 20 prostate patients. Comparisons were made using geometric similarity metrics including volumetric and surface Dice similarity coefficient (vDSC and sDSC), Hausdorff distance (HD) and Added Path Length (APL). To assess the time saved, the time taken to manually draw the expert contours, as well as the time to correct the AI contours, were recorded. Results There are differences in the number of CT contours offered by each AI auto-segmentation solution at the time of the study (Mir 99; MV 143; Rad 83; Ray 67; Ther 86), with all offering contours of some lymph node levels as well as OARs. Averaged across all structures, the median vDSCs were good for all systems and compared favorably with existing literature: Mir 0.82; MV 0.88; Rad 0.86; Ray 0.87; Ther 0.88. All systems offer substantial time savings, ranging between: breast 14-20 mins; head and neck 74-93 mins; lung 20-26 mins; prostate 35-42 mins. The time saved, averaged across all structures, was similar for all systems: Mir 39.8 mins; MV 43.6 mins; Rad 36.6 min; Ray 43.2 mins; Ther 45.2 mins. Conclusions All five commercial AI auto-segmentation solutions evaluated in this work offer high quality contours in significantly reduced time compared to manual contouring, and could be used to render the radiotherapy workflow more efficient and standardized.
Collapse
Affiliation(s)
- Paul J. Doolan
- Department of Medical Physics, German Oncology Center, Limassol, Cyprus
| | | | - Yiannis Roussakis
- Department of Medical Physics, German Oncology Center, Limassol, Cyprus
| | - Agnes Leczynski
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
| | - Mary Peratikou
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
| | - Melka Benjamin
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
| | - Konstantinos Ferentinos
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
- School of Medicine, European University Cyprus, Nicosia, Cyprus
| | - Iosif Strouthos
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
- School of Medicine, European University Cyprus, Nicosia, Cyprus
| | - Constantinos Zamboglou
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
- School of Medicine, European University Cyprus, Nicosia, Cyprus
- Department of Radiation Oncology, Medical Center – University of Freiberg, Freiberg, Germany
| | - Efstratios Karagiannis
- Department of Radiation Oncology, German Oncology Center, Limassol, Cyprus
- School of Medicine, European University Cyprus, Nicosia, Cyprus
| |
Collapse
|
28
|
Zhang F, Wang Q, Lu N, Chen D, Jiang H, Yang A, Yu Y, Wang Y. Applying a novel two-step deep learning network to improve the automatic delineation of esophagus in non-small cell lung cancer radiotherapy. Front Oncol 2023; 13:1174530. [PMID: 37534258 PMCID: PMC10391539 DOI: 10.3389/fonc.2023.1174530] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2023] [Accepted: 05/22/2023] [Indexed: 08/04/2023] Open
Abstract
Purpose To introduce a model for automatic segmentation of thoracic organs at risk (OARs), especially the esophagus, in non-small cell lung cancer radiotherapy, using a novel two-step deep learning network. Materials and methods A total of 59 lung cancer patients' CT images were enrolled, of which 39 patients were randomly selected as the training set, 8 patients as the validation set, and 12 patients as the testing set. The automatic segmentations of the six OARs including the esophagus were carried out. In addition, two sets of treatment plans were made on the basis of the manually delineated tumor and OARs (Plan1) as well as the manually delineated tumor and the automatically delineated OARs (Plan2). The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) of the proposed model were compared with those of U-Net as a benchmark. Next, two groups of plans were also compared according to the dose-volume histogram parameters. Results The DSC, HD95, and ASD of the proposed model were better than those of U-Net, while the two groups of plans were almost the same. The highest mean DSC of the proposed method was 0.94 for the left lung, and the lowest HD95 and ASD were 3.78 and 1.16 mm for the trachea, respectively. Moreover, the DSC reached 0.73 for the esophagus. Conclusions The two-step segmentation method can accurately segment the OARs of lung cancer. The mean DSC of the esophagus realized preliminary clinical significance (>0.70). Choosing different deep learning networks based on different characteristics of organs offers a new option for automatic segmentation in radiotherapy.
Collapse
Affiliation(s)
- Fuli Zhang
- Radiation Oncology Department, The Seventh Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Qiusheng Wang
- School of Automation Science and Electrical Engineering, Beihang University, Beijing, China
| | - Na Lu
- Radiation Oncology Department, The Seventh Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Diandian Chen
- Radiation Oncology Department, The Seventh Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Huayong Jiang
- Radiation Oncology Department, The Seventh Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Anning Yang
- School of Automation Science and Electrical Engineering, Beihang University, Beijing, China
| | - Yanjun Yu
- Radiation Oncology Department, The Seventh Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Yadi Wang
- Radiation Oncology Department, The Seventh Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| |
Collapse
|
29
|
Duan J, Bernard ME, Castle JR, Feng X, Wang C, Kenamond MC, Chen Q. Contouring quality assurance methodology based on multiple geometric features against deep learning auto-segmentation. Med Phys 2023; 50:2715-2732. [PMID: 36788735 PMCID: PMC10175153 DOI: 10.1002/mp.16299] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Revised: 01/06/2023] [Accepted: 01/26/2023] [Indexed: 02/16/2023] Open
Abstract
BACKGROUND Contouring error is one of the top failure modes in radiation treatment. Multiple efforts have been made to develop tools to automatically detect segmentation errors. Deep learning-based auto-segmentation (DLAS) has been used as a baseline for flagging manual segmentation errors, but those efforts are limited to using only one or two contour comparison metrics. PURPOSE The purpose of this research is to develop an improved contouring quality assurance system to identify and flag manual contouring errors. METHODS AND MATERIALS DLAS contours were used as a reference to compare with manually segmented contours. A total of 27 geometric agreement metrics were determined from the comparisons between the two segmentation approaches. Feature selection was performed to optimize the training of a machine learning classification model to identify potential contouring errors. A public dataset with 339 cases was used to train and test the classifier. Four independent classifiers were trained using five-fold cross validation, and the predictions from each classifier were ensembled using soft voting. The trained model was validated on a held-out testing dataset. An additional independent clinical dataset with 60 cases was used to test the generalizability of the model. Model predictions were reviewed by an expert to confirm or reject the findings. RESULTS The proposed machine learning multiple features (ML-MF) approach outperformed traditional nonmachine-learning-based approaches that are based on only one or two geometric agreement metrics. The machine learning model achieved recall (precision) values of 0.842 (0.899), 0.762 (0.762), 0.727 (0.842), and 0.773 (0.773) for Brainstem, Parotid_L, Parotid_R, and mandible contours, respectively compared to 0.526 (0.909), 0.619 (0.765), 0.682 (0.882), 0.773 (0.568) for an approach based solely on Dice similarity coefficient values. In the external validation dataset, 66.7, 93.3, 94.1, and 58.8% of flagged cases were confirmed to have contouring errors by an expert for Brainstem, Parotid_L, Parotid_R, and mandible contours, respectively. CONCLUSIONS The proposed ML-MF approach, which includes multiple geometric agreement metrics to flag manual contouring errors, demonstrated superior performance in comparison to traditional methods. This method is easy to implement in clinical practice and can help to reduce the significant time and labor costs associated with manual segmentation and review.
Collapse
Affiliation(s)
- Jingwei Duan
- Department of Radiation Medicine, University of Kentucky, Lexington, KY 40506
| | - Mark E. Bernard
- Department of Radiation Medicine, University of Kentucky, Lexington, KY 40506
| | - James R. Castle
- Carina Medical LLC, 145 Graham Ave, A168, Lexington, KY 40506
| | - Xue Feng
- Carina Medical LLC, 145 Graham Ave, A168, Lexington, KY 40506
| | - Chi Wang
- Department of Internal Medicine, University of Kentucky, Lexington, KY 40506
| | - Mark C. Kenamond
- Department of Radiation Medicine, University of Kentucky, Lexington, KY 40506
| | - Quan Chen
- Department of Radiation Medicine, University of Kentucky, Lexington, KY 40506
| |
Collapse
|
30
|
Luu MH, Mai HS, Pham XL, Le QA, Le QK, Walsum TV, Le NH, Franklin D, Le VH, Moelker A, Chu DT, Trung NL. Quantification of liver-Lung shunt fraction on 3D SPECT/CT images for selective internal radiation therapy of liver cancer using CNN-based segmentations and non-rigid registration. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 233:107453. [PMID: 36921463 DOI: 10.1016/j.cmpb.2023.107453] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/13/2022] [Revised: 01/25/2023] [Accepted: 02/27/2023] [Indexed: 06/18/2023]
Abstract
PURPOSE Selective internal radiation therapy (SIRT) has been proven to be an effective treatment for hepatocellular carcinoma (HCC) patients. In clinical practice, the treatment planning for SIRT using 90Y microspheres requires estimation of the liver-lung shunt fraction (LSF) to avoid radiation pneumonitis. Currently, the manual segmentation method to draw a region of interest (ROI) of the liver and lung in 2D planar imaging of 99mTc-MAA and 3D SPECT/CT images is inconvenient, time-consuming and observer-dependent. In this study, we propose and evaluate a nearly automatic method for LSF quantification using 3D SPECT/CT images, offering improved performance compared with the current manual segmentation method. METHODS We retrospectively acquired 3D SPECT with non-contrast-enhanced CT images (nCECT) of 60 HCC patients from a SPECT/CT scanning machine, along with the corresponding diagnostic contrast-enhanced CT images (CECT). Our approach for LSF quantification is to use CNN-based methods for liver and lung segmentations in the nCECT image. We first apply 3D ResUnet to coarsely segment the liver. If the liver segmentation contains a large error, we dilate the coarse liver segmentation into the liver mask as a ROI in the nCECT image. Subsequently, non-rigid registration is applied to deform the liver in the CECT image to fit that obtained in the nCECT image. The final liver segmentation is obtained by segmenting the liver in the deformed CECT image using nnU-Net. In addition, the lung segmentations are obtained using 2D ResUnet. Finally, LSF quantitation is performed based on the number of counts in the SPECT image inside the segmentations. Evaluations and Results: To evaluate the liver segmentation accuracy, we used Dice similarity coefficient (DSC), asymmetric surface distance (ASSD), and max surface distance (MSD) and compared the proposed method to five well-known CNN-based methods for liver segmentation. Furthermore, the LSF error obtained by the proposed method was compared to a state-of-the-art method, modified Deepmedic, and the LSF quantifications obtained by manual segmentation. The results show that the proposed method achieved a DSC score for the liver segmentation that is comparable to other state-of-the-art methods, with an average of 0.93, and the highest consistency in segmentation accuracy, yielding a standard deviation of the DSC score of 0.01. The proposed method also obtains the lowest ASSD and MSD scores on average (2.6 mm and 31.5 mm, respectively). Moreover, for the proposed method, a median LSF error of 0.14% is obtained, which is a statically significant improvement to the state-of-the-art-method (p=0.004), and is much smaller than the median error in LSF manual determination by the medical experts using 2D planar image (1.74% and p<0.001). CONCLUSIONS A method for LSF quantification using 3D SPECT/CT images based on CNNs and non-rigid registration was proposed, evaluated and compared to state-of-the-art techniques. The proposed method can quantitatively determine the LSF with high accuracy and has the potential to be applied in clinical practice.
Collapse
Affiliation(s)
- Manh Ha Luu
- AVITECH, VNU University of Engineering and Technology, Hanoi, Vietnam; FET, VNU University of Engineering and Technology, Hanoi, Vietnam; Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands.
| | - Hong Son Mai
- Department of Nuclear Medicine, Hospital 108, Hanoi, Vietnam
| | - Xuan Loc Pham
- FET, VNU University of Engineering and Technology, Hanoi, Vietnam
| | - Quoc Anh Le
- AVITECH, VNU University of Engineering and Technology, Hanoi, Vietnam
| | - Quoc Khanh Le
- Department of Nuclear Medicine, Hospital 108, Hanoi, Vietnam
| | - Theo van Walsum
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands
| | - Ngoc Ha Le
- Department of Nuclear Medicine, Hospital 108, Hanoi, Vietnam
| | - Daniel Franklin
- School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia
| | - Vu Ha Le
- AVITECH, VNU University of Engineering and Technology, Hanoi, Vietnam; FET, VNU University of Engineering and Technology, Hanoi, Vietnam
| | - Adriaan Moelker
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands
| | - Duc Trinh Chu
- FET, VNU University of Engineering and Technology, Hanoi, Vietnam
| | - Nguyen Linh Trung
- AVITECH, VNU University of Engineering and Technology, Hanoi, Vietnam
| |
Collapse
|
31
|
Meric I, Alagoz E, Hysing LB, Kögler T, Lathouwers D, Lionheart WRB, Mattingly J, Obhodas J, Pausch G, Pettersen HES, Ratliff HN, Rovituso M, Schellhammer SM, Setterdahl LM, Skjerdal K, Sterpin E, Sudac D, Turko JA, Ytre-Hauge KS. A hybrid multi-particle approach to range assessment-based treatment verification in particle therapy. Sci Rep 2023; 13:6709. [PMID: 37185591 PMCID: PMC10130067 DOI: 10.1038/s41598-023-33777-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Accepted: 04/18/2023] [Indexed: 05/17/2023] Open
Abstract
Particle therapy (PT) used for cancer treatment can spare healthy tissue and reduce treatment toxicity. However, full exploitation of the dosimetric advantages of PT is not yet possible due to range uncertainties, warranting development of range-monitoring techniques. This study proposes a novel range-monitoring technique introducing the yet unexplored concept of simultaneous detection and imaging of fast neutrons and prompt-gamma rays produced in beam-tissue interactions. A quasi-monolithic organic detector array is proposed, and its feasibility for detecting range shifts in the context of proton therapy is explored through Monte Carlo simulations of realistic patient models and detector resolution effects. The results indicate that range shifts of [Formula: see text] can be detected at relatively low proton intensities ([Formula: see text] protons/spot) when spatial information obtained through imaging of both particle species are used simultaneously. This study lays the foundation for multi-particle detection and imaging systems in the context of range verification in PT.
Collapse
Affiliation(s)
- Ilker Meric
- Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, P.O. Box 7030, 5020, Bergen, Norway.
| | - Enver Alagoz
- Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, P.O. Box 7030, 5020, Bergen, Norway
| | - Liv B Hysing
- Department of Oncology and Medical Physics, Haukeland University Hospital, Bergen, Norway
- Department of Physics and Technology, University of Bergen, P.O. Box 7803, 5020, Bergen, Norway
| | - Toni Kögler
- OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany.
- Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology-OncoRay, Dresden, Germany.
| | | | | | - John Mattingly
- Department of Nuclear Engineering, North Carolina State University, Raleigh, NC, USA
| | | | - Guntram Pausch
- Target Systemelektronik GmbH & Co. KG, Wuppertal, Germany
| | - Helge E S Pettersen
- Department of Oncology and Medical Physics, Haukeland University Hospital, Bergen, Norway
| | - Hunter N Ratliff
- Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, P.O. Box 7030, 5020, Bergen, Norway
| | | | - Sonja M Schellhammer
- OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany
- Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology-OncoRay, Dresden, Germany
| | - Lena M Setterdahl
- Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, P.O. Box 7030, 5020, Bergen, Norway
| | - Kyrre Skjerdal
- Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, P.O. Box 7030, 5020, Bergen, Norway
| | - Edmond Sterpin
- Department of Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Leuven, Belgium
| | | | - Joseph A Turko
- OncoRay-National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany
- Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology-OncoRay, Dresden, Germany
| | - Kristian S Ytre-Hauge
- Department of Physics and Technology, University of Bergen, P.O. Box 7803, 5020, Bergen, Norway
| |
Collapse
|
32
|
Ramachandran P, Eswarlal T, Lehman M, Colbert Z. Assessment of Optimizers and their Performance in Autosegmenting Lung Tumors. J Med Phys 2023; 48:129-135. [PMID: 37576091 PMCID: PMC10419743 DOI: 10.4103/jmp.jmp_54_23] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 05/06/2023] [Accepted: 05/14/2023] [Indexed: 08/15/2023] Open
Abstract
Purpose Optimizers are widely utilized across various domains to enhance desired outcomes by either maximizing or minimizing objective functions. In the context of deep learning, they help to minimize the loss function and improve model's performance. This study aims to evaluate the accuracy of different optimizers employed for autosegmentation of non-small cell lung cancer (NSCLC) target volumes on thoracic computed tomography images utilized in oncology. Materials and Methods The study utilized 112 patients, comprising 92 patients from "The Cancer Imaging Archive" (TCIA) and 20 of our local clinical patients, to evaluate the efficacy of various optimizers. The gross tumor volume was selected as the foreground mask for training and testing the models. Of the 92 TCIA patients, 57 were used for training and validation, and the remaining 35 for testing using nnU-Net. The performance of the final model was further evaluated on the 20 local clinical patient datasets. Six different optimizers, namely AdaDelta, AdaGrad, Adam, NAdam, RMSprop, and stochastic gradient descent (SGD), were investigated. To assess the agreement between the predicted volume and the ground truth, several metrics including Dice similarity coefficient (DSC), Jaccard index, sensitivity, precision, Hausdorff distance (HD), 95th percentile Hausdorff distance (HD95), and average symmetric surface distance (ASSD) were utilized. Results The DSC values for AdaDelta, AdaGrad, Adam, NAdam, RMSprop, and SGD were 0.75, 0.84, 0.85, 0.84, 0.83, and 0.81, respectively, for the TCIA test data. However, when the model trained on TCIA datasets was applied to the clinical datasets, the DSC, HD, HD95, and ASSD metrics showed a statistically significant decrease in performance compared to the TCIA test datasets, indicating the presence of image and/or mask heterogeneity between the data sources. Conclusion The choice of optimizer in deep learning is a critical factor that can significantly impact the performance of autosegmentation models. However, it is worth noting that the behavior of optimizers may vary when applied to new clinical datasets, which can lead to changes in models' performance. Therefore, selecting the appropriate optimizer for a specific task is essential to ensure optimal performance and generalizability of the model to different datasets.
Collapse
Affiliation(s)
- Prabhakar Ramachandran
- Department of Radiation Oncology, Cancer Services, Princess Alexandra Hospital, Woolloongabba, Queensland, Australia
| | - Tamma Eswarlal
- Department of Engineering Mathematics, College of Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India
| | - Margot Lehman
- Department of Radiation Oncology, Cancer Services, Princess Alexandra Hospital, Woolloongabba, Queensland, Australia
| | - Zachery Colbert
- Department of Radiation Oncology, Cancer Services, Princess Alexandra Hospital, Woolloongabba, Queensland, Australia
| |
Collapse
|
33
|
Boukerroui D, Vasquez Osorio E, Brunenberg E, Gooding MJ. Analytic calculations and synthetic shapes for validation of quantitative contour comparison software. Phys Imaging Radiat Oncol 2023; 26:100436. [PMID: 37089904 PMCID: PMC10119950 DOI: 10.1016/j.phro.2023.100436] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Revised: 03/24/2023] [Accepted: 03/29/2023] [Indexed: 04/05/2023] Open
Abstract
A high level of variability in reported values was observed in a recent survey of contour similarity measures (CSMs) calculation tools. Such variations in the output measurements prevent meaningful comparison between studies. The purpose of this study was to develop a dataset with analytically calculated gold standard values to facilitate standardization and ensure accuracy of CSM implementations. The dataset was generated in the Digital Imaging and Communications in Medicine (DICOM) format. Both the dataset and the software used for its generation are made publicly available to encourage robust testing of CSM implementations for accuracy, improving consistency between different implementations.
Collapse
|
34
|
Multiround Transfer Learning and Modified Generative Adversarial Network for Lung Cancer Detection. INT J INTELL SYST 2023. [DOI: 10.1155/2023/6376275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
Abstract
Lung cancer has been the leading cause of cancer death for many decades. With the advent of artificial intelligence, various machine learning models have been proposed for lung cancer detection (LCD). Typically, challenges in building an accurate LCD model are the small-scale datasets, the poor generalizability to detect unseen data, and the selection of useful source domains and prioritization of multiple source domains for transfer learning. In this paper, a multiround transfer learning and modified generative adversarial network (MTL-MGAN) algorithm is proposed for LCD. The MTL transfers the knowledge between the prioritized source domains and target domain to get rid of exhaust search of datasets prioritization among multiple datasets, maximizing the transferability with a multiround transfer learning process, and avoiding negative transfer via customization of loss functions in the aspects of domain, instance, and feature. In regard to the MGAN, it not only generates additional training data but also creates intermediate domains to bridge the gap between the source domains and target domains. 10 benchmark datasets are chosen for the performance evaluation and analysis of the MTL-MGAN. The proposed algorithm has significantly improved the accuracy compared with related works. To examine the contributions of the individual components of the MTL-MGAN, ablation studies are conducted to confirm the effectiveness of the prioritization algorithm, the MTL, the negative transfer avoidance via loss functions, and the MGAN. The research implications are to confirm the feasibility of multiround transfer learning to enhance the optimal solution of the target model and to provide a generic approach to bridge the gap between the source domain and target domain using MGAN.
Collapse
|
35
|
Baroudi H, Brock KK, Cao W, Chen X, Chung C, Court LE, El Basha MD, Farhat M, Gay S, Gronberg MP, Gupta AC, Hernandez S, Huang K, Jaffray DA, Lim R, Marquez B, Nealon K, Netherton TJ, Nguyen CM, Reber B, Rhee DJ, Salazar RM, Shanker MD, Sjogreen C, Woodland M, Yang J, Yu C, Zhao Y. Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'? Diagnostics (Basel) 2023; 13:diagnostics13040667. [PMID: 36832155 PMCID: PMC9955359 DOI: 10.3390/diagnostics13040667] [Citation(s) in RCA: 19] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2022] [Revised: 01/21/2023] [Accepted: 01/30/2023] [Indexed: 02/12/2023] Open
Abstract
Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.
Collapse
Affiliation(s)
- Hana Baroudi
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Kristy K. Brock
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Department of Imaging Physics, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Wenhua Cao
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Xinru Chen
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Caroline Chung
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Laurence E. Court
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Correspondence:
| | - Mohammad D. El Basha
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Maguy Farhat
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Skylar Gay
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Mary P. Gronberg
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Aashish Chandra Gupta
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
- Department of Imaging Physics, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Soleil Hernandez
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Kai Huang
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - David A. Jaffray
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Department of Imaging Physics, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Rebecca Lim
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Barbara Marquez
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Kelly Nealon
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Tucker J. Netherton
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Callistus M. Nguyen
- Department of Imaging Physics, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Brandon Reber
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
- Department of Imaging Physics, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Dong Joo Rhee
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Ramon M. Salazar
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Mihir D. Shanker
- The University of Queensland, Saint Lucia 4072, Australia
- The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Carlos Sjogreen
- Department of Physics, University of Houston, Houston, TX 77004, USA
| | - McKell Woodland
- Department of Imaging Physics, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Department of Computer Science, Rice University, Houston, TX 77005, USA
| | - Jinzhong Yang
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Cenji Yu
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| | - Yao Zhao
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX 77030, USA
| |
Collapse
|
36
|
Osuala R, Kushibar K, Garrucho L, Linardos A, Szafranowska Z, Klein S, Glocker B, Diaz O, Lekadir K. Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging. Med Image Anal 2023; 84:102704. [PMID: 36473414 DOI: 10.1016/j.media.2022.102704] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2021] [Revised: 11/02/2022] [Accepted: 11/21/2022] [Indexed: 11/26/2022]
Abstract
Despite technological and medical advances, the detection, interpretation, and treatment of cancer based on imaging data continue to pose significant challenges. These include inter-observer variability, class imbalance, dataset shifts, inter- and intra-tumour heterogeneity, malignancy determination, and treatment effect uncertainty. Given the recent advancements in image synthesis, Generative Adversarial Networks (GANs), and adversarial training, we assess the potential of these technologies to address a number of key challenges of cancer imaging. We categorise these challenges into (a) data scarcity and imbalance, (b) data access and privacy, (c) data annotation and segmentation, (d) cancer detection and diagnosis, and (e) tumour profiling, treatment planning and monitoring. Based on our analysis of 164 publications that apply adversarial training techniques in the context of cancer imaging, we highlight multiple underexplored solutions with research potential. We further contribute the Synthesis Study Trustworthiness Test (SynTRUST), a meta-analysis framework for assessing the validation rigour of medical image synthesis studies. SynTRUST is based on 26 concrete measures of thoroughness, reproducibility, usefulness, scalability, and tenability. Based on SynTRUST, we analyse 16 of the most promising cancer imaging challenge solutions and observe a high validation rigour in general, but also several desirable improvements. With this work, we strive to bridge the gap between the needs of the clinical cancer imaging community and the current and prospective research on data synthesis and adversarial networks in the artificial intelligence community.
Collapse
Affiliation(s)
- Richard Osuala
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain.
| | - Kaisar Kushibar
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain
| | - Lidia Garrucho
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain
| | - Akis Linardos
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain
| | - Zuzanna Szafranowska
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain
| | - Stefan Klein
- Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands
| | - Ben Glocker
- Biomedical Image Analysis Group, Department of Computing, Imperial College London, UK
| | - Oliver Diaz
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain
| | - Karim Lekadir
- Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Spain
| |
Collapse
|
37
|
Kanwar A, Merz B, Claunch C, Rana S, Hung A, Thompson RF. Stress-testing pelvic autosegmentation algorithms using anatomical edge cases. Phys Imaging Radiat Oncol 2023; 25:100413. [PMID: 36793398 PMCID: PMC9922913 DOI: 10.1016/j.phro.2023.100413] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 01/11/2023] [Accepted: 01/12/2023] [Indexed: 01/17/2023] Open
Abstract
Commercial autosegmentation has entered clinical use, however real-world performance may suffer in certain cases. We aimed to assess the influence of anatomic variants on performance. We identified 112 prostate cancer patients with anatomic variations (edge cases). Pelvic anatomy was autosegmented using three commercial tools. To evaluate performance, Dice similarity coefficients, and mean surface and 95% Hausdorff distances were calculated versus clinician-delineated references. Deep learning autosegmentation outperformed atlas-based and model-based methods. However, edge case performance was lower versus the normal cohort (0.12 mean DSC reduction). Anatomic variation presents challenges to commercial autosegmentation.
Collapse
Affiliation(s)
- Aasheesh Kanwar
- Department of Radiation Medicine, Oregon Health and Sciences University, Portland, OR, United States
| | - Brandon Merz
- Department of Radiation Medicine, Oregon Health and Sciences University, Portland, OR, United States
| | - Cheryl Claunch
- Department of Radiation Oncology, Baylor College of Medicine, Houston, TX, United States
| | - Shushan Rana
- PeaceHealth Medical Group – PeaceHealth Southwest Radiation Oncology, Vancouver, Washington, United States
| | - Arthur Hung
- Department of Radiation Medicine, Oregon Health and Sciences University, Portland, OR, United States
| | - Reid F. Thompson
- Department of Radiation Medicine, Oregon Health and Sciences University, Portland, OR, United States
- Division of Hospital and Specialty Medicine, VA Portland Healthcare System, Portland, OR, United States
| |
Collapse
|
38
|
Zhao L, Jia C, Ma J, Shao Y, Liu Z, Yuan H. Medical image segmentation based on self-supervised hybrid fusion network. Front Oncol 2023; 13:1109786. [PMID: 37124508 PMCID: PMC10141651 DOI: 10.3389/fonc.2023.1109786] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Accepted: 03/28/2023] [Indexed: 05/02/2023] Open
Abstract
Automatic segmentation of medical images has been a hot research topic in the field of deep learning in recent years, and achieving accurate segmentation of medical images is conducive to breakthroughs in disease diagnosis, monitoring, and treatment. In medicine, MRI imaging technology is often used to image brain tumors, and further judgment of the tumor area needs to be combined with expert analysis. If the diagnosis can be carried out by computer-aided methods, the efficiency and accuracy will be effectively improved. Therefore, this paper completes the task of brain tumor segmentation by building a self-supervised deep learning network. Specifically, it designs a multi-modal encoder-decoder network based on the extension of the residual network. Aiming at the problem of multi-modal feature extraction, the network introduces a multi-modal hybrid fusion module to fully extract the unique features of each modality and reduce the complexity of the whole framework. In addition, to better learn multi-modal complementary features and improve the robustness of the model, a pretext task to complete the masked area is set, to realize the self-supervised learning of the network. Thus, it can effectively improve the encoder's ability to extract multi-modal features and enhance the noise immunity. Experimental results present that our method is superior to the compared methods on the tested datasets.
Collapse
Affiliation(s)
- Liang Zhao
- School of Software Technology, Dalian University of Technology, Dalian, China
| | - Chaoran Jia
- School of Software Technology, Dalian University of Technology, Dalian, China
| | - Jiajun Ma
- School of Software Technology, Dalian University of Technology, Dalian, China
| | - Yu Shao
- School of Software Technology, Dalian University of Technology, Dalian, China
| | - Zhuo Liu
- The First Affiliated Hospital of Dalian Medical University, Dalian, China
- *Correspondence: Zhuo Liu, ; Hong Yuan,
| | - Hong Yuan
- The Affiliated Central Hospital, Dalian University of Technology, Dalian, China
- *Correspondence: Zhuo Liu, ; Hong Yuan,
| |
Collapse
|
39
|
Allioui H, Mourdi Y, Sadgal M. Strong semantic segmentation for Covid-19 detection: Evaluating the use of deep learning models as a performant tool in radiography. Radiography (Lond) 2023; 29:109-118. [PMID: 36335787 PMCID: PMC9595354 DOI: 10.1016/j.radi.2022.10.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2022] [Revised: 10/12/2022] [Accepted: 10/17/2022] [Indexed: 11/06/2022]
Abstract
INTRODUCTION With the increasing number of Covid-19 cases as well as care costs, chest diseases have gained increasing interest in several communities, particularly in medical and computer vision. Clinical and analytical exams are widely recognized techniques for diagnosing and handling Covid-19 cases. However, strong detection tools can help avoid damage to chest tissues. The proposed method provides an important way to enhance the semantic segmentation process using combined potential deep learning (DL) modules to increase consistency. Based on Covid-19 CT images, this work hypothesized that a novel model for semantic segmentation might be able to extract definite graphical features of Covid-19 and afford an accurate clinical diagnosis while optimizing the classical test and saving time. METHODS CT images were collected considering different cases (normal chest CT, pneumonia, typical viral causes, and Covid-19 cases). The study presents an advanced DL method to deal with chest semantic segmentation issues. The approach employs a modified version of the U-net to enable and support Covid-19 detection from the studied images. RESULTS The validation tests demonstrated competitive results with important performance rates: Precision (90.96% ± 2.5) with an F-score of (91.08% ± 3.2), an accuracy of (93.37% ± 1.2), a sensitivity of (96.88% ± 2.8) and a specificity of (96.91% ± 2.3). In addition, the visual segmentation results are very close to the Ground truth. CONCLUSION The findings of this study reveal the proof-of-principle for using cooperative components to strengthen the semantic segmentation modules for effective and truthful Covid-19 diagnosis. IMPLICATIONS FOR PRACTICE This paper has highlighted that DL based approach, with several modules, may be contributing to provide strong support for radiographers and physicians, and that further use of DL is required to design and implement performant automated vision systems to detect chest diseases.
Collapse
Affiliation(s)
- H Allioui
- Computer Sciences Department, Faculty of Sciences Semlalia, Cadi Ayyad University, Morocco.
| | - Y Mourdi
- Polydisciplinary Faculty Safi, Cadi Ayyad University, Morocco.
| | - M Sadgal
- Computer Sciences Department, Faculty of Sciences Semlalia, Cadi Ayyad University, Morocco.
| |
Collapse
|
40
|
Roper J, Lin M, Rong Y. Extensive upfront validation and testing are needed prior to the clinical implementation of AI-based auto-segmentation tools. J Appl Clin Med Phys 2022; 24:e13873. [PMID: 36545883 PMCID: PMC9859989 DOI: 10.1002/acm2.13873] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Revised: 11/30/2022] [Accepted: 12/01/2022] [Indexed: 12/24/2022] Open
Affiliation(s)
- Justin Roper
- Department of Radiation OncologyWinship Cancer Institute of Emory UniversityAtlantaGeorgiaUSA
| | - Mu‐Han Lin
- Department of Radiation OncologyUniversity of Texas Southwestern Medical CenterDallasTexasUSA
| | - Yi Rong
- Department of Radiation OncologyMayo Clinic HospitalsPhoenixArizonaUSA
| |
Collapse
|
41
|
Costea M, Zlate A, Durand M, Baudier T, Grégoire V, Sarrut D, Biston MC. Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system. Radiother Oncol 2022; 177:61-70. [PMID: 36328093 DOI: 10.1016/j.radonc.2022.10.029] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Revised: 10/21/2022] [Accepted: 10/23/2022] [Indexed: 11/06/2022]
Abstract
BACKGROUND AND PURPOSE To investigate the performance of head-and-neck (HN) organs-at-risk (OAR) automatic segmentation (AS) using four atlas-based (ABAS) and two deep learning (DL) solutions. MATERIAL AND METHODS All patients underwent iodine contrast-enhanced planning CT. Fourteen OAR were manually delineated. DL.1 and DL.2 solutions were trained with 63 mono-centric patients and > 1000 multi-centric patients, respectively. Ten and 15 patients with varied anatomies were selected for the atlas library and for testing, respectively. The evaluation was based on geometric indices (DICE coefficient and 95th percentile-Hausdorff Distance (HD95%)), time needed for manual corrections and clinical dosimetric endpoints obtained using automated treatment planning. RESULTS Both DICE and HD95% results indicated that DL algorithms generally performed better compared with ABAS algorithms for automatic segmentation of HN OAR. However, the hybrid-ABAS (ABAS.3) algorithm sometimes provided the highest agreement to the reference contours compared with the 2 DL. Compared with DL.2 and ABAS.3, DL.1 contours were the fastest to correct. For the 3 solutions, the differences in dose distributions obtained using AS contours and AS + manually corrected contours were not statistically significant. High dose differences could be observed when OAR contours were at short distances to the targets. However, this was not always interrelated. CONCLUSION DL methods generally showed higher delineation accuracy compared with ABAS methods for AS segmentation of HN OAR. Most ABAS contours had high conformity to the reference but were more time consuming than DL algorithms, especially when considering the computing time and the time spent on manual corrections.
Collapse
Affiliation(s)
- Madalina Costea
- Centre Léon Bérard, 28 rue Laennec, 69373 LYON Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France
| | | | - Morgane Durand
- Centre Léon Bérard, 28 rue Laennec, 69373 LYON Cedex 08, France
| | - Thomas Baudier
- Centre Léon Bérard, 28 rue Laennec, 69373 LYON Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France
| | | | - David Sarrut
- Centre Léon Bérard, 28 rue Laennec, 69373 LYON Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France
| | - Marie-Claude Biston
- Centre Léon Bérard, 28 rue Laennec, 69373 LYON Cedex 08, France; CREATIS, CNRS UMR5220, Inserm U1044, INSA-Lyon, Université Lyon 1, Villeurbanne, France.
| |
Collapse
|
42
|
Maleki F, Ovens K, Gupta R, Reinhold C, Spatz A, Forghani R. Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls. Radiol Artif Intell 2022; 5:e220028. [PMID: 36721408 PMCID: PMC9885377 DOI: 10.1148/ryai.220028] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2022] [Revised: 10/10/2022] [Accepted: 10/24/2022] [Indexed: 11/17/2022]
Abstract
Purpose To investigate the impact of the following three methodological pitfalls on model generalizability: (a) violation of the independence assumption, (b) model evaluation with an inappropriate performance indicator or baseline for comparison, and (c) batch effect. Materials and Methods The authors used retrospective CT, histopathologic analysis, and radiography datasets to develop machine learning models with and without the three methodological pitfalls to quantitatively illustrate their effect on model performance and generalizability. F1 score was used to measure performance, and differences in performance between models developed with and without errors were assessed using the Wilcoxon rank sum test when applicable. Results Violation of the independence assumption by applying oversampling, feature selection, and data augmentation before splitting data into training, validation, and test sets seemingly improved model F1 scores by 71.2% for predicting local recurrence and 5.0% for predicting 3-year overall survival in head and neck cancer and by 46.0% for distinguishing histopathologic patterns in lung cancer. Randomly distributing data points for a patient across datasets superficially improved the F1 score by 21.8%. High model performance metrics did not indicate high-quality lung segmentation. In the presence of a batch effect, a model built for pneumonia detection had an F1 score of 98.7% but correctly classified only 3.86% of samples from a new dataset of healthy patients. Conclusion Machine learning models developed with these methodological pitfalls, which are undetectable during internal evaluation, produce inaccurate predictions; thus, understanding and avoiding these pitfalls is necessary for developing generalizable models.Keywords: Random Forest, Diagnosis, Prognosis, Convolutional Neural Network (CNN), Medical Image Analysis, Generalizability, Machine Learning, Deep Learning, Model Evaluation Supplemental material is available for this article. Published under a CC BY 4.0 license.
Collapse
|
43
|
Draelos RL, Carin L. Explainable multiple abnormality classification of chest CT volumes. Artif Intell Med 2022; 132:102372. [DOI: 10.1016/j.artmed.2022.102372] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2021] [Revised: 06/09/2022] [Accepted: 07/28/2022] [Indexed: 12/20/2022]
|
44
|
Gooding MJ, Boukerroui D, Vasquez Osorio E, Monshouwer R, Brunenberg E. Multicenter comparison of measures for quantitative evaluation of contouring in radiotherapy. Phys Imaging Radiat Oncol 2022; 24:152-158. [PMID: 36424980 PMCID: PMC9679364 DOI: 10.1016/j.phro.2022.11.009] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Revised: 11/10/2022] [Accepted: 11/11/2022] [Indexed: 11/17/2022] Open
Abstract
Background and Purpose A wide range of quantitative measures are available to facilitate clinical implementation of auto-contouring software, on-going Quality Assurance (QA) and interobserver contouring variation studies. This study aimed to assess the variation in output when applying different implementations of the measures to the same data in order to investigate how consistently such measures are defined and implemented in radiation oncology. Materials and Methods A survey was conducted to assess if there were any differences in definitions of contouring measures or their implementations that would lead to variation in reported results between institutions. This took two forms: a set of computed tomography (CT) image data with "Test" and "Reference" contours was distributed for participants to process using their preferred tools and report results, and a questionnaire regarding the definition of measures and their implementation was completed by the participants. Results Thirteen participants completed the survey and submitted results, with one commercial and twelve in-house solutions represented. Excluding outliers, variations of up to 50% in Dice Similarity Coefficient (DSC), 50% in 3D Hausdorff Distance (HD), and 200% in Average Distance (AD) were observed between the participant submitted results. Collaborative investigation with participants revealed a large number of bugs in implementation, confounding the understanding of intentional implementation choices. Conclusion Care must be taken when comparing quantitative results between different studies. There is a need for a dataset with clearly defined measures and ground truth for validation of such tools prior to their use.
Collapse
Affiliation(s)
| | | | | | - René Monshouwer
- Radboud University Medical Centre, Nijmegen, the Netherlands
| | | |
Collapse
|
45
|
Gibbons E, Hoffmann M, Westhuyzen J, Hodgson A, Chick B, Last A. Clinical evaluation of deep learning and atlas-based auto-segmentation for critical organs at risk in radiation therapy. J Med Radiat Sci 2022; 70 Suppl 2:15-25. [PMID: 36148621 PMCID: PMC10122925 DOI: 10.1002/jmrs.618] [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: 03/17/2022] [Accepted: 08/27/2022] [Indexed: 11/12/2022] Open
Abstract
INTRODUCTION Contouring organs at risk (OARs) is a time-intensive task that is a critical part of radiation therapy. Atlas-based automatic segmentation has shown some success at reducing this time burden on practitioners; however, this method often requires significant manual editing to reach a clinically accurate standard. Deep learning (DL) auto-segmentation has recently emerged as a promising solution. This study compares the accuracy of DL and atlas-based auto-segmentation in relation to clinical 'gold standard' reference contours. METHODS Ninety CT datasets (30 head and neck, 30 thoracic, 30 pelvic) were automatically contoured using both atlas and DL segmentation techniques. Sixteen critical OARs were then quantitatively measured for accuracy using the Dice similarity coefficient (DSC) and Hausdorff distance (HD). Qualitative analysis was performed to visually classify the accuracy of each structure into one of four explicitly defined categories. Additionally, the time to edit atlas and DL contours to a clinically acceptable level was recorded for a subset of 9 OARs. RESULTS Of the 16 OARs analysed, DL delivered statistically significant improvements over atlas segmentation in 13 OARs measured with DSC, 12 OARs measured with HD, and 12 OARs measured qualitatively. The mean editing time for the subset of DL contours was 50%, 23% and 61% faster (all P < 0.05) than that of atlas segmentation for the head and neck, thorax, and pelvis respectively. CONCLUSIONS Deep learning segmentation comprehensively outperformed atlas-based contouring for the majority of evaluated OARs. Improvements were observed in geometric accuracy and visual acceptability, while editing time was reduced leading to increased workflow efficiency.
Collapse
Affiliation(s)
- Eddie Gibbons
- Department of Radiation Oncology, Mid North Coast Cancer Institute, Port Macquarie, New South Wales, Australia
| | - Matthew Hoffmann
- Department of Radiation Oncology, Mid North Coast Cancer Institute, Port Macquarie, New South Wales, Australia
| | - Justin Westhuyzen
- Department of Radiation Oncology, Mid North Coast Cancer Institute, Coffs Harbour, New South Wales, Australia
| | - Andrew Hodgson
- Department of Radiation Oncology, Mid North Coast Cancer Institute, Port Macquarie, New South Wales, Australia
| | - Brendan Chick
- Department of Radiation Oncology, Mid North Coast Cancer Institute, Port Macquarie, New South Wales, Australia
| | - Andrew Last
- Department of Radiation Oncology, Mid North Coast Cancer Institute, Port Macquarie, New South Wales, Australia
| |
Collapse
|
46
|
Shen J, Zhang F, Di M, Shen J, Wang S, Chen Q, Chen Y, Liu Z, Lian X, Ma J, Pang T, Dong T, Wang B, Guan Q, He L, Zhang Y, Liang H. Clinical target volume automatic segmentation based on lymph node stations for lung cancer with bulky lump lymph nodes. Thorac Cancer 2022; 13:2897-2903. [PMID: 36085253 PMCID: PMC9575127 DOI: 10.1111/1759-7714.14638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2022] [Revised: 08/18/2022] [Accepted: 08/21/2022] [Indexed: 11/30/2022] Open
Abstract
Background The lack of standardized delineation of lymph node station in lung cancer radiotherapy leads to nonstandard clinical target volume (CTV) contouring, especially in patients with bulky lump gross target volume lymph nodes (GTVnd). This study defines lymph node region boundaries in radiotherapy for lung cancer and automatically contours lymph node stations based on the International Association for the Study of Lung Cancer (IASLC) lymph node map. Methods Computed tomography (CT) scans of 200 patients with small cell lung cancer were collected. The lymph node zone boundaries were defined based on the IASLC lymph node map, with adjustments to meet radiotherapy requirements. Contours of lymph node stations were confirmed by two experienced oncologists. A model (DiUNet) was constructed by incorporating the contours of GTVnd to precisely contour the boundaries. Quantitative evaluation metrics and clinical evaluations were conducted. Results The mean 3D Dice similarity coefficient (Dice similarity coefficient) values of DiUNet in most lymph node stations was greater than 0.7, 98.87% of the lymph node station slices are accepted. The mean DiUNet score was not significantly different from that of the man contoured in the evaluation of lymph node stations and CTV. Conclusion This is the first study to propose a method that automatically contours lymph node regions station by station based on the IASLC lymph node map with bulky lump GTVnd. Delineation of lymph node stations based on the DiUNet model is a promising strategy to obtain accuracy and efficiency for CTV delineation in lung cancer patients, especially for bulky lump GTVnd.
Collapse
Affiliation(s)
- Jie Shen
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Fuquan Zhang
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Mingyi Di
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Jing Shen
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | | | - Qi Chen
- MedMind Technology Co, Ltd., Beijing, China
| | - Yu Chen
- MedMind Technology Co, Ltd., Beijing, China
| | - Zhikai Liu
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Xin Lian
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Jiabin Ma
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Tingtian Pang
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Tingting Dong
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Bei Wang
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Qiu Guan
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Lei He
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Yue Zhang
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| | - Hao Liang
- Department of Radiation Oncology, Peking Union Medical College, Beijing, China
| |
Collapse
|
47
|
|
48
|
Dourthe B, Shaikh N, Pai S A, Fels S, Brown SHM, Wilson DR, Street J, Oxland TR. Automated Segmentation of Spinal Muscles From Upright Open MRI Using a Multiscale Pyramid 2D Convolutional Neural Network. Spine (Phila Pa 1976) 2022; 47:1179-1186. [PMID: 34919072 DOI: 10.1097/brs.0000000000004308] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/25/2021] [Accepted: 11/29/2021] [Indexed: 02/01/2023]
Abstract
STUDY DESIGN Randomized trial. OBJECTIVE To implement an algorithm enabling the automated segmentation of spinal muscles from open magnetic resonance images in healthy volunteers and patients with adult spinal deformity (ASD). SUMMARY OF BACKGROUND DATA Understanding spinal muscle anatomy is critical to diagnosing and treating spinal deformity.Muscle boundaries can be extrapolated from medical images using segmentation, which is usually done manually by clinical experts and remains complicated and time-consuming. METHODS Three groups were examined: two healthy volunteer groups (N = 6 for each group) and one ASD group (N = 8 patients) were imaged at the lumbar and thoracic regions of the spine in an upright open magnetic resonance imaging scanner while maintaining different postures (various seated, standing, and supine). For each group and region, a selection of regions of interest (ROIs) was manually segmented. A multiscale pyramid two-dimensional convolutional neural network was implemented to automatically segment all defined ROIs. A five-fold crossvalidation method was applied and distinct models were trained for each resulting set and group and evaluated using Dice coefficients calculated between the model output and the manually segmented target. RESULTS Good to excellent results were found across all ROIs for the ASD (Dice coefficient >0.76) and healthy (dice coefficient > 0.86) groups. CONCLUSION This study represents a fundamental step toward the development of an automated spinal muscle properties extraction pipeline, which will ultimately allow clinicians to have easier access to patient-specific simulations, diagnosis, and treatment.
Collapse
Affiliation(s)
- Benjamin Dourthe
- ICORD, Blusson Spinal Cord Centre, University of British Columbia, Vancouver, BC, Canada
- Department of Orthopaedics, University of British Columbia, Vancouver, BC, Canada
| | - Noor Shaikh
- Department of Orthopaedics, University of British Columbia, Vancouver, BC, Canada
- School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada
- Depart-Department of Mechanical Engineering, University of British Columbia, Vancouver, BC, Canada
| | - Anoosha Pai S
- Department of Orthopaedics, University of British Columbia, Vancouver, BC, Canada
- School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada
| | - Sidney Fels
- Electrical and Computer Engineering Department, University of British Columbia, Vancouver, BC, Canada
| | - Stephen H M Brown
- Department of Human Health and Nutritional Sciences, University of Guelph, Guelph, ON, Canada
| | - David R Wilson
- ICORD, Blusson Spinal Cord Centre, University of British Columbia, Vancouver, BC, Canada
- Department of Orthopaedics, University of British Columbia, Vancouver, BC, Canada
- Centre for Hip Health and Mobility, University of British Columbia, Vancouver, BC, Canada
| | - John Street
- ICORD, Blusson Spinal Cord Centre, University of British Columbia, Vancouver, BC, Canada
- Department of Orthopaedics, University of British Columbia, Vancouver, BC, Canada
| | - Thomas R Oxland
- ICORD, Blusson Spinal Cord Centre, University of British Columbia, Vancouver, BC, Canada
- Department of Orthopaedics, University of British Columbia, Vancouver, BC, Canada
- Depart-Department of Mechanical Engineering, University of British Columbia, Vancouver, BC, Canada
| |
Collapse
|
49
|
Principi S, O’Connor S, Frank L, Schmidt TG. Reduced Chest Computed Tomography Scan Length for Patients Positive for Coronavirus Disease 2019: Dose Reduction and Impact on Diagnostic Utility. J Comput Assist Tomogr 2022; 46:576-583. [PMID: 35405727 PMCID: PMC9296570 DOI: 10.1097/rct.0000000000001312] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
METHODS This study used the Personalized Rapid Estimation of Dose in CT (PREDICT) tool to estimate patient-specific organ doses from CT image data. The PREDICT is a research tool that combines a linear Boltzmann transport equation solver for radiation dose map generation with deep learning algorithms for organ contouring. Computed tomography images from 74 subjects in the Medical Imaging Data Resource Center-RSNA International COVID-19 Open Radiology Database data set (chest CT of adult patients positive for COVID-19), which included expert annotations including "infectious opacities," were analyzed. First, the full z-scan length of the CT image data set was evaluated. Next, the z-scan length was reduced from the left hemidiaphragm to the top of the aortic arch. Generic dose reduction based on dose length product (DLP) and patient-specific organ dose reductions were calculated. The percentage of infectious opacities excluded from the reduced z-scan length was used to quantify the effect on diagnostic utility. RESULTS Generic dose reduction, based on DLP, was 69%. The organ dose reduction ranged from approximately equal to 18% (breasts) to approximately equal to 64% (bone surface and bone marrow). On average, 12.4% of the infectious opacities were not included in the reduced z-coverage, per patient, of which 5.1% were above the top of the arch and 7.5% below the left hemidiaphragm. CONCLUSIONS Limiting z-scan length of chest CTs reduced radiation dose without significantly compromising diagnostic utility in COVID-19 patients. The PREDICT demonstrated that patient-specific organ dose reductions varied from generic dose reduction based on DLP.
Collapse
Affiliation(s)
- Sara Principi
- Biomedical Engineering Department, Medical College of Wisconsin and Marquette University, 1637 W Wisconsin Ave, Milwaukee, WI 53233, USA
| | - Stacy O’Connor
- Radiology Department, Medical College of Wisconsin, 9200 W Wisconsin Avenue, Milwaukee, WI 53226, USA
| | - Luba Frank
- Radiology Department, Medical College of Wisconsin, 9200 W Wisconsin Avenue, Milwaukee, WI 53226, USA
| | - Taly Gilat Schmidt
- Biomedical Engineering Department, Medical College of Wisconsin and Marquette University, 1637 W Wisconsin Ave, Milwaukee, WI 53233, USA
| |
Collapse
|
50
|
Johnston N, De Rycke J, Lievens Y, van Eijkeren M, Aelterman J, Vandersmissen E, Ponte S, Vanderstraeten B. Dose-volume-based evaluation of convolutional neural network-based auto-segmentation of thoracic organs at risk. Phys Imaging Radiat Oncol 2022; 23:109-117. [PMID: 35936797 PMCID: PMC9352974 DOI: 10.1016/j.phro.2022.07.004] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2022] [Revised: 07/20/2022] [Accepted: 07/21/2022] [Indexed: 12/19/2022] Open
Abstract
Dice score and Hausdorff distance do not correlate with dose-volume-based results. Auto-contours close to the tumor or in entry/exit beams should be checked. Heart and esophagus must be checked for locally advanced non-small cell lung cancer. Bronchi must be checked for peripheral early-stage non-small cell lung cancer. Every treatment plan still passed the clinical goals for the manual organs at risk.
Background and purpose The geometrical accuracy of auto-segmentation using convolutional neural networks (CNNs) has been demonstrated. This study aimed to investigate the dose-volume impact of differences between automatic and manual OARs for locally advanced (LA) and peripherally located early-stage (ES) non-small cell lung cancer (NSCLC). Material and methods A single CNN was created for automatic delineation of the heart, lungs, main left and right bronchus, esophagus, spinal cord and trachea using 55/10/40 patients for training/validation/testing. Dice score coefficient (DSC) and 95th percentile Hausdorff distance (HD95) were used for geometrical analysis. A new treatment plan based on the auto-segmented OARs was created for each test patient using 3D for ES-NSCLC (SBRT, 3–8 fractions) and IMRT for LA-NSCLC (24–35 fractions). The correlation between geometrical metrics and dose-volume differences was investigated. Results The average (±1 SD) DSC and HD95 were 0.82 ± 0.07 and 16.2 ± 22.4 mm, while the average dose-volume differences were 0.5 ± 1.5 Gy (ES) and 1.5 ± 2.8 Gy (LA). The geometrical metrics did not correlate with the observed dose-volume differences (average Pearson for DSC: −0.27 ± 0.18 (ES) and −0.09 ± 0.12 (LA); HD95: 0.1 ± 0.3 mm (ES) and 0.2 ± 0.2 mm (LA)). Conclusions After post-processing, manual adjustments of automatic contours are only needed for clinically relevant OARs situated close to the tumor or within an entry or exit beam e.g., the heart and the esophagus for LA-NSCLC and the bronchi for ES-NSCLC. The lungs do not need to be checked further in detail.
Collapse
Affiliation(s)
- Noémie Johnston
- Centre Hospitalier Universitaire de Liège, Service de Radiothérapie, Liège, Belgium
| | - Jeffrey De Rycke
- Ghent University, Faculty of Medicine and Health Sciences, Department of Human Structure and Repair, Gent, Belgium
| | - Yolande Lievens
- Ghent University, Faculty of Medicine and Health Sciences, Department of Human Structure and Repair, Gent, Belgium
- Ghent University Hospital, Department of Radiotherapy-Oncology, Gent, Belgium
| | - Marc van Eijkeren
- Ghent University, Faculty of Medicine and Health Sciences, Department of Human Structure and Repair, Gent, Belgium
- Ghent University Hospital, Department of Radiotherapy-Oncology, Gent, Belgium
| | - Jan Aelterman
- Ghent University, Department of Physics and Astronomy, Ghent University Centre for X-ray Tomography, Gent, Belgium
- Ghent University, Department TELIN / IMEC, Image Processing Interpretation Group, Gent, Belgium
| | | | - Stephan Ponte
- Centre Hospitalier Universitaire de Liège, Service de Radiothérapie, Liège, Belgium
| | - Barbara Vanderstraeten
- Ghent University, Faculty of Medicine and Health Sciences, Department of Human Structure and Repair, Gent, Belgium
- Ghent University Hospital, Department of Radiotherapy-Oncology, Gent, Belgium
- Corresponding author at: Ghent University Hospital, Department of Radiotherapy-Oncology, RTP Ingang 98, Corneel Heymanslaan 10, B-9000 Gent, Belgium.
| |
Collapse
|