1
|
Summerfield N, Morris E, Banerjee S, He Q, Ghanem AI, Zhu S, Zhao J, Dong M, Glide-Hurst C. Enhancing Precision in Cardiac Segmentation for Magnetic Resonance-Guided Radiation Therapy Through Deep Learning. Int J Radiat Oncol Biol Phys 2024:S0360-3016(24)00671-0. [PMID: 38797498 DOI: 10.1016/j.ijrobp.2024.05.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Revised: 04/25/2024] [Accepted: 05/17/2024] [Indexed: 05/29/2024]
Abstract
PURPOSE Cardiac substructure dose metrics are more strongly linked to late cardiac morbidities than to whole-heart metrics. Magnetic resonance (MR)-guided radiation therapy (MRgRT) enables substructure visualization during daily localization, allowing potential for enhanced cardiac sparing. We extend a publicly available state-of-the-art deep learning framework, "No New" U-Net, to incorporate self-distillation (nnU-Net.wSD) for substructure segmentation for MRgRT. METHODS AND MATERIALS Eighteen (institute A) patients who underwent thoracic or abdominal radiation therapy on a 0.35 T MR-guided linear accelerator were retrospectively evaluated. On each image, 1 of 2 radiation oncologists delineated reference contours of 12 cardiac substructures (chambers, great vessels, and coronary arteries) used to train (n = 10), validate (n = 3), and test (n = 5) nnU-Net.wSD by leveraging a teacher-student network and comparing it to standard 3-dimensional U-Net. The impact of using simulation data or including 3 to 4 daily images for augmentation during training was evaluated for nnU-Net.wSD. Geometric metrics (Dice similarity coefficient, mean distance to agreement, and 95% Hausdorff distance), visual inspection, and clinical dose-volume histograms were evaluated. To determine generalizability, institute A's model was tested on an unlabeled data set from institute B (n = 22) and evaluated via consensus scoring and volume comparisons. RESULTS nnU-Net.wSD yielded a Dice similarity coefficient (reported mean ± SD) of 0.65 ± 0.25 across the 12 substructures (chambers, 0.85 ± 0.05; great vessels, 0.67 ± 0.19; and coronary arteries, 0.33 ± 0.16; mean distance to agreement, <3 mm; mean 95% Hausdorff distance, <9 mm) while outperforming the 3-dimensional U-Net (0.583 ± 0.28; P <.01). Leveraging fractionated data for augmentation improved over a single MR simulation time point (0.579 ± 0.29; P <.01). Predicted contours yielded dose-volume histograms that closely matched those of the clinical treatment plans where mean and maximum (ie, dose to 0.03 cc) doses deviated by 0.32 ± 0.5 Gy and 1.42 ± 2.6 Gy, respectively. There were no statistically significant differences between institute A and B volumes (P >.05) for 11 of 12 substructures, with larger volumes requiring minor changes and coronary arteries exhibiting more variability. CONCLUSIONS This work is a critical step toward rapid and reliable cardiac substructure segmentation to improve cardiac sparing in low-field MRgRT.
Collapse
Affiliation(s)
- Nicholas Summerfield
- Department of Medical Physics, University of Wisconsin-Madison, Madison, Wisconsin; Department of Human Oncology, University of Wisconsin-Madison, Madison, Wisconsin
| | - Eric Morris
- Department of Radiation Oncology, Washington University of Medicine in St. Louis, St. Louis, Missouri
| | - Soumyanil Banerjee
- Department of Computer Science, Wayne State University, Detroit, Michigan
| | - Qisheng He
- Department of Computer Science, Wayne State University, Detroit, Michigan
| | - Ahmed I Ghanem
- Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, Michigan; Alexandria Department of Clinical Oncology, Faculty of Medicine, Alexandria University, Alexandria, Egypt
| | - Simeng Zhu
- Department of Radiation Oncology, The Ohio State University, Columbus, Ohio
| | - Jiwei Zhao
- Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, Wisconsin
| | - Ming Dong
- Department of Computer Science, Wayne State University, Detroit, Michigan
| | - Carri Glide-Hurst
- Department of Medical Physics, University of Wisconsin-Madison, Madison, Wisconsin; Department of Human Oncology, University of Wisconsin-Madison, Madison, Wisconsin.
| |
Collapse
|
2
|
Finnegan RN, Quinn A, Booth J, Belous G, Hardcastle N, Stewart M, Griffiths B, Carroll S, Thwaites DI. Cardiac substructure delineation in radiation therapy - A state-of-the-art review. J Med Imaging Radiat Oncol 2024. [PMID: 38757728 DOI: 10.1111/1754-9485.13668] [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: 01/24/2024] [Accepted: 04/29/2024] [Indexed: 05/18/2024]
Abstract
Delineation of cardiac substructures is crucial for a better understanding of radiation-related cardiotoxicities and to facilitate accurate and precise cardiac dose calculation for developing and applying risk models. This review examines recent advancements in cardiac substructure delineation in the radiation therapy (RT) context, aiming to provide a comprehensive overview of the current level of knowledge, challenges and future directions in this evolving field. Imaging used for RT planning presents challenges in reliably visualising cardiac anatomy. Although cardiac atlases and contouring guidelines aid in standardisation and reduction of variability, significant uncertainties remain in defining cardiac anatomy. Coupled with the inherent complexity of the heart, this necessitates auto-contouring for consistent large-scale data analysis and improved efficiency in prospective applications. Auto-contouring models, developed primarily for breast and lung cancer RT, have demonstrated performance comparable to manual contouring, marking a significant milestone in the evolution of cardiac delineation practices. Nevertheless, several key concerns require further investigation. There is an unmet need for expanding cardiac auto-contouring models to encompass a broader range of cancer sites. A shift in focus is needed from ensuring accuracy to enhancing the robustness and accessibility of auto-contouring models. Addressing these challenges is paramount for the integration of cardiac substructure delineation and associated risk models into routine clinical practice, thereby improving the safety of RT for future cancer patients.
Collapse
Affiliation(s)
- Robert N Finnegan
- Northern Sydney Cancer Centre, Royal North Shore Hospital, Sydney, New South Wales, Australia
- Institute of Medical Physics, School of Physics, University of Sydney, Sydney, New South Wales, Australia
| | - Alexandra Quinn
- Northern Sydney Cancer Centre, Royal North Shore Hospital, Sydney, New South Wales, Australia
| | - Jeremy Booth
- Northern Sydney Cancer Centre, Royal North Shore Hospital, Sydney, New South Wales, Australia
- Institute of Medical Physics, School of Physics, University of Sydney, Sydney, New South Wales, Australia
| | - Gregg Belous
- Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation, Brisbane, Queensland, Australia
| | - Nicholas Hardcastle
- Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia
- Sir Peter MacCallum Department of Oncology, University of Melbourne, Melbourne, Victoria, Australia
| | - Maegan Stewart
- Northern Sydney Cancer Centre, Royal North Shore Hospital, Sydney, New South Wales, Australia
- School of Health Sciences, Faculty of Medicine and Health, University of Sydney, Sydney, New South Wales, Australia
| | - Brooke Griffiths
- Northern Sydney Cancer Centre, Royal North Shore Hospital, Sydney, New South Wales, Australia
| | - Susan Carroll
- Northern Sydney Cancer Centre, Royal North Shore Hospital, Sydney, New South Wales, Australia
- School of Health Sciences, Faculty of Medicine and Health, University of Sydney, Sydney, New South Wales, Australia
| | - David I Thwaites
- Institute of Medical Physics, School of Physics, University of Sydney, Sydney, New South Wales, Australia
- Radiotherapy Research Group, Leeds Institute of Medical Research, St James's Hospital and University of Leeds, Leeds, UK
| |
Collapse
|
3
|
Wen X, Zhao C, Zhao B, Yuan M, Chang J, Liu W, Meng J, Shi L, Yang S, Zeng J, Yang Y. Application of deep learning in radiation therapy for cancer. Cancer Radiother 2024; 28:208-217. [PMID: 38519291 DOI: 10.1016/j.canrad.2023.07.015] [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: 06/26/2023] [Revised: 07/17/2023] [Accepted: 07/18/2023] [Indexed: 03/24/2024]
Abstract
In recent years, with the development of artificial intelligence, deep learning has been gradually applied to clinical treatment and research. It has also found its way into the applications in radiotherapy, a crucial method for cancer treatment. This study summarizes the commonly used and latest deep learning algorithms (including transformer, and diffusion models), introduces the workflow of different radiotherapy, and illustrates the application of different algorithms in different radiotherapy modules, as well as the defects and challenges of deep learning in the field of radiotherapy, so as to provide some help for the development of automatic radiotherapy for cancer.
Collapse
Affiliation(s)
- X Wen
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; Department of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China
| | - C Zhao
- School of Biomedical Engineering, Shanghai Jiao Tong University, No. 800, Dongchuan Road, Minhang District, Shanghai, China
| | - B Zhao
- Department of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China
| | - M Yuan
- Department of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China
| | - J Chang
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; School of Basic Medicine, Qingdao University, Qingdao, China
| | - W Liu
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; School of Basic Medicine, Qingdao University, Qingdao, China
| | - J Meng
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; School of Basic Medicine, Qingdao University, Qingdao, China
| | - L Shi
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; School of Basic Medicine, Qingdao University, Qingdao, China
| | - S Yang
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; School of Basic Medicine, Qingdao University, Qingdao, China
| | - J Zeng
- Cancer Institute of the Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao University, Qingdao, China; School of Basic Medicine, Qingdao University, Qingdao, China
| | - Y Yang
- Department of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China.
| |
Collapse
|
4
|
Olloni A, Lorenzen EL, Jeppesen SS, Diederichsen A, Finnegan R, Hoffmann L, Kristiansen C, Knap M, Milo MLH, Møller DS, Pøhl M, Persson G, Sand HMB, Sarup N, Thing RS, Brink C, Schytte T. An open source auto-segmentation algorithm for delineating heart and substructures - Development and validation within a multicenter lung cancer cohort. Radiother Oncol 2024; 191:110065. [PMID: 38122851 DOI: 10.1016/j.radonc.2023.110065] [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: 08/03/2023] [Revised: 11/27/2023] [Accepted: 12/13/2023] [Indexed: 12/23/2023]
Abstract
BACKGROUND AND PURPOSE Irradiation of the heart in thoracic cancers raises toxicity concerns. For accurate dose estimation, automated heart and substructure segmentation is potentially useful. In this study, a hybrid automatic segmentation is developed. The accuracy of delineation and dose predictions were evaluated, testing the method's potential within heart toxicity studies. MATERIALS AND METHODS The hybrid segmentation method delineated the heart, four chambers, three large vessels, and the coronary arteries. The method consisted of a nnU-net heart segmentation and partly atlas- and model-based segmentation of the substructures. The nnU-net training and atlas segmentation was based on lung cancer patients and was validated against a national consensus dataset of 12 patients with breast cancer. The accuracy of dose predictions between manual and auto-segmented heart and substructures was evaluated by transferring the dose distribution of 240 previously treated lung cancer patients to the consensus data set. RESULTS The hybrid auto-segmentation method performed well with a heart dice similarity coefficient (DSC) of 0.95, with no statistically significant difference between the automatic and manual delineations. The DSC for the chambers varied from 0.78-0.86 for the automatic segmentation and was comparable with the inter-observer variability. Most importantly, the automatic segmentation was as precise as the clinical experts in predicting the dose distribution to the heart and all substructures. CONCLUSION The hybrid segmentation method performed well in delineating the heart and substructures. The prediction of dose by the automatic segmentation was aligned with the manual delineations, enabling measurement of heart and substructure dose in large cohorts. The delineation algorithm will be available for download.
Collapse
Affiliation(s)
- Agon Olloni
- Department of Oncology, Odense University Hospital, Denmark; Department of Clinical Research, University of Southern Denmark, Denmark; Academy of Geriatric Cancer Research (AgeCare), Odense University Hospital, Denmark.
| | - Ebbe Laugaard Lorenzen
- Department of Clinical Research, University of Southern Denmark, Denmark; Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Denmark
| | - Stefan Starup Jeppesen
- Department of Oncology, Odense University Hospital, Denmark; Department of Clinical Research, University of Southern Denmark, Denmark; Academy of Geriatric Cancer Research (AgeCare), Odense University Hospital, Denmark
| | - Axel Diederichsen
- Department of Clinical Research, University of Southern Denmark, Denmark; Department of Cardiology, Odense University Hospital, Denmark
| | - Robert Finnegan
- Northern Sydney Cancer Centre, Royal North Shore Hospital, St Leonards, NSW, Australia
| | - Lone Hoffmann
- Department of Oncology, Aarhus University Hospital, Denmark; Department of Clinical Medicine, Faculty of Health Sciences, Aarhus University, Denmark
| | - Charlotte Kristiansen
- Department of Oncology, Vejle Hospital University Hospital of Southern Denmark, Denmark
| | - Marianne Knap
- Department of Oncology, Aarhus University Hospital, Denmark
| | | | - Ditte Sloth Møller
- Department of Oncology, Aarhus University Hospital, Denmark; Department of Clinical Medicine, Faculty of Health Sciences, Aarhus University, Denmark
| | - Mette Pøhl
- Department of Oncology, Rigshospitalet, Copenhagen University Hospital, Denmark
| | - Gitte Persson
- Department of Oncology, Copenhagen University Hospital, Herlev and Gentofte, Denmark; Department of Clinical Medicine, Copenhagen University, Denmark
| | - Hella M B Sand
- Department of Oncology, Aalborg University Hospital, Denmark
| | - Nis Sarup
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Denmark
| | - Rune Slot Thing
- Department of Oncology, Vejle Hospital University Hospital of Southern Denmark, Denmark
| | - Carsten Brink
- Department of Clinical Research, University of Southern Denmark, Denmark; Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Denmark
| | - Tine Schytte
- Department of Oncology, Odense University Hospital, Denmark; Department of Clinical Research, University of Southern Denmark, Denmark
| |
Collapse
|
5
|
Balgobind BV, Visser J, Grehn M, Marquard Knap M, de Ruysscher D, Levis M, Alcantara P, Boda-Heggemann J, Both M, Cozzi S, Cvek J, Dieleman EMT, Elicin O, Giaj-Levra N, Jumeau R, Krug D, Algara López M, Mayinger M, Mehrhof F, Miszczyk M, Pérez-Calatayud MJ, van der Pol LHG, van der Toorn PP, Vitolo V, Postema PG, Pruvot E, Verhoeff JC, Blanck O. Refining critical structure contouring in STereotactic Arrhythmia Radioablation (STAR): Benchmark results and consensus guidelines from the STOPSTORM.eu consortium. Radiother Oncol 2023; 189:109949. [PMID: 37827279 DOI: 10.1016/j.radonc.2023.109949] [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: 05/16/2023] [Revised: 09/05/2023] [Accepted: 10/09/2023] [Indexed: 10/14/2023]
Abstract
BACKGROUND AND PURPOSE In patients with recurrent ventricular tachycardia (VT), STereotactic Arrhythmia Radioablation (STAR) shows promising results. The STOPSTORM.eu consortium was established to investigate and harmonise STAR treatment in Europe. The primary goals of this benchmark study were to standardise contouring of organs at risk (OAR) for STAR, including detailed substructures of the heart, and accredit each participating centre. MATERIALS AND METHODS Centres within the STOPSTORM.eu consortium were asked to delineate 31 OAR in three STAR cases. Delineation was reviewed by the consortium expert panel and after a dedicated workshop feedback and accreditation was provided to all participants. Further quantitative analysis was performed by calculating DICE similarity coefficients (DSC), median distance to agreement (MDA), and 95th percentile distance to agreement (HD95). RESULTS Twenty centres participated in this study. Based on DSC, MDA and HD95, the delineations of well-known OAR in radiotherapy were similar, such as lungs (median DSC = 0.96, median MDA = 0.1 mm and median HD95 = 1.1 mm) and aorta (median DSC = 0.90, median MDA = 0.1 mm and median HD95 = 1.5 mm). Some centres did not include the gastro-oesophageal junction, leading to differences in stomach and oesophagus delineations. For cardiac substructures, such as chambers (median DSC = 0.83, median MDA = 0.2 mm and median HD95 = 0.5 mm), valves (median DSC = 0.16, median MDA = 4.6 mm and median HD95 = 16.0 mm), coronary arteries (median DSC = 0.4, median MDA = 0.7 mm and median HD95 = 8.3 mm) and the sinoatrial and atrioventricular nodes (median DSC = 0.29, median MDA = 4.4 mm and median HD95 = 11.4 mm), deviations between centres occurred more frequently. After the dedicated workshop all centres were accredited and contouring consensus guidelines for STAR were established. CONCLUSION This STOPSTORM multi-centre critical structure contouring benchmark study showed high agreement for standard radiotherapy OAR. However, for cardiac substructures larger disagreement in contouring occurred, which may have significant impact on STAR treatment planning and dosimetry evaluation. To standardize OAR contouring, consensus guidelines for critical structure contouring in STAR were established.
Collapse
Affiliation(s)
- Brian V Balgobind
- Department of Radiation Oncology, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands.
| | - Jorrit Visser
- Department of Radiation Oncology, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
| | - Melanie Grehn
- Department of Radiation Oncology, University Medical Center Schleswig-Holstein, Kiel, Germany
| | | | - Dirk de Ruysscher
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University, Maastricht, the Netherlands
| | - Mario Levis
- Department of Oncology, University of Torino, Torino, Italy
| | - Pino Alcantara
- Department of Radiation Oncology, Hospital Clínico San Carlos, Faculty of Medicine, University Complutense of Madrid, Madrid, Spain
| | - Judit Boda-Heggemann
- Department of Radiation Oncology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, Mannheim, Germany
| | - Marcus Both
- Department of Radiology and Neuroradiology, University Medical Center Schleswig-Holstein, Kiel, Germany
| | - Salvatore Cozzi
- Radiation Oncology Unit, Azienda USL-IRCCS, Reggio Emilia, Italy; Radiation Oncology Department, Centre Léon Bérard, Lyon, France
| | - Jakub Cvek
- Department of Oncology, University Hospital and Faculty of Medicine, Ostrava, Czech Republic
| | - Edith M T Dieleman
- Department of Radiation Oncology, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
| | - Olgun Elicin
- Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Niccolò Giaj-Levra
- Department of Advanced Radiation Oncology Department, IRCCS Sacro Cuore Don Calabria Hospital, Negrar, Verona, Italy
| | - Raphaël Jumeau
- Department of Radio-Oncology, Lausanne University Hospital, Lausanne, Switzerland
| | - David Krug
- Department of Radiation Oncology, University Medical Center Schleswig-Holstein, Kiel, Germany
| | - Manuel Algara López
- Department of Radiotherapy, Hospital del Mar, Universitat Pompeu Fabra, Barcelona, Spain
| | - Michael Mayinger
- Department of Radiation Oncology, University Hospital of Zurich, Zurich, Switzerland
| | - Felix Mehrhof
- Department for Radiation Oncology, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Marcin Miszczyk
- IIIrd Radiotherapy and Chemotherapy Department, Maria Skłodowska-Curie National Research Institute of Oncology, Gliwice, Poland
| | | | - Luuk H G van der Pol
- Department of Radiotherapy, University Medical Center Utrecht, Utrecht, the Netherlands
| | | | - Viviana Vitolo
- Radiation Oncology Clinical Department, National Center of Oncological Hadrontherapy (Fondazione CNAO), Pavia, Italy
| | - Pieter G Postema
- Department of Cardiology, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
| | - Etienne Pruvot
- Heart and Vessel Department, Service of Cardiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Joost C Verhoeff
- Department of Radiotherapy, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Oliver Blanck
- Department of Radiation Oncology, University Medical Center Schleswig-Holstein, Kiel, Germany
| |
Collapse
|
6
|
Skarsø ER, Refsgaard L, Saini A, Sloth Møller D, Lorenzen EL, Maae E, Andersen K, Maraldo MV, Milo ML, Nyeng TB, Vrou Offersen B, Korreman SS. Development of a national deep learning-based auto-segmentation model for the heart on clinical delineations from the DBCG RT nation cohort. Acta Oncol 2023; 62:1201-1207. [PMID: 37712509 DOI: 10.1080/0284186x.2023.2252582] [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: 04/29/2023] [Accepted: 08/16/2023] [Indexed: 09/16/2023]
Abstract
BACKGROUND This study aimed at investigating the feasibility of developing a deep learning-based auto-segmentation model for the heart trained on clinical delineations. MATERIAL AND METHODS This study included two different datasets. The first dataset contained clinical heart delineations from the DBCG RT Nation study (1,561 patients). The second dataset was smaller (114 patients), but with corrected heart delineations. Before training the model on the clinical delineations an outlier-detection was performed, to remove cases with gross deviations from the delineation guideline. No outlier detection was performed for the dataset with corrected heart delineations. Both models were trained with a 3D full resolution nnUNet. The models were evaluated with the dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and Mean Surface Distance (MSD). The difference between the models were tested with the Mann-Whitney U-test. The balance of dataset quantity versus quality was investigated, by stepwise reducing the cohort size for the model trained on clinical delineations. RESULTS During the outlier-detection 137 patients were excluded from the clinical cohort due to non-compliance with delineation guidelines. The model trained on the curated clinical cohort performed with a median DSC of 0.96 (IQR 0.94-0.96), median HD95 of 4.00 mm (IQR 3.00 mm-6.00 mm) and a median MSD of 1.49 mm (IQR 1.12 mm-2.02 mm). The model trained on the dedicated and corrected cohort performed with a median DSC of 0.95 (IQR 0.93-0.96), median HD95 of 5.65 mm (IQR 3.37 mm-8.62 mm) and median MSD of 1.63 mm (IQR 1.35 mm-2.11 mm). The difference between the two models were found non-significant for all metrics (p > 0.05). Reduction of cohort size showed no significant difference for all metrics (p > 0.05). However, with the smallest cohort size, a few outlier structures were found. CONCLUSIONS This study demonstrated a deep learning-based auto-segmentation model trained on curated clinical delineations which performs on par with a model trained on dedicated delineations, making it easier to develop multi-institutional auto-segmentation models.
Collapse
Affiliation(s)
- Emma Riis Skarsø
- Danish Center for Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
- Department of Clinical medicine, Aarhus University, Aarhus, Denmark
| | - Lasse Refsgaard
- Department of Clinical medicine, Aarhus University, Aarhus, Denmark
- Department of Experimental Clinical Oncology, Aarhus University Hospital, Aarhus, Denmark
| | - Abhilasha Saini
- Department of Clinical Oncology and Palliative Care, Zealand University Hospital, Næstved, Denmark
| | - Ditte Sloth Møller
- Department of Clinical medicine, Aarhus University, Aarhus, Denmark
- Department of Oncology, Aarhus University Hospital, Aarhus, Denmark
| | - Ebbe Laugaard Lorenzen
- Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, Odense, Denmark
| | - Else Maae
- Department of Oncology, Vejle Hospital, University Hospital of Southern Denmark, Vejle, Denmark
| | - Karen Andersen
- Department of Oncology, Herlev and Gentofte Hospital, Herlev, Denmark
| | - Maja Vestmø Maraldo
- Department of Clinical Oncology, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark
| | - Marie Louise Milo
- Department of Oncology, Aalborg University Hospital, Aalborg, Denmark
| | | | - Birgitte Vrou Offersen
- Danish Center for Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
- Department of Clinical medicine, Aarhus University, Aarhus, Denmark
- Department of Experimental Clinical Oncology, Aarhus University Hospital, Aarhus, Denmark
- Department of Oncology, Aarhus University Hospital, Aarhus, Denmark
| | - Stine Sofia Korreman
- Danish Center for Particle Therapy, Aarhus University Hospital, Aarhus, Denmark
- Department of Clinical medicine, Aarhus University, Aarhus, Denmark
- Department of Oncology, Aarhus University Hospital, Aarhus, Denmark
| |
Collapse
|
7
|
Gao L, Yusufaly TI, Williamson CW, Mell LK. Optimized Atlas-Based Auto-Segmentation of Bony Structures from Whole-Body Computed Tomography. Pract Radiat Oncol 2023; 13:e442-e450. [PMID: 37030539 DOI: 10.1016/j.prro.2023.03.013] [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: 10/05/2022] [Revised: 03/14/2023] [Accepted: 03/15/2023] [Indexed: 04/09/2023]
Abstract
PURPOSE To develop and test a method for fully automated segmentation of bony structures from whole-body computed tomography (CT) and evaluate its performance compared with manual segmentation. METHODS AND MATERIALS We developed a workflow for automatic whole-body bone segmentation using atlas-based segmentation (ABS) method with a postprocessing module (ABSPP) in MIM MAESTRO software. Fifty-two CT scans comprised the training set to build the atlas library, and 29 CT scans comprised the test set. To validate the workflow, we compared Dice similarity coefficient (DSC), mean distance to agreement, and relative volume errors between ABSPP and ABS with no postprocessing (ABSNPP) with manual segmentation as the reference (gold standard). RESULTS The ABSPP method resulted in significantly improved segmentation accuracy (DSC range, 0.85-0.98) compared with the ABSNPP method (DSC range, 0.55-0.87; P < .001). Mean distance to agreement results also indicated high agreement between ABSPP and manual reference delineations (range, 0.11-1.56 mm), which was significantly improved compared with ABSNPP (range, 1.00-2.34 mm) for the majority of tested bony structures. Relative volume errors were also significantly lower for ABSPP compared with ABSNPP for most bony structures. CONCLUSIONS We developed a fully automated MIM workflow for bony structure segmentation from whole-body CT, which exhibited high accuracy compared with manual delineation. The integrated postprocessing module significantly improved workflow performance.
Collapse
Affiliation(s)
- Lei Gao
- Department of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California
| | - Tahir I Yusufaly
- Russell H. Morgan Department of Radiology and Radiologic Sciences, Johns Hopkins University, School of Medicine, Baltimore, Maryland
| | - Casey W Williamson
- Department of Radiation Medicine, Oregon Health Sciences University, Portland, Oregon
| | - Loren K Mell
- Department of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California.
| |
Collapse
|
8
|
Welgemoed C, Spezi E, Riddle P, Gooding MJ, Gujral D, McLauchlan R, Aboagye EO. Clinical evaluation of atlas-based auto-segmentation in breast and nodal radiotherapy. Br J Radiol 2023; 96:20230040. [PMID: 37493138 PMCID: PMC10461279 DOI: 10.1259/bjr.20230040] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2023] [Revised: 06/23/2023] [Accepted: 06/28/2023] [Indexed: 07/27/2023] Open
Abstract
OBJECTIVES Accurate contouring of anatomical structures allows for high-precision radiotherapy planning, targeting the dose at treatment volumes and avoiding organs at risk. Manual contouring is time-consuming with significant user variability, whereas auto-segmentation (AS) has proven efficiency benefits but requires editing before treatment planning. This study investigated whether atlas-based AS (ABAS) accuracy improves with template atlas group size and character-specific atlas and test case selection. METHODS AND MATERIALS One clinician retrospectively contoured the breast, nodes, lung, heart, and brachial plexus on 100 CT scans, adhering to peer-reviewed guidelines. Atlases were clustered in group sizes, treatment positions, chest wall separations, and ASs created with Mirada software. The similarity of ASs compared to reference contours was described by the Jaccard similarity coefficient (JSC) and centroid distance variance (CDV). RESULTS Across group sizes, for all structures combined, the mean JSC was 0.6 (SD 0.3, p = .999). Across atlas-specific groups, 0.6 (SD 0.3, p = 1.000). The correlation between JSC and structure volume was weak in both scenarios (adjusted R2-0.007 and 0.185).Mean CDV was similar across groups but varied up to 1.2 cm for specific structures. CONCLUSIONS Character-specific atlas groups and test case selection did not improve accuracy outcomes. High-quality ASs were obtained from groups containing as few as ten atlases, subsequently simplifying the application of ABAS. CDV measures indicating auto-segmentation variations on the x, y, and z axes can be utilised to decide on the clinical relevance of variations and reduce AS editing. ADVANCES IN KNOWLEDGE High-quality ABASs can be obtained from as few as ten template atlases.Atlas and test case selection do not improve AS accuracy.Unlike well-known quantitative similarity indices, volume displacement metrics provide information on the location of segmentation variations, helping assessment of the clinical relevance of variations and reducing clinician editing. Volume displacement metrics combined with the qualitative measure of clinician assessment could reduce user variability.
Collapse
Affiliation(s)
| | - Emiliano Spezi
- School of Engineering, Cardiff University, Cardiff, United Kingdom
| | - Pippa Riddle
- Radiotherapy Department, Imperial College Healthcare NHS Trust, Charing Cross Hospital, London, United Kingdom
| | | | | | | | - Eric O Aboagye
- Department of Surgery and Cancer, Imperial College London, Hammersmith Campus, London, United Kingdom
| |
Collapse
|
9
|
Mövik L, Bäck A, Pettersson N. Impact of delineation errors on the estimated organ at risk dose and of dose errors on the normal tissue complication probability model. Med Phys 2023; 50:1879-1892. [PMID: 36693127 DOI: 10.1002/mp.16235] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Revised: 12/04/2022] [Accepted: 01/01/2023] [Indexed: 01/25/2023] Open
Abstract
BACKGROUND Normal tissue complication probability (NTCP) models are often based on doses retrieved from delineated volumes. For retrospective dose-response studies focusing on organs that have not been delineated historically, automatic segmentation might be considered. However, automatic segmentation risks generating considerable delineation errors and knowledge regarding how these errors impact the estimated organ dose is important. Furthermore, organ-at-risk (OAR) dose uncertainties cannot be eliminated and might affect the resulting NTCP model. Therefore, it is also of interest to study how OAR dose errors impact the NTCP modeling results. PURPOSE To investigate how random delineation errors of the proximal bronchial tree, heart, and esophagus impact the estimated OAR dose, and to investigate how random errors in the doses used for dose-response modeling affect the estimated NTCPs. METHODS We investigated the impact of random delineation errors on the estimated OAR dose using the treatment plans of 39 patients treated with conventionally fractionated radiation therapy of non-small-cell lung cancer. Study-specific reference structures were defined by manually contouring the proximal bronchial tree, heart and esophagus. For each patient and organ, 120 reshaped structures were created by introducing random shifts and margins to the entire reference structure. The mean and near-maximum dose to the reference and reshaped structures were compared. In a separate investigation, the impact of random dose errors on the NTCP model was studied performing dose-response modeling with study sets containing treatment outcomes and OAR doses with and without introduced errors. Universal patient populations with defined population risks, dose-response relationships and distributions of OAR doses were used as ground truth. From such a universal population, we randomly sampled data sets consisting of OAR dose and treatment outcome into reference populations. Study sets of different sizes were created by repeatedly introducing errors to the OAR doses of each reference population. The NTCP models generated with dose errors were compared to the reference NTCP model of the corresponding reference population. RESULTS A total of 14 040 reshaped structures with random delineation errors were created. The delineation errors resulted in systematic mean dose errors of less than 1% of the prescribed dose (PD). Mean dose differences above 15% of PD and near-maximum doses differences above 25% of PD were observed for 211 and 457 reshaped structures, respectively. Introducing random errors to OAR doses used for dose-response modeling resulted in systematic underestimations of the median NTCP. For all investigated scenarios, the median differences in NTCP were within 0.1 percentage points (p.p.) when comparing different study sizes. CONCLUSIONS Introducing random delineation errors to the proximal bronchial tree, heart and esophagus resulted in mean dose and near-maximum dose differences above 15% and 25% of PD, respectively. We did not observe an association between the dose level and the magnitude of the dose errors. For the scenarios investigated in this study, introducing random errors to OAR doses used for dose-response modeling resulted in systematic underestimations of the median NTCP for reference risks higher than the universal population risk. The median NTCP underestimation was similar for different study sizes, all within 0.1 p.p.
Collapse
Affiliation(s)
- Louise Mövik
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Anna Bäck
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Therapeutic Radiation Physics, Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Niclas Pettersson
- Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Therapeutic Radiation Physics, Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, Gothenburg, Sweden
| |
Collapse
|
10
|
Mackay K, Bernstein D, Glocker B, Kamnitsas K, Taylor A. A Review of the Metrics Used to Assess Auto-Contouring Systems in Radiotherapy. Clin Oncol (R Coll Radiol) 2023; 35:354-369. [PMID: 36803407 DOI: 10.1016/j.clon.2023.01.016] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2022] [Revised: 12/05/2022] [Accepted: 01/23/2023] [Indexed: 02/01/2023]
Abstract
Auto-contouring could revolutionise future planning of radiotherapy treatment. The lack of consensus on how to assess and validate auto-contouring systems currently limits clinical use. This review formally quantifies the assessment metrics used in studies published during one calendar year and assesses the need for standardised practice. A PubMed literature search was undertaken for papers evaluating radiotherapy auto-contouring published during 2021. Papers were assessed for types of metric and the methodology used to generate ground-truth comparators. Our PubMed search identified 212 studies, of which 117 met the criteria for clinical review. Geometric assessment metrics were used in 116 of 117 studies (99.1%). This includes the Dice Similarity Coefficient used in 113 (96.6%) studies. Clinically relevant metrics, such as qualitative, dosimetric and time-saving metrics, were less frequently used in 22 (18.8%), 27 (23.1%) and 18 (15.4%) of 117 studies, respectively. There was heterogeneity within each category of metric. Over 90 different names for geometric measures were used. Methods for qualitative assessment were different in all but two papers. Variation existed in the methods used to generate radiotherapy plans for dosimetric assessment. Consideration of editing time was only given in 11 (9.4%) papers. A single manual contour as a ground-truth comparator was used in 65 (55.6%) studies. Only 31 (26.5%) studies compared auto-contours to usual inter- and/or intra-observer variation. In conclusion, significant variation exists in how research papers currently assess the accuracy of automatically generated contours. Geometric measures are the most popular, however their clinical utility is unknown. There is heterogeneity in the methods used to perform clinical assessment. Considering the different stages of system implementation may provide a framework to decide the most appropriate metrics. This analysis supports the need for a consensus on the clinical implementation of auto-contouring.
Collapse
Affiliation(s)
- K Mackay
- The Institute of Cancer Research, London, UK; The Royal Marsden Hospital, London, UK.
| | - D Bernstein
- The Institute of Cancer Research, London, UK; The Royal Marsden Hospital, London, UK
| | - B Glocker
- Department of Computing, Imperial College London, South Kensington Campus, London, UK
| | - K Kamnitsas
- Department of Computing, Imperial College London, South Kensington Campus, London, UK; Department of Engineering Science, University of Oxford, Oxford, UK
| | - A Taylor
- The Institute of Cancer Research, London, UK; The Royal Marsden Hospital, London, UK
| |
Collapse
|