TY - JOUR
T1 - Deep learning–based automatic segmentation of cardiac substructures for lung cancers
AU - Chen, Xinru
AU - Mumme, Raymond P.
AU - Corrigan, Kelsey L.
AU - Mukai-Sasaki, Yuki
AU - Koutroumpakis, Efstratios
AU - Palaskas, Nicolas L.
AU - Nguyen, Callistus M.
AU - Zhao, Yao
AU - Huang, Kai
AU - Yu, Cenji
AU - Xu, Ting
AU - Daniel, Aji
AU - Balter, Peter A.
AU - Zhang, Xiaodong
AU - Niedzielski, Joshua S.
AU - Shete, Sanjay S.
AU - Deswal, Anita
AU - Court, Laurence E.
AU - Liao, Zhongxing
AU - Yang, Jinzhong
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2024/2
Y1 - 2024/2
N2 - Purpose: Accurate and comprehensive segmentation of cardiac substructures is crucial for minimizing the risk of radiation-induced heart disease in lung cancer radiotherapy. We sought to develop and validate deep learning–based auto-segmentation models for cardiac substructures. Materials and Methods: Nineteen cardiac substructures (whole heart, 4 heart chambers, 6 great vessels, 4 valves, and 4 coronary arteries) in 100 patients treated for non-small cell lung cancer were manually delineated by two radiation oncologists. The valves and coronary arteries were delineated as planning risk volumes. An nnU-Net auto-segmentation model was trained, validated, and tested on this dataset with a split ratio of 75:5:20. The auto-segmented contours were evaluated by comparing them with manually drawn contours in terms of Dice similarity coefficient (DSC) and dose metrics extracted from clinical plans. An independent dataset of 42 patients was used for subjective evaluation of the auto-segmentation model by 4 physicians. Results: The average DSCs were 0.95 (+/– 0.01) for the whole heart, 0.91 (+/– 0.02) for 4 chambers, 0.86 (+/– 0.09) for 6 great vessels, 0.81 (+/– 0.09) for 4 valves, and 0.60 (+/– 0.14) for 4 coronary arteries. The average absolute errors in mean/max doses to all substructures were 1.04 (+/– 1.99) Gy and 2.20 (+/– 4.37) Gy. The subjective evaluation revealed that 94% of the auto-segmented contours were clinically acceptable. Conclusion: We demonstrated the effectiveness of our nnU-Net model for delineating cardiac substructures, including coronary arteries. Our results indicate that this model has promise for studies regarding radiation dose to cardiac substructures.
AB - Purpose: Accurate and comprehensive segmentation of cardiac substructures is crucial for minimizing the risk of radiation-induced heart disease in lung cancer radiotherapy. We sought to develop and validate deep learning–based auto-segmentation models for cardiac substructures. Materials and Methods: Nineteen cardiac substructures (whole heart, 4 heart chambers, 6 great vessels, 4 valves, and 4 coronary arteries) in 100 patients treated for non-small cell lung cancer were manually delineated by two radiation oncologists. The valves and coronary arteries were delineated as planning risk volumes. An nnU-Net auto-segmentation model was trained, validated, and tested on this dataset with a split ratio of 75:5:20. The auto-segmented contours were evaluated by comparing them with manually drawn contours in terms of Dice similarity coefficient (DSC) and dose metrics extracted from clinical plans. An independent dataset of 42 patients was used for subjective evaluation of the auto-segmentation model by 4 physicians. Results: The average DSCs were 0.95 (+/– 0.01) for the whole heart, 0.91 (+/– 0.02) for 4 chambers, 0.86 (+/– 0.09) for 6 great vessels, 0.81 (+/– 0.09) for 4 valves, and 0.60 (+/– 0.14) for 4 coronary arteries. The average absolute errors in mean/max doses to all substructures were 1.04 (+/– 1.99) Gy and 2.20 (+/– 4.37) Gy. The subjective evaluation revealed that 94% of the auto-segmented contours were clinically acceptable. Conclusion: We demonstrated the effectiveness of our nnU-Net model for delineating cardiac substructures, including coronary arteries. Our results indicate that this model has promise for studies regarding radiation dose to cardiac substructures.
KW - Auto-segmentation
KW - Coronary arteries
KW - Lung cancer
KW - Neural networks
KW - Radiotherapy
UR - http://www.scopus.com/inward/record.url?scp=85181690584&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85181690584&partnerID=8YFLogxK
U2 - 10.1016/j.radonc.2023.110061
DO - 10.1016/j.radonc.2023.110061
M3 - Article
C2 - 38122850
AN - SCOPUS:85181690584
SN - 0167-8140
VL - 191
JO - Radiotherapy and Oncology
JF - Radiotherapy and Oncology
M1 - 110061
ER -