Deep Learning-Based Automatic Segmentation of Cardiac Substructures for Lung Cancers

Authors

Xinru Chen
Raymond P Mumme
Kelsey L Corrigan
Yuki Mukai-Sasaki
Efstratios Koutroumpakis
Nicolas L Palaskas
Callistus M Nguyen
Yao Zhao
Kai Huang
Cenji Yu
Ting Xu
Aji Daniel
Peter A Balter
Xiaodong Zhang
Joshua S Niedzielski
Sanjay S Shete
Anita Deswal
Laurence E Court
Zhongxing Liao
Jinzhong Yang

Publication Date

2-1-2024

Journal

Radiotherapy Oncology

Abstract

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.

Keywords

Humans, Lung Neoplasms, Carcinoma, Non-Small-Cell Lung, Deep Learning, Radiotherapy Planning, Computer-Assisted, Heart, Organs at Risk, Lung cancer, Radiotherapy, Neural networks, Auto-segmentation, Coronary arteries

DOI

10.1016/j.radonc.2023.110061

PMID

38122850

PMCID

PMC12005477

PubMedCentral® Posted Date

4-17-2025

PubMedCentral® Full Text Version

Author MSS

Published Open-Access

yes