Comprehensive Evaluation of a Deep Learning Model for Automatic Organs-at-Risk Segmentation on Heterogeneous Computed Tomography Images for Abdominal Radiation Therapy

作者：Liao, Wenjun; Luo, Xiangde; He, Yuan; Dong, Ye; Li, Churong; Li, Kang; Zhang, Shichuan; Zhang, Shaoting; Wang, Guotai; Xiao, Jianghong^*

来源：International Journal of Radiation Oncology Biology Physics, 2023, 117(4): 994-1006.

DOI：10.1016/j.ijrobp.2023.05.034

• CONTOURING GUIDELINES
• CERVICAL-CANCER
• TARGET VOLUME
• DELINEATION

Purpose: Our purpose was to develop a deep learning model (AbsegNet) that produces accurate contours of 16 organs at risk (OARs) for abdominal malignancies as an essential part of fully automated radiation treatment planning.Methods and Materials: Three data sets with 544 computed tomography scans were retrospectively collected. Data set 1 was split into 300 training cases and 128 test cases (cohort 1) for AbsegNet. Data set 2, including cohort 2 (n = 24) and cohort 3 (n = 20), were used to validate AbsegNet externally. Data set 3, including cohort 4 (n = 40) and cohort 5 (n = 32), were used to clinically assess the accuracy of AbsegNet-generated contours. Each cohort was from a different center. The Dice similarity coefficient and 95th-percentile Hausdorff distance were calculated to evaluate the delineation quality for each OAR. Clinical accuracy evaluation was classified into 4 levels: no revision, minor revisions (0% < volumetric revision degrees [VRD] <= 10%), moderate revisions (10% <= VRD < 20%), and major revisions (VRD >= 20%).Results: For all OARs, AbsegNet achieved a mean Dice similarity coefficient of 86.73%, 85.65%, and 88.04% in cohorts 1, 2, and 3, respectively, and a mean 95th-percentile Hausdorff distance of 8.92, 10.18, and 12.40 mm, respectively. The performance of AbsegNet outperformed SwinUNETR, DeepLabV3+, Attention-UNet, UNet, and 3D-UNet. When experts evaluated contours from cohorts 4 and 5, 4 OARs (liver, kidney_L, kidney_R, and spleen) of all patients were scored as having no revision, and over 87.5% of patients with contours of the stomach, esophagus, adrenals, or rectum were considered as having no or minor revisions. Only 15.0% of patients with colon and small bowel contours required major revisions.Conclusions: We propose a novel deep-learning model to delineate OARs on diverse data sets. Most contours produced by AbsegNet are accurate and robust and are, therefore, clinically applicable and helpful to facilitate radiation therapy workflow.

• 单位
  四川大学; 南方医科大学; 电子科技大学; 1