CT-based deep learning segmentation of ovarian cancer and the stability of the extracted radiomics features

Wang, Yiang1; Wang, Mandi1,2; Cao, Peng1; Wong, Esther M. F.1,3; Ho, Grace4; Lam, Tina P. W.4; Han, Lujun5,6; Lee, Elaine Y. P.1,7

2023-06-01

10.21037/qims-22-1135

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY   影响因子和分区

2223-4292

2223-4306

Background: Radiomics analysis could provide complementary tissue characterization in ovarian cancer (OC). However, OC segmentation required in radiomics analysis is time-consuming and labour-intensive. In this study, we aim to evaluate the performance of deep learning-based segmentation of OC on contrastenhanced CT images and the stability of radiomics features extracted from the automated segmentation. Methods: Staging abdominopelvic CT images of 367 patients with OC were retrospectively recruited. The training and cross-validation sets came from center A (n=283), and testing set (n=84) came from centers B and C. The tumours were manually delineated by a board-certified radiologist. Four model architectures provided by no-new-Net (nnU-Net) method were tested in this task. The segmentation performance evaluated by Dice score, Jaccard score, sensitivity and precision were compared among 4 architectures. The Pearson correlation coefficient (rho), concordance correlation coefficient (rho c) and Bland-Altman plots were used to evaluate the volumetric assessment of OC between manual and automated segmentations. The stability of extracted radiomics features was evaluated by intraclass correlation coefficient (ICC). Results: The 3D U-Net cascade architecture achieved highest median Dice score, Jaccard score, sensitivity and precision for OC segmentation in the testing set, 0.941, 0.890, 0.973 and 0.925, respectively. Tumour volumes of manual and automated segmentations were highly correlated (rho=0.944 and rho c =0.933). 85.0% of radiomics features had high correlation with ICC >0.8. Conclusions: The presented deep-learning segmentation could provide highly accurate automated segmentation of OC on CT images with high stability of the extracted radiomics features, showing the potential as a batch-processing segmentation tool.

Ovarian cancer (OC) computed tomography deep learning automated segmentation radiomics

SCI

英语

其他

Health and Medical Research Fund, Hong Kong[08192106]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:001009890100001

AME PUBLISHING COMPANY

Web of Science

1.Univ Hong Kong, Dept Diagnost Radiol, Hong Kong, Peoples R China
2.Jinan Univ, Southern Univ Sci & Technol, Shenzhen Peoples Hosp, Affiliated Hosp 1, Shenzhen, Peoples R China
3.Pamela Youde Nethersole Eastern Hosp, Dept Radiol, Hong Kong, Peoples R China
4.Queen Mary Hosp, Dept Radiol, Hong Kong, Peoples R China
5.Sun Yat sen Univ, Dept Med Imaging, Guangdong Key Lab Nasopharyngeal Carcinoma Diag &, State Key Lab Oncol South China,Canc Ctr, Guangzhou, Peoples R China
6.Sun Yat sen Univ, State Key Lab Oncol South China, Guangdong Key Lab Nasopharyngeal Carcinoma Diag &, Canc Ctr, Guangzhou 510060, Peoples R China
7.Univ Hong Kong, Queen Mary Hosp, Dept Diagnost Radiol, Room 406, Block K,102 Pokfulam Rd, Hong Kong, Peoples R China

Wang, Yiang,Wang, Mandi,Cao, Peng,et al. CT-based deep learning segmentation of ovarian cancer and the stability of the extracted radiomics features[J]. QUANTITATIVE IMAGING IN MEDICINE AND SURGERY,2023.

Wang, Yiang.,Wang, Mandi.,Cao, Peng.,Wong, Esther M. F..,Ho, Grace.,...&Lee, Elaine Y. P..(2023).CT-based deep learning segmentation of ovarian cancer and the stability of the extracted radiomics features.QUANTITATIVE IMAGING IN MEDICINE AND SURGERY.

Wang, Yiang,et al."CT-based deep learning segmentation of ovarian cancer and the stability of the extracted radiomics features".QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (2023).