Deep learning–based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: A multicentre study
Xingyu Zhao,
Peiyi Xie,
Mengmeng Wang,
Wenru Li,
Perry J. Pickhardt,
Wei Xia,
Fei Xiong,
Rui Zhang,
Yao Xie,
Junming Jian,
Honglin Bai,
Caifang Ni,
Jinhui Gu,
Tao Yu,
Yuguo Tang,
Xin Gao,
Xiaochun Meng
Affiliations
Xingyu Zhao
University of Science and Technology of China, No.96 Jinzhai Road, Hefei, Anhui, 230026, China; Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Peiyi Xie
Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, No.26 Yuancunerheng Road, Guangzhou, Guangdong 510655, China
Mengmeng Wang
University of Science and Technology of China, No.96 Jinzhai Road, Hefei, Anhui, 230026, China; Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Wenru Li
Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, No.26 Yuancunerheng Road, Guangzhou, Guangdong 510655, China
Perry J. Pickhardt
Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, USA
Wei Xia
Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Fei Xiong
Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, No.26 Yuancunerheng Road, Guangzhou, Guangdong 510655, China
Rui Zhang
Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Yao Xie
Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, No.26 Yuancunerheng Road, Guangzhou, Guangdong 510655, China
Junming Jian
University of Science and Technology of China, No.96 Jinzhai Road, Hefei, Anhui, 230026, China; Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Honglin Bai
University of Science and Technology of China, No.96 Jinzhai Road, Hefei, Anhui, 230026, China; Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Caifang Ni
The First Affiliated Hospital of Soochow University, No. 899, Pinghai Road, Suzhou, Jiangsu 215006, China
Jinhui Gu
Chinese Academy of Traditional Chinese Medicine, No. 16, Inner South Street, Dongzhimen, Beijing 100700, China; Guiyang College of Traditional Chinese Medicine, NO.50 Shi Dong Road, Guiyang, Guizhou 550002, China; The People's Hospital of Suzhou National Hi-Tech District, 215129, China
Tao Yu
Beijing Hospital General Surgery Department, National Center of Gerontology, No. 1, Donghua Dahua Road, Beijing 100730, China
Yuguo Tang
Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China
Xin Gao
Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, No. 88, Keling Road, Suzhou, Jiangsu 215163, China; Corresponding authors.
Xiaochun Meng
Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, No.26 Yuancunerheng Road, Guangzhou, Guangdong 510655, China; Corresponding authors.
Background: Accurate lymph nodes (LNs) assessment is important for rectal cancer (RC) staging in multiparametric magnetic resonance imaging (mpMRI). However, it is incredibly time-consumming to identify all the LNs in scan region. This study aims to develop and validate a deep-learning-based, fully-automated lymph node detection and segmentation (auto-LNDS) model based on mpMRI. Methods: In total, 5789 annotated LNs (diameter ≥ 3 mm) in mpMRI from 293 patients with RC in a single center were enrolled. Fused T2-weighted images (T2WI) and diffusion-weighted images (DWI) provided input for the deep learning framework Mask R-CNN through transfer learning to generate the auto-LNDS model. The model was then validated both on the internal and external datasets consisting of 935 LNs and 1198 LNs, respectively. The performance for LNs detection was evaluated using sensitivity, positive predictive value (PPV), and false positive rate per case (FP/vol), and segmentation performance was evaluated using the Dice similarity coefficient (DSC). Findings: For LNs detection, auto-LNDS achieved sensitivity, PPV, and FP/vol of 80.0%, 73.5% and 8.6 in internal testing, and 62.6%, 64.5%, and 8.2 in external testing, respectively, significantly better than the performance of junior radiologists. The time taken for model detection and segmentation was 1.3 s/case, compared with 200 s/case for the radiologists. For LNs segmentation, the DSC of the model was in the range of 0.81–0.82. Interpretation: This deep learning–based auto-LNDS model can achieve pelvic LNseffectively based on mpMRI for RC, and holds great potential for facilitating N-staging in clinical practice.
