Deep learning-enabled pelvic ultrasound images for accurate diagnosis of ovarian cancer in China: a retrospective, multicentre, diagnostic study
Yue Gao, Shaoqing Zeng, Xiaoyan Xu, Huayi Li, Shuzhong Yao, Kun Song, Xiao Li, Lingxi Chen, Junying Tang, Hui Xing, Zhiying Yu, Qinghua Zhang, Shue Zeng, Cunjian Yi, Hongning Xie, Xiaoming Xiong, Guangyao Cai, Zhi Wang, Yuan Wu, Jianhua Chi, Xiaofei Jiao, Yan Qin, Xiaogang Mao, Yu Chen, Xin Jin, Qingqing Mo, Pingbo Chen, Yi Huang, Yushuang Shi, Junmei Wang, Yimin Zhou, Shuping Ding, Shan Zhu, Xin Liu, Xiangyi Dong, Lin Cheng, Linlin Zhu, Huanhuan Cheng, Li Cha, Yanli Hao, Chunchun Jin, Ludan Zhang, Peng Zhou, Meng Sun, Qin Xu, Kehua Chen, Zeyan Gao, Xu Zhang, Yuanyuan Ma, Yan Liu, Liling Xiao, Li Xu, Lin Peng, Zheyu Hao, Mi Yang, Yane Wang, Hongping Ou, Yongmei Jia, Lihua Tian, Wei Zhang, Ping Jin, Xun Tian, Lei Huang, Zhen Wang, Jiahao Liu, Tian Fang, Danmei Yan, Heng Cao, Jingjing Ma, Xiaoting Li, Xu Zheng, Hua Lou, Chunyan Song, Ruyuan Li, Siyuan Wang, Wenqian Li, Xulei Zheng, Jing Chen, Guannan Li, Ruqi Chen, Cheng Xu, Ruidi Yu, Ji Wang, Sen Xu, Beihua Kong, Xing Xie, Ding Ma, Qinglei Gao, Yue Gao, Shaoqing Zeng, Xiaoyan Xu, Huayi Li, Shuzhong Yao, Kun Song, Xiao Li, Lingxi Chen, Junying Tang, Hui Xing, Zhiying Yu, Qinghua Zhang, Shue Zeng, Cunjian Yi, Hongning Xie, Xiaoming Xiong, Guangyao Cai, Zhi Wang, Yuan Wu, Jianhua Chi, Xiaofei Jiao, Yan Qin, Xiaogang Mao, Yu Chen, Xin Jin, Qingqing Mo, Pingbo Chen, Yi Huang, Yushuang Shi, Junmei Wang, Yimin Zhou, Shuping Ding, Shan Zhu, Xin Liu, Xiangyi Dong, Lin Cheng, Linlin Zhu, Huanhuan Cheng, Li Cha, Yanli Hao, Chunchun Jin, Ludan Zhang, Peng Zhou, Meng Sun, Qin Xu, Kehua Chen, Zeyan Gao, Xu Zhang, Yuanyuan Ma, Yan Liu, Liling Xiao, Li Xu, Lin Peng, Zheyu Hao, Mi Yang, Yane Wang, Hongping Ou, Yongmei Jia, Lihua Tian, Wei Zhang, Ping Jin, Xun Tian, Lei Huang, Zhen Wang, Jiahao Liu, Tian Fang, Danmei Yan, Heng Cao, Jingjing Ma, Xiaoting Li, Xu Zheng, Hua Lou, Chunyan Song, Ruyuan Li, Siyuan Wang, Wenqian Li, Xulei Zheng, Jing Chen, Guannan Li, Ruqi Chen, Cheng Xu, Ruidi Yu, Ji Wang, Sen Xu, Beihua Kong, Xing Xie, Ding Ma, Qinglei Gao
Abstract
Background: Ultrasound is a critical non-invasive test for preoperative diagnosis of ovarian cancer. Deep learning is making advances in image-recognition tasks; therefore, we aimed to develop a deep convolutional neural network (DCNN) model that automates evaluation of ultrasound images and to facilitate a more accurate diagnosis of ovarian cancer than existing methods.
Methods: In this retrospective, multicentre, diagnostic study, we collected pelvic ultrasound images from ten hospitals across China between September 2003, and May 2019. We included consecutive adult patients (aged ≥18 years) with adnexal lesions in ultrasonography and healthy controls and excluded duplicated cases and patients without adnexa or pathological diagnosis. For DCNN model development, patients were assigned to the training dataset (34 488 images of 3755 patients with ovarian cancer, 541 442 images of 101 777 controls). For model validation, patients were assigned to the internal validation dataset (3031 images of 266 patients with ovarian cancer, 5385 images of 602 with benign adnexal lesions), external validation datasets 1 (486 images of 67 with ovarian cancer, 933 images of 268 with benign adnexal lesions), and 2 (1253 images of 166 with ovarian cancer, 5257 images of 723 benign adnexal lesions). Using these datasets, we assessed the diagnostic value of DCNN, compared DCNN with 35 radiologists, and explored whether DCNN could augment the diagnostic accuracy of six radiologists. Pathological diagnosis was the reference standard.
Findings: For DCNN to detect ovarian cancer, AUC was 0·911 (95% CI 0·886-0·936) in the internal dataset, 0·870 (95% CI 0·822-0·918) in external validation dataset 1, and 0·831 (95% CI 0·793-0·869) in external validation dataset 2. The DCNN model was more accurate than radiologists at detecting ovarian cancer in the internal dataset (88·8% vs 85·7%) and external validation dataset 1 (86·9% vs 81·1%). Accuracy and sensitivity of diagnosis increased more after DCNN-assisted diagnosis than assessment by radiologists alone (87·6% [85·0-90·2] vs 78·3% [72·1-84·5], p<0·0001; 82·7% [78·5-86·9] vs 70·4% [59·1-81·7], p<0·0001). The average accuracy of DCNN-assisted evaluations for six radiologists reached 0·876 and were significantly augmented when they were DCNN-assisted (p<0·05).
Interpretation: The performance of DCNN-enabled ultrasound exceeded the average diagnostic level of radiologists matched the level of expert ultrasound image readers, and augmented radiologists' accuracy. However, these observations warrant further investigations in prospective studies or randomised clinical trials.
Funding: National Key Basic Research Program of China, National Sci-Tech Support Projects, and National Natural Science Foundation of China.
Conflict of interest statement
Declaration of interests QLG will apply for a patent for the DCNN model used in this study pending to Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology. All other authors declare no competing interests.
Copyright © 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.
Source: PubMed