Meiyun Wang1, Fangfang Fu1, Bingjie Zheng2, Yan Bai1, Qingxia Wu1, Jianqiang Wu3, Lin Sun4, Qiuyu Liu5, Mingge Liu6, Yichen Yang7, Hongru Shen7, Dalu Kong8, Xiaoyue Ma9, Peiting You10, Xiangchun Li11, Fei Tian12. 1. Department of Radiology, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University, Zhengzhou, China. 2. Department of Radiology, Henan Provincial Cancer Hospital, Affiliated Cancer Hospital of Zhengzhou University, Zhengzhou, China. 3. Department of Radiology, Dengfeng People's Hospital, Zhengzhou, China. 4. Department of Pathology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Tianjin, China. 5. Department of Pathology, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University, Zhengzhou, China. 6. Department of Pathology, Henan Provincial Cancer Hospital, Affiliated Cancer Hospital of Zhengzhou University, Zhengzhou, China. 7. Department of Epidemiology and Biostatistics, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China. 8. Department of Abdominal Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China. 9. Department of Magnetic Resonance, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China. 10. School of Mathematical Science, Peking University, Beijing, China. 11. Department of Epidemiology and Biostatistics, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China. lixiangchun@tmu.edu.cn. 12. Department of Abdominal Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, China. tianfei@tmu.edu.cn.
Abstract
BACKGROUND AND AIMS: Computed tomography (CT) scan is frequently used to detect hepatocellular carcinoma (HCC) in routine clinical practice. The aim of this study is to develop a deep-learning AI system to improve the diagnostic accuracy of HCC by analysing liver CT imaging data. METHODS: We developed a deep-learning AI system by training on CT images from 7512 patients at Henan Provincial Peoples' Hospital. Its performance was validated on one internal test set (Henan Provincial Peoples' Hospital, n = 385) and one external test set (Henan Provincial Cancer Hospital, n = 556). The area under the receiver-operating characteristic curve (AUROC) was used as the primary classification metric. Accuracy, sensitivity, specificity, precision, negative predictive value and F1 metric were used to measure the performance of AI systems and radiologists. RESULTS: AI system achieved high performance in identifying HCC patients, with AUROC of 0.887 (95% CI 0.855-0.919) on the internal test set and 0.883 (95% CI 0.855-0.911) on the external test set. For internal test set, accuracy was 81.0% (76.8-84.8%), sensitivity was 78.4% (72.4-83.7%), specificity was 84.4% (78.0-89.6%) and F1 (harmonic average of precision and recall rate) was 0.824. For external test set, accuracy was 81.3% (77.8-84.5%), sensitivity was 89.4% (85.0-92.8%), specificity was 74.0% (68.5-78.9%) and F1 was 0.819. Compared with radiologists, AI system achieved comparable accuracy and F1 metric on internal test set (0.853 versus 0.818, P = 0.107; 0.863 vs. 0.824, P = 0.082) and external test set (0.805 vs. 0.793, P = 0.663; 0.810 vs. 0.814, P = 0.866). The predicted HCC risk scores by AI system in HCC patients with multiple tumours and high fibrosis stage were higher than those with solitary tumour and low fibrosis stage (tumour number: 0.197 vs. 0.138, P = 0.006; fibrosis stage: 0.183 vs. 0.127, P < 0.001). Radiologists' review showed that the accuracy of saliency heatmaps predicted by algorithms was 92.1% (95% CI: 89.2-95.0%). CONCLUSIONS: AI system achieved high performance in the detection of HCC compared with a group of specialised radiologists. Further investigation by prospective clinical trials was necessitated to verify this model.
BACKGROUND AND AIMS: Computed tomography (CT) scan is frequently used to detect hepatocellular carcinoma (HCC) in routine clinical practice. The aim of this study is to develop a deep-learning AI system to improve the diagnostic accuracy of HCC by analysing liver CT imaging data. METHODS: We developed a deep-learning AI system by training on CT images from 7512 patients at Henan Provincial Peoples' Hospital. Its performance was validated on one internal test set (Henan Provincial Peoples' Hospital, n = 385) and one external test set (Henan Provincial Cancer Hospital, n = 556). The area under the receiver-operating characteristic curve (AUROC) was used as the primary classification metric. Accuracy, sensitivity, specificity, precision, negative predictive value and F1 metric were used to measure the performance of AI systems and radiologists. RESULTS: AI system achieved high performance in identifying HCC patients, with AUROC of 0.887 (95% CI 0.855-0.919) on the internal test set and 0.883 (95% CI 0.855-0.911) on the external test set. For internal test set, accuracy was 81.0% (76.8-84.8%), sensitivity was 78.4% (72.4-83.7%), specificity was 84.4% (78.0-89.6%) and F1 (harmonic average of precision and recall rate) was 0.824. For external test set, accuracy was 81.3% (77.8-84.5%), sensitivity was 89.4% (85.0-92.8%), specificity was 74.0% (68.5-78.9%) and F1 was 0.819. Compared with radiologists, AI system achieved comparable accuracy and F1 metric on internal test set (0.853 versus 0.818, P = 0.107; 0.863 vs. 0.824, P = 0.082) and external test set (0.805 vs. 0.793, P = 0.663; 0.810 vs. 0.814, P = 0.866). The predicted HCC risk scores by AI system in HCC patients with multiple tumours and high fibrosis stage were higher than those with solitary tumour and low fibrosis stage (tumour number: 0.197 vs. 0.138, P = 0.006; fibrosis stage: 0.183 vs. 0.127, P < 0.001). Radiologists' review showed that the accuracy of saliency heatmaps predicted by algorithms was 92.1% (95% CI: 89.2-95.0%). CONCLUSIONS: AI system achieved high performance in the detection of HCC compared with a group of specialised radiologists. Further investigation by prospective clinical trials was necessitated to verify this model.
Authors: Masao Omata; Laurentius A Lesmana; Ryosuke Tateishi; Pei-Jer Chen; Shi-Ming Lin; Haruhiko Yoshida; Masatoshi Kudo; Jeong Min Lee; Byung Ihn Choi; Ronnie T P Poon; Shuichiro Shiina; Ann Lii Cheng; Ji-Dong Jia; Shuntaro Obi; Kwang Hyub Han; Wasim Jafri; Pierce Chow; Seng Gee Lim; Yogesh K Chawla; Unggul Budihusodo; Rino A Gani; C Rinaldi Lesmana; Terawan Agus Putranto; Yun Fan Liaw; Shiv Kumar Sarin Journal: Hepatol Int Date: 2010-03-18 Impact factor: 6.047
Authors: Freddie Bray; Jacques Ferlay; Isabelle Soerjomataram; Rebecca L Siegel; Lindsey A Torre; Ahmedin Jemal Journal: CA Cancer J Clin Date: 2018-09-12 Impact factor: 508.702
Authors: Vo Tan Duc; Phan Cong Chien; Le Duy Mai Huyen; Tran Le Minh Chau; Nguyen Do Trung Chanh; Duong Thi Minh Soan; Hoang Cao Huyen; Huynh Minh Thanh; Le Nguyen Gia Hy; Nguyen Hoang Nam; Mai Thi Tu Uyen; Le Huu Hanh Nhi; Le Huu Nhat Minh Journal: Cureus Date: 2022-01-17