Hanning Ying, Xiaoqing Liu, Min Zhang, Yiyue Ren, Shihui Zhen, Xiaojie Wang, Bo Liu, Peng Hu, Lian Duan, Mingzhi Cai, Ming Jiang, Xiangdong Cheng, Xiangyang Gong, Haitao Jiang, Jianshuai Jiang, Jianjun Zheng, Kelei Zhu, Wei Zhou, Baochun Lu, Hongkun Zhou, Yiyu Shen, Jinlin Du, Mingliang Ying, Qiang Hong, Jingang Mo, Jianfeng Li, Guanxiong Ye, Shizheng Zhang, Hongjie Hu, Jihong Sun, Hui Liu, Yiming Li, Xingxin Xu, Huiping Bai, Shuxin Wang, Xin Cheng, Xiaoyin Xu, Long Jiao, Risheng Yu, Wan Yee Lau, Yizhou Yu, and Xiujun Cai
Abstract Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists’ F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.