Large-scale AI-guided liver malignancy diagnosis: multicenter study and a single-arm trial.
Authors
Affiliations (28)
Affiliations (28)
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China.
- DAMO Academy, Alibaba Group, Hangzhou, China.
- EURECOM, Sophia Antipolis, France.
- Faculty of Science and Engineering, Sorbonne University, Paris, France.
- Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
- State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, China.
- South China Hospital, Medical School, Shenzhen University, Shenzhen, China.
- Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China.
- Department of Radiology, The Second Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou, China.
- Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Department of Radiology, Yantai Yuhuangding Hospital, Yantai, China.
- Hupan Laboratory, Hangzhou, China.
- Department of Radiology, Chengdu Sixth People's Hospital, Chengdu, China.
- Department of Ultrasound Medicine, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
- Université Côte D'Azur, INSERM, CNRS, iBV, Nice, France.
- Department of Nuclear Medicine, Centre Antoine Lacassagne, Nice, France.
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK. [email protected].
- EURECOM, Sophia Antipolis, France. [email protected].
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK. [email protected].
- DAMO Academy, Alibaba Group, Hangzhou, China. [email protected].
- Hupan Laboratory, Hangzhou, China. [email protected].
- Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. [email protected].
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China. [email protected].
- Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. [email protected].
- DAMO Academy, Alibaba Group, Washington DC, USA. [email protected].
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China. [email protected].
- Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. [email protected].
Abstract
Liver malignancies are frequently evaluated on contrast-enhanced computed tomography (CE-CT), but missed or delayed diagnoses remain a clinically important challenge in high-volume, real-world radiology workflows, highlighting the need for scalable diagnostic safety net approaches. To address this, we developed the Liver DiagnOsis Network (LiON), a CE-CT-based artificial intelligence (AI) system that supports flexible multiphase processing, clinical data integration and workflow-compatible liver malignancy diagnosis. LiON was trained on 6,443 patients and retrospectively validated across 22,251 patients from multicenter and real-world cohorts. LiON achieved high performance for malignancy diagnosis, with an area under the receiver operating characteristic curve (AUC) of 0.975 (95% confidence interval (CI): 0.971-0.979), and maintained robust performance in real-world cohorts and among patients with hepatic steatosis (AUC 0.971, 95% CI: 0.952-0.985) and cirrhosis (AUC 0.924, 95% CI: 0.901-0.946). We then conducted a single-arm trial in 10,333 patients in routine clinical practice, in which LiON functioned as an additional AI reader within the existing clinical workflow. The trial met its primary endpoint, defined as an AUC for malignancy diagnosis with the lower bound of the 95% CI exceeding 0.900, achieving an AUC of 0.952 (95% CI: 0.942-0.961). Secondary outcomes demonstrated that AI-human collaboration identified 51 previously overlooked lesions (15 malignancies) and triggered 37 amended radiology reports, 22 multidisciplinary team escalations and clinical management changes in a subset of patients. These findings suggest that AI, when deployed as a workflow-compatible diagnostic support, may help reduce missed or delayed diagnoses and guide clinical interventions. Nevertheless, further evidence from prospective comparative studies across diverse healthcare systems is warranted to assess effects on clinical outcomes. ClinicalTrials.gov identifier: NCT07153783 .