Large-scale AI-guided liver maligancy diagnosis: multicenter study and a single-arm trial

Liver malignancies are frequently evaluated on cotrast-enhanced computed tomography (CT-CE), but missed or delayed diagnoses remain an important challenge. A multinational research group developed LiON (‘liver diagnosis network’), a CT-CE based artificial intelligence (AI) system that supports flexible multiphase processing, clinical data integration, and workflow-compatible liver malignancy diagnosis. LiON was trained on 6443 patients and retrospectively validated across 22,251 patients from real-world cohorts, and achieved high performance for malignancy diagnosis (AUC 0.975; 95% CI 0.971-0.979) and maintained robust performance in real-world cohorts and among patients with hepatic steatosis (0.971; 0.952-0.985) and cirrhosis (0.924; 0.901-0.946). The authors 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 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. The author conclude that these findings suggest that AI, when deployed as a workflow-compatible diagnostic support, may help reduce missed or delayed diagnoses. Further evidence from prospective studies is warranted.