Pragmatic RCT of AI-Assisted Reading for Malignant Hepatic Lesions on CE-CT

A Multicenter Randomized Controlled Trial of AI-Assisted Reading Compared With Standard Radiology Interpretation for Malignant Hepatic Lesions on Contrast-Enhanced CT: Diagnostic, Clinical and Workflow Outcomes

The purpose of this multicenter pragmatic randomized controlled trial is to determine whether AI-assisted interpretation of multiphasic liver contrast-enhanced computed tomography (CE-CT) is non-inferior to standard radiology reporting with respect to missed clinically significant malignant focal liver lesions, **with the non-inferiority margin prespecified in the statistical analysis plan before enrollment**, and whether it improves lesion detection, diagnostic characterization, downstream clinical management, and reporting efficiency. On AI-assisted center-days, AI results will be revealed only after the first-line radiologist has saved an unaided initial assessment and may be used to revise the final report. On control center-days, examinations will be interpreted using the standard radiology workflow without access to AI tools.

Inclusion Criteria:

1. Age range 18 years and above
2. Underwent dynamic contrast-enhanced abdominal CT examination with liver coverage
3. Imaging must include at least three required phases: non-contrast, arterial phase, and venous phase; a delayed phase is optional
4. Complete imaging data that meet AI system and radiologist interpretation requirements.

Exclusion Criteria:

1. History of recent upper-abdominal surgery (within 30 days) or major hepatobiliary-pancreatic surgery affecting liver evaluation (e.g., liver transplantation or Whipple procedure); patients with prior simple cholecystectomy or single-lesion interventional procedures are not excluded
2. History of recent hepatic trauma (within 30 days)
3. Poor image quality or severe noise artifacts (e.g., metal or motion artifacts)
4. Missing required imaging phases (required at least non-contrast, arterial, and venous phases) or inadequate scan range (e.g., lower-abdomen CT such as pelvic or rectal scans not covering the liver)