Assessing the performance of AI‐assisted technicians in liver segmentation, Couinaud division, and lesion detection: a pilot study

An AI-assisted workflow allowed non-radiologists to perform liver delineation, Couinaud segmentation, and lesion detection on MRI with accuracy comparable to radiologists, reducing workload. Agreement on whole-liver volume and segment measurements was high, and all lesions identified by radiologists were found; non-radiologists also flagged additional lesions confirmed by external adjudicator radiologists.