Abstract
ABSTRACT
Background
Manual prescription of liver MRI volumes introduces inter‐operator variability and prolongs exam duration. Artificial intelligence (AI)‐based prescription has been demonstrated, but existing work has been limited to single‐vendor settings.
Purpose
To develop and validate an AI model for automated liver MRI prescription using a large, consecutive, multicenter dataset encompassing multiple vendors, field strengths, localizer sequences, and liver pathologies.
Study Type
Retrospective.
Population
A total of 11,012 patients (5928 female) who underwent liver MRI exams across three vendors (GE HealthCare, Philips Healthcare, Siemens Healthineers) at three institutions, split into training/validation/test sets (70/10/20%). Liver disorders included cirrhosis, ascites, portal hypertension, and iron overload.
Field Strength/Sequence
Three‐plane localizers acquired using single‐shot fast spin echo (68.3%) and gradient echo (31.7%) at 1.5 T (52.8%) and 3 T (47.2%).
Assessment
A YOLOv8 object detection model was trained to detect the liver, torso, and arms on localizer images. Automated prescription accuracy was assessed using three‐dimensional intersection‐over‐union (IoU
3D
) for axial, coronal, and sagittal prescriptions. Subgroup analyses evaluated performance across technical and patient‐related factors.
Statistical Tests
Mann–Whitney
U
tests with Bonferroni correction, Kruskal‐Wallis tests, Wilcoxon signed‐rank tests, Spearman correlation. Effect sizes were calculated using rank‐biserial correlation (
r
rb
) and epsilon‐squared (
ε
2
).
p
Results
Median axial prescription IoU
3D
was 0.963 (interquartile range: 0.946–0.976), with median IoU
3D
above 0.940 for coronal and sagittal prescriptions. For axial prescriptions, margins less than 4 mm in each direction were required to achieve complete coverage of manual prescriptions in 90% of cases in the held‐out test set. Effects were negligible to small across vendors, field strengths, localizer sequences, and patient factors (
r
rb
≤ 0.16,
ε
2
≤ 0.01).
Data Conclusion
A single multivendor model achieved accurate automated liver MRI prescription without clinically meaningful performance differences across vendors, field strengths, localizer sequences, or patient factors.
Evidence Level
2.
Technical Efficacy
Stage 1.