Artificial intelligence-driven three-dimensional modeling of biliary strictures using magnetic resonance cholangiopancreatography for quantitative assessment and stent planning
World Journal of Gastroenterology · 2027-01-14 · 33 (2)
DOI: 10.3748/wjg.125661 ↗Abstract
BACKGROUND Magnetic resonance cholangiopancreatography (MRCP) depicts the biliary tree three-dimensionally but is used mainly for qualitative diagnosis rather than quantitative procedural planning. Endoscopic drainage of biliary strictures, particularly hilar and intrahepatic lesions, depends on an accurate understanding of stricture location, length, ductal curvature, and branch involvement, yet MRCP information is seldom converted into reproducible measurements. Artificial intelligence (AI) may bridge this gap by transforming diagnostic imaging into quantitative, procedure-oriented geometry. We hypothesized that MRCP-derived biliary anatomy could be converted into an interpretable three-dimensional (3D) model supporting biliary stricture assessment and candidate stent-planning geometry. AIM To develop and evaluate a proof-of-concept AI workflow that converts MRCP-derived biliary anatomy into a quantitative 3D stricture model. METHODS This single-center study analyzed 384 MRCP examinations (242 controls and 142 with suspected biliary stricture). Expert-corrected masks and 3D annotations were used to train or evaluate modules for region-of-interest localization, bile duct segmentation, projection-based multi-view classification, synthetic morphology restoration, and centerline-guided tubular mesh generation. Binary stricture detection and three-class severity classification were assessed with patient-level cross-validation after excluding unavailable or task-incompatible labels. Segmentation and restoration were evaluated using Dice scores. RESULTS In 380 evaluable cases, projection-based binary classification achieved an accuracy of 0.9770, balanced accuracy of 0.9721, macro F1 score of 0.9749, and receiver operating characteristic area under the curve of 0.9953. Three-class severity classification was less accurate (accuracy 0.8711), indicating that severity stratification is more difficult than binary detection. The best Dice score was 0.8113 in the segmentation comparison and 0.8944 in the extended normal-group experiment. In synthetic restoration, DiceFocalLoss produced the highest Dice score (0.7531), and lesion weighting improved reconstruction of interrupted duct segments. In anatomically simple cases, restored geometry was converted into a centerline-guided tubular mesh, whereas complex hilar or intrahepatic branching remained vulnerable to projection overlap. CONCLUSION MRCP-based AI modeling of biliary strictures is feasible for quantitative 3D assessment and exploratory stent-planning geometry. External validation and prospective clinical evaluation are required before procedural implementation.
EUVIMED