AI-Based 3D Liver Segmentation and Volumetric Analysis in Living Donor Data.

Abstract

This study investigated the application of deep learning for 3-dimensional (3D) liver segmentation and volumetric analysis in living donor liver transplantation. Using abdominal computed tomography data from 55 donors, this study aimed to evaluate the liver segmentation performance of various U-Net-based models, including 3D U-Net, RU-Net, DU-Net, and RDU-Net, before and after hepatectomy. Accurate liver volume measurement is critical in liver transplantation to ensure adequate functional recovery and minimize postoperative complications. The models were trained and validated using a fivefold cross-validation approach. Performance metrics such as Dice similarity coefficient (DSC), recall, specificity, precision, and accuracy were used to assess the segmentation results. The highest segmentation accuracy was achieved in preoperative images with a DSC of 95.73 ± 1.08%, while postoperative day 7 images showed the lowest performance with a DSC of 93.14 ± 2.10%. A volumetric analysis conducted to measure hepatic resection and regeneration rates revealed an average liver resection rate of 40.52 ± 8.89% and a regeneration rate of 13.50 ± 8.95% by postoperative day 63. A regression analysis was performed on the volumetric results of the artificial intelligence model's liver resection rate and regeneration rate, and all results were statistically significant at p < 0.0001. The results indicate high reliability and clinical applicability of deep learning models in accurately measuring liver volume and assessing regenerative capacity, thus enhancing the management and recovery of liver donors.