Comparison of publicly available artificial intelligence models for pancreatic segmentation on T1-weighted Dixon images.

ABSTRACT:

Purpose

This study aimed to compare three publicly available deep learning models (TotalSegmentator, TotalVibeSegmentator, and PanSegNet) for automated pancreatic segmentation on magnetic resonance images and to evaluate their performance against human annotations in terms of segmentation accuracy, volumetric measurement, and intrapancreatic fat fraction (IPFF) assessment.

Materials and methods

Twenty upper abdominal T1-weighted magnetic resonance series acquired using the two-point Dixon method were randomly selected. Three radiologists manually segmented the pancreas, and a ground-truth mask was constructed through a majority vote per voxel. Pancreatic segmentation was also performed using the three artificial intelligence models. Performance was evaluated using the Dice s

SUBMITTER: Sonoda Y 

PROVIDER: S-EPMC12479682 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature