DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark

arXiv cs.CV / 4/28/2026

📰 NewsSignals & Early TrendsModels & Research

共有:

Key Points

DyABD is a new benchmark dataset for abdominal muscle segmentation, featuring dynamic abdominal MRI data from patients with abdominal hernias alongside high-quality muscle annotations.
The dataset is designed to be exceptionally challenging because the MRIs are captured while patients perform exercises, producing extreme anatomical variability and including both pre- and post-corrective scans.
DyABD evaluates how well existing medical image segmentation models generalize to the unseen dataset under Supervised, Few Shot, and Zero Shot learning settings.
The study finds that most current approaches still reach only around a Dice Coefficient of 0.82, indicating substantial remaining room for improvement in medical image segmentation.
Beyond segmentation accuracy, the dataset is intended to support clinical research related to the high recurrence rates of abdominal hernias.

Abstract

This work introduces DyABD, a novel and complex benchmark dataset of dynamic abdominal MRIs from patients with abdominal hernias and associated high quality abdominal muscle annotations. DyABD is the first-of-its-kind in four key ways; (1) it proposes the first abdominal muscle segmentation task, (2) the dynamic MRIs are acquired whilst the patients perform various exercises, introducing extreme anatomical variability, making it one of the most challenging segmentation datasets to date, (3) it includes both pre and post corrective MRIs and (4) DyABD promotes clinical research into the high recurrence rates of abdominal hernias. Beyond dataset introduction, this work provides a comprehensive evaluation of the generalisation capabilities of existing segmentation models across Supervised, Few Shot and Zero Shot paradigms on the unseen DyABD dataset. This work reveals that there is still room for substantial improvement in the field of medical image segmentation, with the majority of techniques achieving a Dice Coefficient of 0.82. This work therefore sheds light on the true progress of the field and redefines the benchmark for progress in medical image segmentation.