DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark

2026-04-25

AI Summary

This study addresses the lack of standardized datasets and evaluation benchmarks for abdominal muscle segmentation in dynamic MRI of ventral hernia patients. To this end, the authors introduce DyABD, the first benchmark dataset specifically designed for this task, featuring high-quality annotations across preoperative and postoperative scans as well as diverse motion states. The work formally defines the abdominal muscle segmentation task and incorporates motion-induced extreme anatomical variations to challenge model robustness. A systematic evaluation of state-of-the-art segmentation models is conducted under supervised, few-shot, and zero-shot settings. Experimental results show that current methods achieve a Dice score of approximately 0.82 on DyABD, indicating substantial room for improvement and establishing a foundational resource for investigating the high recurrence rates associated with ventral hernias.

Technology Category

• Computer Vision: Segmentation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Evaluation and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• abdominal muscle segmentation
• dynamic MRI
• abdominal hernia
• medical image segmentation
• anatomical variability

Innovation

• abdominal muscle segmentation
• dynamic MRI
• medical image benchmark
• few-shot segmentation
• anatomical variability