Anatomy-aware Representation Learning for Medical Ultrasound
Seok-Hwan Oh, Myeong-Gee Kim, Guil Jung, hyeonjik lee, Young-Min Kim, Sang-yun Kim, Hyuksool Kwon, Hyeonmin Bae
Abstract
Diagnostic accuracy of ultrasound imaging is limited by qualitative variability and its reliance on the expertise of medical professionals. Such challenges increase demand for computer-aided diagnostic systems that enhance diagnostic accuracy and efficiency. However, the unique texture and structural attributes of ultrasound images, and the scarcity of large-scale ultrasound datasets hinder the effective application of conventional machine learning methodologies. To address the challenges, we propose Anatomy-aware Representation Learning (ARL), a novel self-supervised representation learning framework specifically designed for medical ultrasound imaging. ARL incorporates an anatomy-adaptive Vision Transformer (A-ViT). The A-ViT is parameterized, using the proposed large-scale medical ultrasound dataset, to provide anatomy-aware feature representations. Through extensive experiments across various ultrasound-based diagnostic tasks, including breast and thyroid cancer, cardiac view classification, and gallbladder tumor and COVID-19 identification, we demonstrate that ARL significantly outperforms existing self-supervised learning baselines. The experiments demonstrate the potential of ARL in advancing medical ultrasound diagnostics by providing anatomy-specific feature representation
BibTeX
@inproceedings{
oh2026anatomyaware,
title={Anatomy-aware Representation Learning for Medical Ultrasound},
author={Seok-Hwan Oh and Myeong-Gee Kim and Guil Jung and hyeonjik lee and Young-Min Kim and Sang-yun Kim and Hyuksool Kwon and Hyeonmin Bae},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=5ThIWuDkEf}
}