Learning Anatomically Consistent Embedding for Chest Radiography

TL;DR

This paper introduces PEAC, a self-supervised learning method that leverages anatomical consistency in chest radiography to improve representation learning, outperforming existing methods and enhancing interpretability across diverse patient views and conditions.

Contribution

PEAC is a novel SSL approach that exploits anatomical consistency in medical images, demonstrating superior performance and interpretability in chest radiography analysis.

Findings

PEAC outperforms state-of-the-art SSL methods.

PEAC captures anatomical structure consistency across views and patients.

PEAC enhances interpretability in medical image analysis.

Abstract

Self-supervised learning (SSL) approaches have recently shown substantial success in learning visual representations from unannotated images. Compared with photographic images, medical images acquired with the same imaging protocol exhibit high consistency in anatomy. To exploit this anatomical consistency, this paper introduces a novel SSL approach, called PEAC (patch embedding of anatomical consistency), for medical image analysis. Specifically, in this paper, we propose to learn global and local consistencies via stable grid-based matching, transfer pre-trained PEAC models to diverse downstream tasks, and extensively demonstrate that (1) PEAC achieves significantly better performance than the existing state-of-the-art fully/self-supervised methods, and (2) PEAC captures the anatomical structure consistency across views of the same patient and across patients of different genders, weights, and healthy statuses, which enhances the interpretability of our method for medical image analysis.