ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rays

TL;DR

ART-ASyn is a novel framework that synthesizes realistic, anatomically consistent anomalies in chest X-rays, improving unsupervised anomaly detection and segmentation, especially for unseen datasets.

Contribution

It introduces a texture-based augmentation guided by a new lung segmentation method, enabling realistic anomaly synthesis and zero-shot generalization.

Findings

Synthesizes anatomically consistent anomalies

Enables explicit pixel-level supervision

Demonstrates zero-shot anomaly segmentation

Abstract

Unsupervised anomaly detection aims to identify anomalies without pixel-level annotations. Synthetic anomaly-based methods exhibit a unique capacity to introduce controllable irregularities with known masks, enabling explicit supervision during training. However, existing methods often produce synthetic anomalies that are visually distinct from real pathological patterns and ignore anatomical structure. This paper presents a novel Anatomy-aware Realistic Texture-based Anomaly Synthesis framework (ART-ASyn) for chest X-rays that generates realistic and anatomically consistent lung opacity related anomalies using texture-based augmentation guided by our proposed Progressive Binary Thresholding Segmentation method (PBTSeg) for lung segmentation. The generated paired samples of synthetic anomalies and their corresponding precise pixel-level anomaly mask for each normal sample enable explicit segmentation supervision. In contrast to prior work limited to one-class classification, ART-ASyn is further evaluated for zero-shot anomaly segmentation, demonstrating generalizability on an unseen dataset without target-domain annotations. Code availability is available at https://github.com/angelacao-hub/ART-ASyn.