Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images

Tiange Xiang, Yixiao Zhang, Yongyi Lu, Alan Yuille, Chaoyi Zhang +2 more
3/13/2024
eess.IVcs.CV

Official code: MrGiovanni/SimSID (25 stars, last commit 2024-07-30).

Abstract

Radiography imaging protocols focus on particular body regions, therefore producing images of great similarity and yielding recurrent anatomical structures across patients. Exploiting this structured information could potentially ease the detection of anomalies from radiography images. To this end, we propose a Simple Space-Aware Memory Matrix for In-painting and Detecting anomalies from radiography images (abbreviated as SimSID). We formulate anomaly detection as an image reconstruction task, consisting of a space-aware memory matrix and an in-painting block in the feature space. During the training, SimSID can taxonomize the ingrained anatomical structures into recurrent visual patterns, and in the inference, it can identify anomalies (unseen/modified visual patterns) from the test image. Our SimSID surpasses the state of the arts in unsupervised anomaly detection by +8.0%, +5.0%, and +9.9% AUC scores on ZhangLab, COVIDx, and CheXpert benchmark datasets, respectively. Code: https://github.com/MrGiovanni/SimSID

View on arXivView PDF

Code Implementations(1)

MrGiovanni/SimSIDOfficial100%

[IEEE TPAMI] Anomaly Detection in Chest X-ray

252PythonMar 12, 20242 years agoNOASSERTION

Similar Papers

Unsupervised Patch-GAN with Targeted Patch Ranking for Fine-Grained Novelty Detection in Medical Imaging

87% match2025

MCDDPM: Multichannel Conditional Denoising Diffusion Model for Unsupervised Anomaly Detection in Brain MRI

86% match1 repo112024

Spatial-aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image

86% match1 repo132024

MedIAnomaly: A comparative study of anomaly detection in medical images

86% match1 repo862024

Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images

86% match1 repo132024

MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images

85% match1 repo222024

Cite this paper

@article{xiang2024exploiting,
  title  = {Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images},
  author = {Tiange Xiang and Yixiao Zhang and Yongyi Lu and Alan Yuille and Chaoyi Zhang and Weidong Cai and Zongwei Zhou},
  year   = {2024},
  eprint = {2403.08689},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.08689v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.08689.svg)](https://codeofpaper.com/paper/2403.08689)

Discussion