ADFA: Attention-augmented Differentiable top-k Feature Adaptation for Unsupervised Medical Anomaly Detection

Yiming Huang, Guole Liu, Yaoru Luo, Ge Yang
8/29/2023
cs.CV

No official code found. Best implementation: cbmi-group/ADFA (3 stars, last commit 2023-03-30).

Abstract

The scarcity of annotated data, particularly for rare diseases, limits the variability of training data and the range of detectable lesions, presenting a significant challenge for supervised anomaly detection in medical imaging. To solve this problem, we propose a novel unsupervised method for medical image anomaly detection: Attention-Augmented Differentiable top-k Feature Adaptation (ADFA). The method utilizes Wide-ResNet50-2 (WR50) network pre-trained on ImageNet to extract initial feature representations. To reduce the channel dimensionality while preserving relevant channel information, we employ an attention-augmented patch descriptor on the extracted features. We then apply differentiable top-k feature adaptation to train the patch descriptor, mapping the extracted feature representations to a new vector space, enabling effective detection of anomalies. Experiments show that ADFA outperforms state-of-the-art (SOTA) methods on multiple challenging medical image datasets, confirming its effectiveness in medical anomaly detection.

View on arXivView PDF

Code Implementations(1)

cbmi-group/ADFACommunity100%
30PythonFeb 22, 20233 years ago

Similar Papers

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

87% match1 repo222024

Achieving state-of-the-art performance in the Medical Out-of-Distribution (MOOD) challenge using plausible synthetic anomalies

86% match2023

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

85% match1 repo252024

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

85% match1 repo132024

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

85% match2025

UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection

85% match1 repo162023

Cite this paper

@article{huang2023adfa,
  title  = {ADFA: Attention-augmented Differentiable top-k Feature Adaptation for Unsupervised Medical Anomaly Detection},
  author = {Yiming Huang and Guole Liu and Yaoru Luo and Ge Yang},
  year   = {2023},
  eprint = {2308.15280},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.15280v1}
}

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/2308.15280.svg)](https://codeofpaper.com/paper/2308.15280)

Discussion