Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images

Mariana-Iuliana Georgescu
7/14/2023
eess.IVcs.CV

No official code found. Best implementation: lilygeorgescu/MAE-medical-anomaly-detection (22 stars, last commit 2023-08-15).

Abstract

Pathological anomalies exhibit diverse appearances in medical imaging, making it difficult to collect and annotate a representative amount of data required to train deep learning models in a supervised setting. Therefore, in this work, we tackle anomaly detection in medical images training our framework using only healthy samples. We propose to use the Masked Autoencoder model to learn the structure of the normal samples, then train an anomaly classifier on top of the difference between the original image and the reconstruction provided by the masked autoencoder. We train the anomaly classifier in a supervised manner using as negative samples the reconstruction of the healthy scans, while as positive samples, we use pseudo-abnormal scans obtained via our novel pseudo-abnormal module. The pseudo-abnormal module alters the reconstruction of the normal samples by changing the intensity of several regions. We conduct experiments on two medical image data sets, namely BRATS2020 and LUNA16 and compare our method with four state-of-the-art anomaly detection frameworks, namely AST, RD4AD, AnoVAEGAN and f-AnoGAN.

View on arXivView PDF

Code Implementations(1)

lilygeorgescu/MAE-medical-anomaly-detectionCommunity100%

Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images

223PythonMay 5, 20233 years agoNOASSERTION
anomaly-detectiondeep-learningmachine-learningmedical-images

Similar Papers

Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images

90% match2023

AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays

89% match2023

CRADL: Contrastive Representations for Unsupervised Anomaly Detection and Localization

89% match2023

URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection

89% match2026

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

88% match2023

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

88% match1 repo132024

Cite this paper

@article{georgescu2023masked,
  title  = {Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images},
  author = {Mariana-Iuliana Georgescu},
  year   = {2023},
  eprint = {2307.07534},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.07534v1}
}

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/2307.07534.svg)](https://codeofpaper.com/paper/2307.07534)

Discussion