Awesome Anomaly Detection in Medical Images

A curated list of awesome anomaly detection works in medical imaging, inspired by the other awesome-* initiatives.

For a complete list of anomaly detection in general computer vision, please visit awesome anomaly detection.

--- Last updated: Jan. 9, 2021 ---

To complement or correct it, please contact me at zhoukang [at] shanghaitech [dot] edu [dot] cn or send a pull request.

Overview

• Deep learning based methods
  • Brain MRI
  • Brain CT
  • Retinal OCT
  • Retinal fundus
  • Chest X-Ray in CT
  • Other modalities
• Non-deep learning based methods
  • Brain MRI
• Some works that related to anomaly detection
• Not yet public (MICCAI 2020)

Deep learning based methods

Brain MRI

• [Alex et. al.] [Generative adversarial networks for brain lesion detection] [Medical Imaging 2017: Image Processing] [google scholar] [pdf]
• [Chen et. al.] [Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders] [MIDL'18] [google scholar] [pdf]
• [Chen et. al.] [Deep generative models in the real-world: An open challenge from medical imaging] [arxiv, 2018] [google scholar] [pdf]
• [Chen et. al.] [Unsupervised lesion detection via image restoration with a normative prior] [MIA, 2020] [google scholar] [pdf]
• [Baur et. al.] [Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images] [MICCAI'18 workshop] [google scholar] [pdf]
• [Baur et. al.] [Fusing unsupervised and supervised deep learning for white matter lesion segmentation] [MIDL'19] [google scholar] [pdf]
• [Baur et. al.] [Bayesian Skip-Autoencoders for Unsupervised Hyperintense Anomaly Detection in High Resolution Brain Mri] [ISBI'20] [google scholar] [pdf]
• [Baur et. al.] [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study] [arxiv, 2020] [google scholar] [pdf]
• [Baur et. al.] [Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI] [MICCAI'20] [google scholar] [pdf]
• [Zimmerer et. al.] [Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection] [MIDL'19] [google scholar] [pdf]
• [Zimmerer et. al.] [Unsupervised Anomaly Localization using Variational Auto-Encoders] [MICCAI'19] [google scholar] [pdf]
• [Zimmerer et. al.] [High-and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection] [arxiv, 2019] [google scholar] [pdf]
• [Han et. al.] [MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction] [arxiv, 2020] [google scholar] [pdf]
• [Zhou et. al.] [Unsupervised anomaly localization using VAE and beta-VAE] [arxiv, 2020] [google scholar] [pdf]

Brain CT

• [Pawlowski et. al.] [Unsupervised lesion detection in brain CT using bayesian convolutional autoencoders] [MIDL'18] [google scholar] [pdf]

Retinal OCT

• [Schlegl et. al.] [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery (AnoGAN)] [IPMI'17] [google scholar] [pdf][unofficial code]
• [Schlegl et. al.] [f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks] [MIA, 2019] [google scholar] [pdf][code]
• [Seebock et. al.] [Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT] [TMI, 2019] [google scholar] [pdf]
• [Zhang et. al.] [Memory-Augmented Anomaly Generative Adversarial Network for Retinal OCT Images Screening] [ISBI'20] [google scholar] [pdf]
• [Zhou et. al.] [Sparse-GAN: Sparsity-constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image] [ISBI'20] [google scholar] [pdf]
• [Zhou et. al.] [Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images] [ECCV'20] [pdf][code]

Retinal fundus

• [Zhou et. al.] [Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images] [ECCV'20] [pdf][code]

Chest X-Ray in CT

• [Tang et. al.] [Abnormal Chest X-ray Identification With Generative Adversarial One-Class Classifier] [ISBI'19] [google scholar] [pdf]
• [Zhang et. al.] [Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection] [arxiv, 2020] [google scholar] [pdf]
• [Wolleb et. al.] [DeScarGAN: Disease-Specific Anomaly Detection with Weak Supervision] [MICCAI'20] [google scholar] [pdf][code]

Other modalities

• [Tian et. al.] [Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy] [MICCAI'20] [google scholar] [pdf][code]
• [Liu et. al.] [Photoshopping Colonoscopy Video Frames] [ISBI'20] [google scholar] [pdf]

Non-deep learning based methods

Brain MRI

• [Chen et. al.] [Unsupervised Lesion Detection with Locally Gaussian Approximation] [MLMI'19] [google scholar] [pdf]

Some works that related to anomaly detection

• [Zhang et. al.] [Cascaded Generative and Discriminative Learning for Microcalcification Detection in Breast Mammograms] [ICCV'19] [google scholar] [pdf]
• [Siddiquee et. al.] [Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization] [ICCV'19] [google scholar] [pdf]

Not yet public

• [SteGANomaly: Inhibiting CycleGAN Steganography for Unsupervised Anomaly Detection in Brain MRI] [MICCAI'20]
• [SALAD: Self-Supervised Aggregation Learning for Anomaly Detection on X-Rays] [MICCAI'20]
• [Robust Layer Segmentation against Complex Retinal Abnormalities for en face OCTA Generation] [MICCAI'20]
• [Abnormality Detection on Chest X-ray Using Uncertainty Prediction Auto-Encoders] [MICCAI'20]