# Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays

arXiv: https://arxiv.org/abs/2102.09895 · HTML: https://mlsanity.com/paper/2102.09895/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 19 Feb 2021.

## Builds on (most cited first, 22 of 22)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Deep Structured Energy Based Models for Anomaly Detection](https://mlsanity.com/paper/1605.07717/) (2016)
- [Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations](https://mlsanity.com/paper/2007.07423/) (2020)
- [Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation](https://mlsanity.com/paper/2003.14119/) (2020)
- [Progressive Generative Adversarial Networks for Medical Image Super resolution](https://mlsanity.com/paper/1902.02144/) (2019)
- [Informative sample generation using class aware generative adversarial networks for classification of chest Xrays](https://mlsanity.com/paper/1904.10781/) (2019)
- [Abnormal Chest X-ray Identification With Generative Adversarial One-Class Classifier](https://mlsanity.com/paper/1903.02040/) (2019)
- [Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis](https://mlsanity.com/paper/1905.08090/) (2019)
- [Benefiting from Multitask Learning to Improve Single Image Super-Resolution](https://mlsanity.com/paper/1907.12488/) (2019)
- [Learn to synthesize and synthesize to learn](https://mlsanity.com/paper/1905.00286/) (2019)
- [Regression Networks for Meta-Learning Few-Shot Classification](https://mlsanity.com/paper/1905.13613/) (2019)

## Built on by (most cited first, 2 of 2)

- [Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook](https://mlsanity.com/paper/2205.05173/) (2022)
- [AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays](https://mlsanity.com/paper/2307.12721/) (2023)

## Abstract (arXiv)

Detecting anomalies in musculoskeletal radiographs is of paramount importance for large-scale screening in the radiology workflow. Supervised deep networks take for granted a large number of annotations by radiologists, which is often prohibitively very time-consuming to acquire. Moreover, supervised systems are tailored to closed set scenarios, e.g., trained models suffer from overfitting to previously seen rare anomalies at training. Instead, our approach's rationale is to use task agnostic pretext tasks to leverage unlabeled data based on a cross-sample similarity measure. Besides, we formulate a complex distribution of data from normal class within our framework to avoid a potential bias on the side of anomalies. Through extensive experiments, we show that our method outperforms baselines across unsupervised and self-supervised anomaly detection settings on a real-world medical dataset, the MURA dataset. We also provide rich ablation studies to analyze each training stage's effect and loss terms on the final performance.