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

TL;DR

This paper introduces a self-taught semi-supervised approach for anomaly detection in upper limb X-rays that leverages unlabeled data with task-agnostic pretext tasks and complex normal data modeling, outperforming existing methods.

Contribution

It proposes a novel semi-supervised framework using cross-sample similarity and complex normal data modeling to improve anomaly detection without extensive annotations.

Findings

Outperforms baseline methods on the MURA dataset

Effective in both unsupervised and self-supervised settings

Rich ablation studies validate each component's contribution

Abstract

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.