Outlier Detection in Large Radiological Datasets using UMAP

TL;DR

This paper demonstrates that UMAP can effectively identify outliers and anomalies in large radiological datasets by forming distinct clusters, aiding in dataset curation and quality control.

Contribution

The study introduces the application of UMAP for outlier detection in biomedical imaging datasets, highlighting its effectiveness in identifying errors and inconsistencies.

Findings

UMAP forms independent clusters for anomalies

Effective outlier detection in ChestX-ray14, CheXpert, MURA datasets

Applicable to various data types beyond radiology

Abstract

The success of machine learning algorithms heavily relies on the quality of samples and the accuracy of their corresponding labels. However, building and maintaining large, high-quality datasets is an enormous task. This is especially true for biomedical data and for meta-sets that are compiled from smaller ones, as variations in image quality, labeling, reports, and archiving can lead to errors, inconsistencies, and repeated samples. Here, we show that the uniform manifold approximation and projection (UMAP) algorithm can find these anomalies essentially by forming independent clusters that are distinct from the main (good) data but similar to other points with the same error type. As a representative example, we apply UMAP to discover outliers in the publicly available ChestX-ray14, CheXpert, and MURA datasets. While the results are archival and retrospective and focus on radiological images, the graph-based methods work for any data type and will prove equally beneficial for curation at the time of dataset creation.