Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis

TL;DR

This paper evaluates the effectiveness of Self-Organizing Maps for outlier detection in medical blood cell datasets, demonstrating their potential for dataset cleaning and out-of-distribution detection.

Contribution

It introduces the application of Self-Organizing Maps for unsupervised outlier detection in medical imaging datasets, showing they perform comparably to expert-designed filters.

Findings

Self-Organizing Maps effectively detect outliers based on quantization errors.

They perform on par with domain expert filters.

SOMs are useful for dataset exploration and cleaning.

Abstract

The quality of datasets plays a crucial role in the successful training and deployment of deep learning models. Especially in the medical field, where system performance may impact the health of patients, clean datasets are a safety requirement for reliable predictions. Therefore, outlier detection is an essential process when building autonomous clinical decision systems. In this work, we assess the suitability of Self-Organizing Maps for outlier detection specifically on a medical dataset containing quantitative phase images of white blood cells. We detect and evaluate outliers based on quantization errors and distance maps. Our findings confirm the suitability of Self-Organizing Maps for unsupervised Out-Of-Distribution detection on the dataset at hand. Self-Organizing Maps perform on par with a manually specified filter based on expert domain knowledge. Additionally, they show promise as a tool in the exploration and cleaning of medical datasets. As a direction for future research, we suggest a combination of Self-Organizing Maps and feature extraction based on deep learning.