Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis
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.
Cite
@article{arxiv.2208.08834,
title = {Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis},
author = {Stefan Röhrl and Alice Hein and Lucie Huang and Dominik Heim and Christian Klenk and Manuel Lengl and Martin Knopp and Nawal Hafez and Oliver Hayden and Klaus Diepold},
journal= {arXiv preprint arXiv:2208.08834},
year = {2022}
}
Comments
Presented at the 2nd Workshop on Interpretable Machine Learning in Healthcare (IMLH) @ ICML 2022