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

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Röhrl, Stefan, Hein, Alice, Huang, Lucie, Heim, Dominik, Klenk, Christian, Lengl, Manuel, Knopp, Martin, Hafez, Nawal, Hayden, Oliver, Diepold, Klaus
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Röhrl, Stefan
Hein, Alice
Huang, Lucie
Heim, Dominik
Klenk, Christian
Lengl, Manuel
Knopp, Martin
Hafez, Nawal
Hayden, Oliver
Diepold, Klaus
description 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.
doi_str_mv 10.48550/arxiv.2208.08834
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2208_08834</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2208_08834</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-cae309c727027998407603192163eb02b93356f3cc5cb52fa1bcd86d3f9087a73</originalsourceid><addsrcrecordid>eNotz71OwzAYhWEvHVDLBTDhG0hw7PhvDOFXKmSge_TFsStLblw5DqJcPWrpdPQuR3oQuqtIWSvOyQOkH_9dUkpUSZRi9Q367JYcvE34yWZrso8TXmY_7fGXDa7o0h4m_3vuDzjO2MWEmyXHA2Q74scQ44hbGwJuJgin2c8btHIQZnt73TXavTzv2rdi272-t822ACHrwoBlRBtJJaFSa1UTKQirNK0EswOhg2aMC8eM4Wbg1EE1mFGJkTlNlATJ1uj-__YC6o_JHyCd-jOsv8DYHzzLR-c</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis</title><source>arXiv.org</source><creator>Röhrl, Stefan ; Hein, Alice ; Huang, Lucie ; Heim, Dominik ; Klenk, Christian ; Lengl, Manuel ; Knopp, Martin ; Hafez, Nawal ; Hayden, Oliver ; Diepold, Klaus</creator><creatorcontrib>Röhrl, Stefan ; Hein, Alice ; Huang, Lucie ; Heim, Dominik ; Klenk, Christian ; Lengl, Manuel ; Knopp, Martin ; Hafez, Nawal ; Hayden, Oliver ; Diepold, Klaus</creatorcontrib><description>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.</description><identifier>DOI: 10.48550/arxiv.2208.08834</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2022-08</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2208.08834$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2208.08834$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Röhrl, Stefan</creatorcontrib><creatorcontrib>Hein, Alice</creatorcontrib><creatorcontrib>Huang, Lucie</creatorcontrib><creatorcontrib>Heim, Dominik</creatorcontrib><creatorcontrib>Klenk, Christian</creatorcontrib><creatorcontrib>Lengl, Manuel</creatorcontrib><creatorcontrib>Knopp, Martin</creatorcontrib><creatorcontrib>Hafez, Nawal</creatorcontrib><creatorcontrib>Hayden, Oliver</creatorcontrib><creatorcontrib>Diepold, Klaus</creatorcontrib><title>Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis</title><description>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.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAYhWEvHVDLBTDhG0hw7PhvDOFXKmSge_TFsStLblw5DqJcPWrpdPQuR3oQuqtIWSvOyQOkH_9dUkpUSZRi9Q367JYcvE34yWZrso8TXmY_7fGXDa7o0h4m_3vuDzjO2MWEmyXHA2Q74scQ44hbGwJuJgin2c8btHIQZnt73TXavTzv2rdi272-t822ACHrwoBlRBtJJaFSa1UTKQirNK0EswOhg2aMC8eM4Wbg1EE1mFGJkTlNlATJ1uj-__YC6o_JHyCd-jOsv8DYHzzLR-c</recordid><startdate>20220818</startdate><enddate>20220818</enddate><creator>Röhrl, Stefan</creator><creator>Hein, Alice</creator><creator>Huang, Lucie</creator><creator>Heim, Dominik</creator><creator>Klenk, Christian</creator><creator>Lengl, Manuel</creator><creator>Knopp, Martin</creator><creator>Hafez, Nawal</creator><creator>Hayden, Oliver</creator><creator>Diepold, Klaus</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220818</creationdate><title>Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis</title><author>Röhrl, Stefan ; Hein, Alice ; Huang, Lucie ; Heim, Dominik ; Klenk, Christian ; Lengl, Manuel ; Knopp, Martin ; Hafez, Nawal ; Hayden, Oliver ; Diepold, Klaus</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-cae309c727027998407603192163eb02b93356f3cc5cb52fa1bcd86d3f9087a73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Röhrl, Stefan</creatorcontrib><creatorcontrib>Hein, Alice</creatorcontrib><creatorcontrib>Huang, Lucie</creatorcontrib><creatorcontrib>Heim, Dominik</creatorcontrib><creatorcontrib>Klenk, Christian</creatorcontrib><creatorcontrib>Lengl, Manuel</creatorcontrib><creatorcontrib>Knopp, Martin</creatorcontrib><creatorcontrib>Hafez, Nawal</creatorcontrib><creatorcontrib>Hayden, Oliver</creatorcontrib><creatorcontrib>Diepold, Klaus</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Röhrl, Stefan</au><au>Hein, Alice</au><au>Huang, Lucie</au><au>Heim, Dominik</au><au>Klenk, Christian</au><au>Lengl, Manuel</au><au>Knopp, Martin</au><au>Hafez, Nawal</au><au>Hayden, Oliver</au><au>Diepold, Klaus</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis</atitle><date>2022-08-18</date><risdate>2022</risdate><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.</abstract><doi>10.48550/arxiv.2208.08834</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2208.08834
ispartof
issn
language eng
recordid cdi_arxiv_primary_2208_08834
source arXiv.org
subjects Computer Science - Learning
title Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T09%3A35%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Outlier%20Detection%20using%20Self-Organizing%20Maps%20for%20Automated%20Blood%20Cell%20Analysis&rft.au=R%C3%B6hrl,%20Stefan&rft.date=2022-08-18&rft_id=info:doi/10.48550/arxiv.2208.08834&rft_dat=%3Carxiv_GOX%3E2208_08834%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true