Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans
Unsupervised anomaly detection models which are trained solely by healthy data, have gained importance in the recent years, as the annotation of medical data is a tedious task. Autoencoders and generative adversarial networks are the standard anomaly detection methods that are utilized to learn the...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-10 |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Dietrichstein, Marc Major, David Trapp, Martin Wimmer, Maria Lenis, Dimitrios Winter, Philip Berg, Astrid Neubauer, Theresa Bühler, Katja |
description | Unsupervised anomaly detection models which are trained solely by healthy data, have gained importance in the recent years, as the annotation of medical data is a tedious task. Autoencoders and generative adversarial networks are the standard anomaly detection methods that are utilized to learn the data distribution. However, they fall short when it comes to inference and evaluation of the likelihood of test samples. We propose a novel combination of generative models and a probabilistic graphical model. After encoding image samples by autoencoders, the distribution of data is modeled by Random and Tensorized Sum-Product Networks ensuring exact and efficient inference at test time. We evaluate different autoencoder architectures in combination with Random and Tensorized Sum-Product Networks on mammography images using patch-wise processing and observe superior performance over utilizing the models standalone and state-of-the-art in anomaly detection for medical data. |
doi_str_mv | 10.48550/arxiv.2210.06188 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2210_06188</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2724396079</sourcerecordid><originalsourceid>FETCH-LOGICAL-a529-4479faed8baee9d4fb081ff3ffeec5494bfa53dff3e73a6aee87f4ef4ec36a13</originalsourceid><addsrcrecordid>eNotj11LwzAUhoMgOOZ-gFcGvO5M89Gml2PqFDYVJnhZTtuT2bkmNWmn-_fWTXjhwMvD4X0IuYrZVGql2C34n3o_5XwoWBJrfUZGXIg40pLzCzIJYcsY40nKlRIj8j6zroHdgd5hh2VXO0v7UNsNXaBFD129R7pyFe4CBVvRdd9Er95VfdnRZ-y-nf8MtLZ0BU3jNh7ajwNdl2DDJTk3sAs4-b9jsn64f5s_RsuXxdN8toxA8SySMs0MYKULQMwqaQqmY2OEMYilkpksDChRDQ2mApIB0qmROKQUCcRiTK5PX4_SeevrBvwh_5PPj_IDcXMiWu--egxdvnW9t8OknKdciixhaSZ-AeQkXyM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2724396079</pqid></control><display><type>article</type><title>Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans</title><source>Freely Accessible Journals</source><source>arXiv.org</source><creator>Dietrichstein, Marc ; Major, David ; Trapp, Martin ; Wimmer, Maria ; Lenis, Dimitrios ; Winter, Philip ; Berg, Astrid ; Neubauer, Theresa ; Bühler, Katja</creator><creatorcontrib>Dietrichstein, Marc ; Major, David ; Trapp, Martin ; Wimmer, Maria ; Lenis, Dimitrios ; Winter, Philip ; Berg, Astrid ; Neubauer, Theresa ; Bühler, Katja</creatorcontrib><description>Unsupervised anomaly detection models which are trained solely by healthy data, have gained importance in the recent years, as the annotation of medical data is a tedious task. Autoencoders and generative adversarial networks are the standard anomaly detection methods that are utilized to learn the data distribution. However, they fall short when it comes to inference and evaluation of the likelihood of test samples. We propose a novel combination of generative models and a probabilistic graphical model. After encoding image samples by autoencoders, the distribution of data is modeled by Random and Tensorized Sum-Product Networks ensuring exact and efficient inference at test time. We evaluate different autoencoder architectures in combination with Random and Tensorized Sum-Product Networks on mammography images using patch-wise processing and observe superior performance over utilizing the models standalone and state-of-the-art in anomaly detection for medical data.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2210.06188</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Annotations ; Anomalies ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Generative adversarial networks ; Inference ; Testing time</subject><ispartof>arXiv.org, 2022-10</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27924</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.06188$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1007/978-3-031-18576-2_8$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Dietrichstein, Marc</creatorcontrib><creatorcontrib>Major, David</creatorcontrib><creatorcontrib>Trapp, Martin</creatorcontrib><creatorcontrib>Wimmer, Maria</creatorcontrib><creatorcontrib>Lenis, Dimitrios</creatorcontrib><creatorcontrib>Winter, Philip</creatorcontrib><creatorcontrib>Berg, Astrid</creatorcontrib><creatorcontrib>Neubauer, Theresa</creatorcontrib><creatorcontrib>Bühler, Katja</creatorcontrib><title>Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans</title><title>arXiv.org</title><description>Unsupervised anomaly detection models which are trained solely by healthy data, have gained importance in the recent years, as the annotation of medical data is a tedious task. Autoencoders and generative adversarial networks are the standard anomaly detection methods that are utilized to learn the data distribution. However, they fall short when it comes to inference and evaluation of the likelihood of test samples. We propose a novel combination of generative models and a probabilistic graphical model. After encoding image samples by autoencoders, the distribution of data is modeled by Random and Tensorized Sum-Product Networks ensuring exact and efficient inference at test time. We evaluate different autoencoder architectures in combination with Random and Tensorized Sum-Product Networks on mammography images using patch-wise processing and observe superior performance over utilizing the models standalone and state-of-the-art in anomaly detection for medical data.</description><subject>Annotations</subject><subject>Anomalies</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Generative adversarial networks</subject><subject>Inference</subject><subject>Testing time</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj11LwzAUhoMgOOZ-gFcGvO5M89Gml2PqFDYVJnhZTtuT2bkmNWmn-_fWTXjhwMvD4X0IuYrZVGql2C34n3o_5XwoWBJrfUZGXIg40pLzCzIJYcsY40nKlRIj8j6zroHdgd5hh2VXO0v7UNsNXaBFD129R7pyFe4CBVvRdd9Er95VfdnRZ-y-nf8MtLZ0BU3jNh7ajwNdl2DDJTk3sAs4-b9jsn64f5s_RsuXxdN8toxA8SySMs0MYKULQMwqaQqmY2OEMYilkpksDChRDQ2mApIB0qmROKQUCcRiTK5PX4_SeevrBvwh_5PPj_IDcXMiWu--egxdvnW9t8OknKdciixhaSZ-AeQkXyM</recordid><startdate>20221012</startdate><enddate>20221012</enddate><creator>Dietrichstein, Marc</creator><creator>Major, David</creator><creator>Trapp, Martin</creator><creator>Wimmer, Maria</creator><creator>Lenis, Dimitrios</creator><creator>Winter, Philip</creator><creator>Berg, Astrid</creator><creator>Neubauer, Theresa</creator><creator>Bühler, Katja</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221012</creationdate><title>Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans</title><author>Dietrichstein, Marc ; Major, David ; Trapp, Martin ; Wimmer, Maria ; Lenis, Dimitrios ; Winter, Philip ; Berg, Astrid ; Neubauer, Theresa ; Bühler, Katja</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a529-4479faed8baee9d4fb081ff3ffeec5494bfa53dff3e73a6aee87f4ef4ec36a13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Annotations</topic><topic>Anomalies</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Generative adversarial networks</topic><topic>Inference</topic><topic>Testing time</topic><toplevel>online_resources</toplevel><creatorcontrib>Dietrichstein, Marc</creatorcontrib><creatorcontrib>Major, David</creatorcontrib><creatorcontrib>Trapp, Martin</creatorcontrib><creatorcontrib>Wimmer, Maria</creatorcontrib><creatorcontrib>Lenis, Dimitrios</creatorcontrib><creatorcontrib>Winter, Philip</creatorcontrib><creatorcontrib>Berg, Astrid</creatorcontrib><creatorcontrib>Neubauer, Theresa</creatorcontrib><creatorcontrib>Bühler, Katja</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dietrichstein, Marc</au><au>Major, David</au><au>Trapp, Martin</au><au>Wimmer, Maria</au><au>Lenis, Dimitrios</au><au>Winter, Philip</au><au>Berg, Astrid</au><au>Neubauer, Theresa</au><au>Bühler, Katja</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans</atitle><jtitle>arXiv.org</jtitle><date>2022-10-12</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Unsupervised anomaly detection models which are trained solely by healthy data, have gained importance in the recent years, as the annotation of medical data is a tedious task. Autoencoders and generative adversarial networks are the standard anomaly detection methods that are utilized to learn the data distribution. However, they fall short when it comes to inference and evaluation of the likelihood of test samples. We propose a novel combination of generative models and a probabilistic graphical model. After encoding image samples by autoencoders, the distribution of data is modeled by Random and Tensorized Sum-Product Networks ensuring exact and efficient inference at test time. We evaluate different autoencoder architectures in combination with Random and Tensorized Sum-Product Networks on mammography images using patch-wise processing and observe superior performance over utilizing the models standalone and state-of-the-art in anomaly detection for medical data.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2210.06188</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_2210_06188 |
source | Freely Accessible Journals; arXiv.org |
subjects | Annotations Anomalies Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Generative adversarial networks Inference Testing time |
title | Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T08%3A04%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Anomaly%20Detection%20using%20Generative%20Models%20and%20Sum-Product%20Networks%20in%20Mammography%20Scans&rft.jtitle=arXiv.org&rft.au=Dietrichstein,%20Marc&rft.date=2022-10-12&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2210.06188&rft_dat=%3Cproquest_arxiv%3E2724396079%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2724396079&rft_id=info:pmid/&rfr_iscdi=true |