Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer
Prostate cancer is a dominant health concern calling for advanced diagnostic tools. Utilizing digital pathology and artificial intelligence, this study explores the potential of 11 deep neural network architectures for automated Gleason grading in prostate carcinoma focusing on comparing traditional...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| 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 | Müller, Dominik Meyer, Philip Rentschler, Lukas Manz, Robin Hieber, Daniel Bäcker, Jonas Cramer, Samantha Wengenmayr, Christoph Märkl, Bruno Huss, Ralf Kramer, Frank Soto-Rey, Iñaki Raffler, Johannes |
| description | Prostate cancer is a dominant health concern calling for advanced diagnostic
tools. Utilizing digital pathology and artificial intelligence, this study
explores the potential of 11 deep neural network architectures for automated
Gleason grading in prostate carcinoma focusing on comparing traditional and
recent architectures. A standardized image classification pipeline, based on
the AUCMEDI framework, facilitated robust evaluation using an in-house dataset
consisting of 34,264 annotated tissue tiles. The results indicated varying
sensitivity across architectures, with ConvNeXt demonstrating the strongest
performance. Notably, newer architectures achieved superior performance, even
though with challenges in differentiating closely related Gleason grades. The
ConvNeXt model was capable of learning a balance between complexity and
generalizability. Overall, this study lays the groundwork for enhanced Gleason
grading systems, potentially improving diagnostic efficiency for prostate
cancer. |
| doi_str_mv | 10.48550/arxiv.2403.16695 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2403_16695</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2403_16695</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-628cb9851376d6fb2762b62b60440802b58d8ddcef371c31f811e9e36db16dab3</originalsourceid><addsrcrecordid>eNotj71OwzAYRb0woMIDMOEXSPBP7DhjFCAgRWqHbgyRHX9uIzV2ZQcEb09dkK50h3N1pYPQAyVlpYQgTzp-z18lqwgvqZSNuEUfbUqQ0uwPeD0C3kF0IS7aT4CDw88AZzyAjj4PLgS3n2tY9AoW9yfQKXjcR20znT3exZDWC8RdPoh36MbpU4L7_96g_evLvnsrhm3_3rVDoWUtCsnUZBolKK-llc6wWjKTQ6qKKMKMUFZZO4HjNZ04dYpSaIBLa6i02vANevy7vdqN5zgvOv6M2XK8WvJfsw1NCg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer</title><source>arXiv.org</source><creator>Müller, Dominik ; Meyer, Philip ; Rentschler, Lukas ; Manz, Robin ; Hieber, Daniel ; Bäcker, Jonas ; Cramer, Samantha ; Wengenmayr, Christoph ; Märkl, Bruno ; Huss, Ralf ; Kramer, Frank ; Soto-Rey, Iñaki ; Raffler, Johannes</creator><creatorcontrib>Müller, Dominik ; Meyer, Philip ; Rentschler, Lukas ; Manz, Robin ; Hieber, Daniel ; Bäcker, Jonas ; Cramer, Samantha ; Wengenmayr, Christoph ; Märkl, Bruno ; Huss, Ralf ; Kramer, Frank ; Soto-Rey, Iñaki ; Raffler, Johannes</creatorcontrib><description>Prostate cancer is a dominant health concern calling for advanced diagnostic
tools. Utilizing digital pathology and artificial intelligence, this study
explores the potential of 11 deep neural network architectures for automated
Gleason grading in prostate carcinoma focusing on comparing traditional and
recent architectures. A standardized image classification pipeline, based on
the AUCMEDI framework, facilitated robust evaluation using an in-house dataset
consisting of 34,264 annotated tissue tiles. The results indicated varying
sensitivity across architectures, with ConvNeXt demonstrating the strongest
performance. Notably, newer architectures achieved superior performance, even
though with challenges in differentiating closely related Gleason grades. The
ConvNeXt model was capable of learning a balance between complexity and
generalizability. Overall, this study lays the groundwork for enhanced Gleason
grading systems, potentially improving diagnostic efficiency for prostate
cancer.</description><identifier>DOI: 10.48550/arxiv.2403.16695</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Quantitative Biology - Tissues and Organs</subject><creationdate>2024-03</creationdate><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2403.16695$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2403.16695$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Müller, Dominik</creatorcontrib><creatorcontrib>Meyer, Philip</creatorcontrib><creatorcontrib>Rentschler, Lukas</creatorcontrib><creatorcontrib>Manz, Robin</creatorcontrib><creatorcontrib>Hieber, Daniel</creatorcontrib><creatorcontrib>Bäcker, Jonas</creatorcontrib><creatorcontrib>Cramer, Samantha</creatorcontrib><creatorcontrib>Wengenmayr, Christoph</creatorcontrib><creatorcontrib>Märkl, Bruno</creatorcontrib><creatorcontrib>Huss, Ralf</creatorcontrib><creatorcontrib>Kramer, Frank</creatorcontrib><creatorcontrib>Soto-Rey, Iñaki</creatorcontrib><creatorcontrib>Raffler, Johannes</creatorcontrib><title>Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer</title><description>Prostate cancer is a dominant health concern calling for advanced diagnostic
tools. Utilizing digital pathology and artificial intelligence, this study
explores the potential of 11 deep neural network architectures for automated
Gleason grading in prostate carcinoma focusing on comparing traditional and
recent architectures. A standardized image classification pipeline, based on
the AUCMEDI framework, facilitated robust evaluation using an in-house dataset
consisting of 34,264 annotated tissue tiles. The results indicated varying
sensitivity across architectures, with ConvNeXt demonstrating the strongest
performance. Notably, newer architectures achieved superior performance, even
though with challenges in differentiating closely related Gleason grades. The
ConvNeXt model was capable of learning a balance between complexity and
generalizability. Overall, this study lays the groundwork for enhanced Gleason
grading systems, potentially improving diagnostic efficiency for prostate
cancer.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Quantitative Biology - Tissues and Organs</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71OwzAYRb0woMIDMOEXSPBP7DhjFCAgRWqHbgyRHX9uIzV2ZQcEb09dkK50h3N1pYPQAyVlpYQgTzp-z18lqwgvqZSNuEUfbUqQ0uwPeD0C3kF0IS7aT4CDw88AZzyAjj4PLgS3n2tY9AoW9yfQKXjcR20znT3exZDWC8RdPoh36MbpU4L7_96g_evLvnsrhm3_3rVDoWUtCsnUZBolKK-llc6wWjKTQ6qKKMKMUFZZO4HjNZ04dYpSaIBLa6i02vANevy7vdqN5zgvOv6M2XK8WvJfsw1NCg</recordid><startdate>20240325</startdate><enddate>20240325</enddate><creator>Müller, Dominik</creator><creator>Meyer, Philip</creator><creator>Rentschler, Lukas</creator><creator>Manz, Robin</creator><creator>Hieber, Daniel</creator><creator>Bäcker, Jonas</creator><creator>Cramer, Samantha</creator><creator>Wengenmayr, Christoph</creator><creator>Märkl, Bruno</creator><creator>Huss, Ralf</creator><creator>Kramer, Frank</creator><creator>Soto-Rey, Iñaki</creator><creator>Raffler, Johannes</creator><scope>AKY</scope><scope>ALC</scope><scope>GOX</scope></search><sort><creationdate>20240325</creationdate><title>Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer</title><author>Müller, Dominik ; Meyer, Philip ; Rentschler, Lukas ; Manz, Robin ; Hieber, Daniel ; Bäcker, Jonas ; Cramer, Samantha ; Wengenmayr, Christoph ; Märkl, Bruno ; Huss, Ralf ; Kramer, Frank ; Soto-Rey, Iñaki ; Raffler, Johannes</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-628cb9851376d6fb2762b62b60440802b58d8ddcef371c31f811e9e36db16dab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Quantitative Biology - Tissues and Organs</topic><toplevel>online_resources</toplevel><creatorcontrib>Müller, Dominik</creatorcontrib><creatorcontrib>Meyer, Philip</creatorcontrib><creatorcontrib>Rentschler, Lukas</creatorcontrib><creatorcontrib>Manz, Robin</creatorcontrib><creatorcontrib>Hieber, Daniel</creatorcontrib><creatorcontrib>Bäcker, Jonas</creatorcontrib><creatorcontrib>Cramer, Samantha</creatorcontrib><creatorcontrib>Wengenmayr, Christoph</creatorcontrib><creatorcontrib>Märkl, Bruno</creatorcontrib><creatorcontrib>Huss, Ralf</creatorcontrib><creatorcontrib>Kramer, Frank</creatorcontrib><creatorcontrib>Soto-Rey, Iñaki</creatorcontrib><creatorcontrib>Raffler, Johannes</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Quantitative Biology</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Müller, Dominik</au><au>Meyer, Philip</au><au>Rentschler, Lukas</au><au>Manz, Robin</au><au>Hieber, Daniel</au><au>Bäcker, Jonas</au><au>Cramer, Samantha</au><au>Wengenmayr, Christoph</au><au>Märkl, Bruno</au><au>Huss, Ralf</au><au>Kramer, Frank</au><au>Soto-Rey, Iñaki</au><au>Raffler, Johannes</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer</atitle><date>2024-03-25</date><risdate>2024</risdate><abstract>Prostate cancer is a dominant health concern calling for advanced diagnostic
tools. Utilizing digital pathology and artificial intelligence, this study
explores the potential of 11 deep neural network architectures for automated
Gleason grading in prostate carcinoma focusing on comparing traditional and
recent architectures. A standardized image classification pipeline, based on
the AUCMEDI framework, facilitated robust evaluation using an in-house dataset
consisting of 34,264 annotated tissue tiles. The results indicated varying
sensitivity across architectures, with ConvNeXt demonstrating the strongest
performance. Notably, newer architectures achieved superior performance, even
though with challenges in differentiating closely related Gleason grades. The
ConvNeXt model was capable of learning a balance between complexity and
generalizability. Overall, this study lays the groundwork for enhanced Gleason
grading systems, potentially improving diagnostic efficiency for prostate
cancer.</abstract><doi>10.48550/arxiv.2403.16695</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2403.16695 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2403_16695 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Quantitative Biology - Tissues and Organs |
| title | Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T20%3A02%3A20IST&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=Assessing%20the%20Performance%20of%20Deep%20Learning%20for%20Automated%20Gleason%20Grading%20in%20Prostate%20Cancer&rft.au=M%C3%BCller,%20Dominik&rft.date=2024-03-25&rft_id=info:doi/10.48550/arxiv.2403.16695&rft_dat=%3Carxiv_GOX%3E2403_16695%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 |