Deep learning-based grading of ductal carcinoma in situ in breast histopathology images
Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possib...
Gespeichert in:
Veröffentlicht in: | Laboratory investigation 2021-04, Vol.101 (4), p.525-533 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 533 |
---|---|
container_issue | 4 |
container_start_page | 525 |
container_title | Laboratory investigation |
container_volume | 101 |
creator | Wetstein, Suzanne C. Stathonikos, Nikolas Pluim, Josien P.W. Heng, Yujing J. ter Hoeve, Natalie D. Vreuls, Celien P.H. van Diest, Paul J. Veta, Mitko |
description | Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed and evaluated a deep learning-based DCIS grading system. The system was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen's kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the three observers (o1, o2 and o3) (κo1,dl = 0.81, κo2,dl = 0.53 and κo3,dl = 0.40) than the observers amongst each other (κo1,o2 = 0.58, κo1,o3 = 0.50 and κo2,o3 = 0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κo1,dl = 0.77, κo2,dl = 0.75 and κo3,dl = 0.70) as the observers amongst each other (κo1,o2 = 0.77, κo1,o3 = 0.75 and κo2,o3 = 0.72). The deep learning system better reflected the grading spectrum of DCIS than two of the observers. In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. To the best of our knowledge, this is the first automated system for the grading of DCIS that could assist pathologists by providing robust and reproducible second opinions on DCIS grade. |
doi_str_mv | 10.1038/s41374-021-00540-6 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_miscellaneous_2491943465</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0023683722006560</els_id><sourcerecordid>2491943465</sourcerecordid><originalsourceid>FETCH-LOGICAL-c527t-f11b1eae3f8968a9e08e05a19e215ef0caffc3d708894be7f22faa1a8e87f0863</originalsourceid><addsrcrecordid>eNqNkVuLFDEQhRtxccfVP-CDNPgiSK-VTl_SIAsy3hYWfFF8DNXpSk-WnmRM0iv7781sj-PlYfGpEvKdqjo5WfaMwTkDLl6HivG2KqBkBUBdQdE8yFas5lAAh_ZhtgIoedEI3p5mj0O4BmBV1dSPslPOGxAN61bZt3dEu3wi9NbYsegx0JCPHod0y53Oh1lFnHKFXhnrtpgbmwcT533tPWGI-caE6HYYN25y421utjhSeJKdaJwCPT3Us-zrh_df1p-Kq88fL9dvrwpVl20sNGM9IySuRdcI7AgEQY2so5LVpEGh1ooPLQjRVT21uiw1IkNBotXJAj_LLpa-u7nf0qDIRo-T3Pm0hr-VDo38-8WajRzdjWw7UUNZpwYvDw28-z5TiHJrgqJpQktuDrKsOtZVPP1bQl_8g1672dtkT5Y18GSoEm2iyoVS3oXgSR-XYSD3ucklN5lyk3e5yb2N53_aOEp-BZWAVwvwg3qngzJkFR0xAEhQy7smnYAlWvw_vTYRo3F27WYbk5Qv0pBwO5L_bfLe_d8sKkpZ35ikOgwdjCcV5eDMffKfRynY6A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2503527487</pqid></control><display><type>article</type><title>Deep learning-based grading of ductal carcinoma in situ in breast histopathology images</title><source>MEDLINE</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /></source><source>Alma/SFX Local Collection</source><creator>Wetstein, Suzanne C. ; Stathonikos, Nikolas ; Pluim, Josien P.W. ; Heng, Yujing J. ; ter Hoeve, Natalie D. ; Vreuls, Celien P.H. ; van Diest, Paul J. ; Veta, Mitko</creator><creatorcontrib>Wetstein, Suzanne C. ; Stathonikos, Nikolas ; Pluim, Josien P.W. ; Heng, Yujing J. ; ter Hoeve, Natalie D. ; Vreuls, Celien P.H. ; van Diest, Paul J. ; Veta, Mitko</creatorcontrib><description>Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed and evaluated a deep learning-based DCIS grading system. The system was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen's kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the three observers (o1, o2 and o3) (κo1,dl = 0.81, κo2,dl = 0.53 and κo3,dl = 0.40) than the observers amongst each other (κo1,o2 = 0.58, κo1,o3 = 0.50 and κo2,o3 = 0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κo1,dl = 0.77, κo2,dl = 0.75 and κo3,dl = 0.70) as the observers amongst each other (κo1,o2 = 0.77, κo1,o3 = 0.75 and κo2,o3 = 0.72). The deep learning system better reflected the grading spectrum of DCIS than two of the observers. In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. To the best of our knowledge, this is the first automated system for the grading of DCIS that could assist pathologists by providing robust and reproducible second opinions on DCIS grade.</description><identifier>ISSN: 0023-6837</identifier><identifier>EISSN: 1530-0307</identifier><identifier>DOI: 10.1038/s41374-021-00540-6</identifier><identifier>PMID: 33608619</identifier><language>eng</language><publisher>New York: Elsevier Inc</publisher><subject>631/1647/48 ; 631/67/1347 ; Agreements ; Automation ; Biopsy ; Breast - pathology ; Breast cancer ; Breast Neoplasms - diagnosis ; Breast Neoplasms - pathology ; Carcinoma, Intraductal, Noninfiltrating - diagnosis ; Carcinoma, Intraductal, Noninfiltrating - pathology ; Deep Learning ; Female ; Histopathology ; Humans ; Image analysis ; Image Interpretation, Computer-Assisted - methods ; Image processing ; Laboratory Medicine ; Lesions ; Life Sciences & Biomedicine ; Medical imaging ; Medicine ; Medicine & Public Health ; Medicine, Research & Experimental ; Middle Aged ; Neoplasm Grading - methods ; Observers ; Pathology ; Research & Experimental Medicine ; Robustness ; Science & Technology ; technical-report</subject><ispartof>Laboratory investigation, 2021-04, Vol.101 (4), p.525-533</ispartof><rights>2021 The Authors</rights><rights>The Author(s) 2021</rights><rights>The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>17</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000619739600001</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c527t-f11b1eae3f8968a9e08e05a19e215ef0caffc3d708894be7f22faa1a8e87f0863</citedby><cites>FETCH-LOGICAL-c527t-f11b1eae3f8968a9e08e05a19e215ef0caffc3d708894be7f22faa1a8e87f0863</cites><orcidid>0000-0001-8699-5739 ; 0000-0002-5457-7580 ; 0000-0002-8930-817X ; 0000-0002-3317-8855</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,315,782,786,887,27931,27932,39265</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33608619$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Wetstein, Suzanne C.</creatorcontrib><creatorcontrib>Stathonikos, Nikolas</creatorcontrib><creatorcontrib>Pluim, Josien P.W.</creatorcontrib><creatorcontrib>Heng, Yujing J.</creatorcontrib><creatorcontrib>ter Hoeve, Natalie D.</creatorcontrib><creatorcontrib>Vreuls, Celien P.H.</creatorcontrib><creatorcontrib>van Diest, Paul J.</creatorcontrib><creatorcontrib>Veta, Mitko</creatorcontrib><title>Deep learning-based grading of ductal carcinoma in situ in breast histopathology images</title><title>Laboratory investigation</title><addtitle>Lab Invest</addtitle><addtitle>LAB INVEST</addtitle><addtitle>Lab Invest</addtitle><description>Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed and evaluated a deep learning-based DCIS grading system. The system was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen's kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the three observers (o1, o2 and o3) (κo1,dl = 0.81, κo2,dl = 0.53 and κo3,dl = 0.40) than the observers amongst each other (κo1,o2 = 0.58, κo1,o3 = 0.50 and κo2,o3 = 0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κo1,dl = 0.77, κo2,dl = 0.75 and κo3,dl = 0.70) as the observers amongst each other (κo1,o2 = 0.77, κo1,o3 = 0.75 and κo2,o3 = 0.72). The deep learning system better reflected the grading spectrum of DCIS than two of the observers. In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. To the best of our knowledge, this is the first automated system for the grading of DCIS that could assist pathologists by providing robust and reproducible second opinions on DCIS grade.</description><subject>631/1647/48</subject><subject>631/67/1347</subject><subject>Agreements</subject><subject>Automation</subject><subject>Biopsy</subject><subject>Breast - pathology</subject><subject>Breast cancer</subject><subject>Breast Neoplasms - diagnosis</subject><subject>Breast Neoplasms - pathology</subject><subject>Carcinoma, Intraductal, Noninfiltrating - diagnosis</subject><subject>Carcinoma, Intraductal, Noninfiltrating - pathology</subject><subject>Deep Learning</subject><subject>Female</subject><subject>Histopathology</subject><subject>Humans</subject><subject>Image analysis</subject><subject>Image Interpretation, Computer-Assisted - methods</subject><subject>Image processing</subject><subject>Laboratory Medicine</subject><subject>Lesions</subject><subject>Life Sciences & Biomedicine</subject><subject>Medical imaging</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Medicine, Research & Experimental</subject><subject>Middle Aged</subject><subject>Neoplasm Grading - methods</subject><subject>Observers</subject><subject>Pathology</subject><subject>Research & Experimental Medicine</subject><subject>Robustness</subject><subject>Science & Technology</subject><subject>technical-report</subject><issn>0023-6837</issn><issn>1530-0307</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>HGBXW</sourceid><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNqNkVuLFDEQhRtxccfVP-CDNPgiSK-VTl_SIAsy3hYWfFF8DNXpSk-WnmRM0iv7781sj-PlYfGpEvKdqjo5WfaMwTkDLl6HivG2KqBkBUBdQdE8yFas5lAAh_ZhtgIoedEI3p5mj0O4BmBV1dSPslPOGxAN61bZt3dEu3wi9NbYsegx0JCPHod0y53Oh1lFnHKFXhnrtpgbmwcT533tPWGI-caE6HYYN25y421utjhSeJKdaJwCPT3Us-zrh_df1p-Kq88fL9dvrwpVl20sNGM9IySuRdcI7AgEQY2so5LVpEGh1ooPLQjRVT21uiw1IkNBotXJAj_LLpa-u7nf0qDIRo-T3Pm0hr-VDo38-8WajRzdjWw7UUNZpwYvDw28-z5TiHJrgqJpQktuDrKsOtZVPP1bQl_8g1672dtkT5Y18GSoEm2iyoVS3oXgSR-XYSD3ucklN5lyk3e5yb2N53_aOEp-BZWAVwvwg3qngzJkFR0xAEhQy7smnYAlWvw_vTYRo3F27WYbk5Qv0pBwO5L_bfLe_d8sKkpZ35ikOgwdjCcV5eDMffKfRynY6A</recordid><startdate>20210401</startdate><enddate>20210401</enddate><creator>Wetstein, Suzanne C.</creator><creator>Stathonikos, Nikolas</creator><creator>Pluim, Josien P.W.</creator><creator>Heng, Yujing J.</creator><creator>ter Hoeve, Natalie D.</creator><creator>Vreuls, Celien P.H.</creator><creator>van Diest, Paul J.</creator><creator>Veta, Mitko</creator><general>Elsevier Inc</general><general>Nature Publishing Group US</general><general>Elsevier</general><general>Nature Publishing Group</general><scope>6I.</scope><scope>AAFTH</scope><scope>C6C</scope><scope>BLEPL</scope><scope>DTL</scope><scope>HGBXW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7QL</scope><scope>7QP</scope><scope>7QR</scope><scope>7T5</scope><scope>7T7</scope><scope>7TK</scope><scope>7TM</scope><scope>7U9</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8C1</scope><scope>8FD</scope><scope>8FE</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>H94</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>LK8</scope><scope>M0S</scope><scope>M1P</scope><scope>M7N</scope><scope>M7P</scope><scope>P64</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0001-8699-5739</orcidid><orcidid>https://orcid.org/0000-0002-5457-7580</orcidid><orcidid>https://orcid.org/0000-0002-8930-817X</orcidid><orcidid>https://orcid.org/0000-0002-3317-8855</orcidid></search><sort><creationdate>20210401</creationdate><title>Deep learning-based grading of ductal carcinoma in situ in breast histopathology images</title><author>Wetstein, Suzanne C. ; Stathonikos, Nikolas ; Pluim, Josien P.W. ; Heng, Yujing J. ; ter Hoeve, Natalie D. ; Vreuls, Celien P.H. ; van Diest, Paul J. ; Veta, Mitko</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c527t-f11b1eae3f8968a9e08e05a19e215ef0caffc3d708894be7f22faa1a8e87f0863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>631/1647/48</topic><topic>631/67/1347</topic><topic>Agreements</topic><topic>Automation</topic><topic>Biopsy</topic><topic>Breast - pathology</topic><topic>Breast cancer</topic><topic>Breast Neoplasms - diagnosis</topic><topic>Breast Neoplasms - pathology</topic><topic>Carcinoma, Intraductal, Noninfiltrating - diagnosis</topic><topic>Carcinoma, Intraductal, Noninfiltrating - pathology</topic><topic>Deep Learning</topic><topic>Female</topic><topic>Histopathology</topic><topic>Humans</topic><topic>Image analysis</topic><topic>Image Interpretation, Computer-Assisted - methods</topic><topic>Image processing</topic><topic>Laboratory Medicine</topic><topic>Lesions</topic><topic>Life Sciences & Biomedicine</topic><topic>Medical imaging</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Medicine, Research & Experimental</topic><topic>Middle Aged</topic><topic>Neoplasm Grading - methods</topic><topic>Observers</topic><topic>Pathology</topic><topic>Research & Experimental Medicine</topic><topic>Robustness</topic><topic>Science & Technology</topic><topic>technical-report</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wetstein, Suzanne C.</creatorcontrib><creatorcontrib>Stathonikos, Nikolas</creatorcontrib><creatorcontrib>Pluim, Josien P.W.</creatorcontrib><creatorcontrib>Heng, Yujing J.</creatorcontrib><creatorcontrib>ter Hoeve, Natalie D.</creatorcontrib><creatorcontrib>Vreuls, Celien P.H.</creatorcontrib><creatorcontrib>van Diest, Paul J.</creatorcontrib><creatorcontrib>Veta, Mitko</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>Springer Nature OA/Free Journals</collection><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>Web of Science - Science Citation Index Expanded - 2021</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Immunology Abstracts</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Neurosciences Abstracts</collection><collection>Nucleic Acids Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Public Health Database</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>ProQuest Biological Science Collection</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biological Science Database</collection><collection>Biotechnology and BioEngineering Abstracts</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>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Laboratory investigation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wetstein, Suzanne C.</au><au>Stathonikos, Nikolas</au><au>Pluim, Josien P.W.</au><au>Heng, Yujing J.</au><au>ter Hoeve, Natalie D.</au><au>Vreuls, Celien P.H.</au><au>van Diest, Paul J.</au><au>Veta, Mitko</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep learning-based grading of ductal carcinoma in situ in breast histopathology images</atitle><jtitle>Laboratory investigation</jtitle><stitle>Lab Invest</stitle><stitle>LAB INVEST</stitle><addtitle>Lab Invest</addtitle><date>2021-04-01</date><risdate>2021</risdate><volume>101</volume><issue>4</issue><spage>525</spage><epage>533</epage><pages>525-533</pages><issn>0023-6837</issn><eissn>1530-0307</eissn><abstract>Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed and evaluated a deep learning-based DCIS grading system. The system was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen's kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the three observers (o1, o2 and o3) (κo1,dl = 0.81, κo2,dl = 0.53 and κo3,dl = 0.40) than the observers amongst each other (κo1,o2 = 0.58, κo1,o3 = 0.50 and κo2,o3 = 0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κo1,dl = 0.77, κo2,dl = 0.75 and κo3,dl = 0.70) as the observers amongst each other (κo1,o2 = 0.77, κo1,o3 = 0.75 and κo2,o3 = 0.72). The deep learning system better reflected the grading spectrum of DCIS than two of the observers. In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. To the best of our knowledge, this is the first automated system for the grading of DCIS that could assist pathologists by providing robust and reproducible second opinions on DCIS grade.</abstract><cop>New York</cop><pub>Elsevier Inc</pub><pmid>33608619</pmid><doi>10.1038/s41374-021-00540-6</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0001-8699-5739</orcidid><orcidid>https://orcid.org/0000-0002-5457-7580</orcidid><orcidid>https://orcid.org/0000-0002-8930-817X</orcidid><orcidid>https://orcid.org/0000-0002-3317-8855</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0023-6837 |
ispartof | Laboratory investigation, 2021-04, Vol.101 (4), p.525-533 |
issn | 0023-6837 1530-0307 |
language | eng |
recordid | cdi_proquest_miscellaneous_2491943465 |
source | MEDLINE; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" />; Alma/SFX Local Collection |
subjects | 631/1647/48 631/67/1347 Agreements Automation Biopsy Breast - pathology Breast cancer Breast Neoplasms - diagnosis Breast Neoplasms - pathology Carcinoma, Intraductal, Noninfiltrating - diagnosis Carcinoma, Intraductal, Noninfiltrating - pathology Deep Learning Female Histopathology Humans Image analysis Image Interpretation, Computer-Assisted - methods Image processing Laboratory Medicine Lesions Life Sciences & Biomedicine Medical imaging Medicine Medicine & Public Health Medicine, Research & Experimental Middle Aged Neoplasm Grading - methods Observers Pathology Research & Experimental Medicine Robustness Science & Technology technical-report |
title | Deep learning-based grading of ductal carcinoma in situ in breast histopathology images |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T21%3A27%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20learning-based%20grading%20of%20ductal%20carcinoma%20in%20situ%20in%20breast%20histopathology%20images&rft.jtitle=Laboratory%20investigation&rft.au=Wetstein,%20Suzanne%20C.&rft.date=2021-04-01&rft.volume=101&rft.issue=4&rft.spage=525&rft.epage=533&rft.pages=525-533&rft.issn=0023-6837&rft.eissn=1530-0307&rft_id=info:doi/10.1038/s41374-021-00540-6&rft_dat=%3Cproquest_pubme%3E2491943465%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2503527487&rft_id=info:pmid/33608619&rft_els_id=S0023683722006560&rfr_iscdi=true |