Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study
Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize t...
Gespeichert in:
| Veröffentlicht in: | Cancers 2021-06, Vol.13 (12), p.3098 |
|---|---|
| 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 | 12 |
| container_start_page | 3098 |
| container_title | Cancers |
| container_volume | 13 |
| creator | Yan, Ye Shao, Lizhi Liu, Zhenyu He, Wei Yang, Guanyu Liu, Jiangang Xia, Haizhui Zhang, Yuting Chen, Huiying Liu, Cheng Lu, Min Ma, Lulin Sun, Kai Zhou, Xuezhi Ye, Xiongjun Wang, Lei Tian, Jie Lu, Jian |
| description | Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients. |
| doi_str_mv | 10.3390/cancers13123098 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8234539</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2548397259</sourcerecordid><originalsourceid>FETCH-LOGICAL-c398t-55d64b89c9ed384d760c1e0d40dd88420fa62018c481b7a20caaec74c90058ea3</originalsourceid><addsrcrecordid>eNpdkU1v1DAQhiMEolXpmaslLlxCHdtJbA5IZaFQaStKgXM0a8_uukrsrT-K9o_099ahFYLOxSPPM-98VdXrhr7jXNETDU5jiA1vGKdKPqsOGe1Z3XVKPP_HP6iOY7ymxThv-q5_WR1wwWjby-6wuvuEuCNLhOCs25DfNm3J9wwu2QTJ3iI5Q0g5YCR-TS5g4zBZTa4wejdXJ-cTbEoweXIZ0FidyEfr9RYnq2EsnM4h4AyW9Cswf34vg49FHXXy0_49OSUXeUy2XqBLGMiPlM3-VfViDWPE48f3qPp19vnn4mu9_PblfHG6rDVXMtVtazqxkkorNFwK03dUN0iNoMZIWYZcQ8doI7WQzaoHRjUA6l5oRWkrEfhR9eFBd5dXExpdWggwDrtgJwj7wYMd_o84ux02_naQjIuWqyLw9lEg-JuMMQ2TjRrHERz6HAfWCslVz9oZffMEvfY5uDLeTAnVSi5poU4eKF22FAOu_zbT0GE--_Dk7PweEEqisw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2544958380</pqid></control><display><type>article</type><title>Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><source>PubMed Central Open Access</source><creator>Yan, Ye ; Shao, Lizhi ; Liu, Zhenyu ; He, Wei ; Yang, Guanyu ; Liu, Jiangang ; Xia, Haizhui ; Zhang, Yuting ; Chen, Huiying ; Liu, Cheng ; Lu, Min ; Ma, Lulin ; Sun, Kai ; Zhou, Xuezhi ; Ye, Xiongjun ; Wang, Lei ; Tian, Jie ; Lu, Jian</creator><creatorcontrib>Yan, Ye ; Shao, Lizhi ; Liu, Zhenyu ; He, Wei ; Yang, Guanyu ; Liu, Jiangang ; Xia, Haizhui ; Zhang, Yuting ; Chen, Huiying ; Liu, Cheng ; Lu, Min ; Ma, Lulin ; Sun, Kai ; Zhou, Xuezhi ; Ye, Xiongjun ; Wang, Lei ; Tian, Jie ; Lu, Jian</creatorcontrib><description>Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients.</description><identifier>ISSN: 2072-6694</identifier><identifier>EISSN: 2072-6694</identifier><identifier>DOI: 10.3390/cancers13123098</identifier><identifier>PMID: 34205786</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Biopsy ; Deep learning ; Hospitals ; Image processing ; Magnetic resonance imaging ; Medical prognosis ; Metastasis ; Neural networks ; Pathology ; Patients ; Performance evaluation ; Prediction models ; Prostate cancer ; Prostatectomy ; Radiomics ; Software ; Surgery ; Survival ; Survival analysis ; Tumors</subject><ispartof>Cancers, 2021-06, Vol.13 (12), p.3098</ispartof><rights>2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c398t-55d64b89c9ed384d760c1e0d40dd88420fa62018c481b7a20caaec74c90058ea3</citedby><cites>FETCH-LOGICAL-c398t-55d64b89c9ed384d760c1e0d40dd88420fa62018c481b7a20caaec74c90058ea3</cites><orcidid>0000-0003-0847-561X ; 0000-0001-7559-8519 ; 0000-0002-9144-7486</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8234539/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8234539/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,27903,27904,53769,53771</link.rule.ids></links><search><creatorcontrib>Yan, Ye</creatorcontrib><creatorcontrib>Shao, Lizhi</creatorcontrib><creatorcontrib>Liu, Zhenyu</creatorcontrib><creatorcontrib>He, Wei</creatorcontrib><creatorcontrib>Yang, Guanyu</creatorcontrib><creatorcontrib>Liu, Jiangang</creatorcontrib><creatorcontrib>Xia, Haizhui</creatorcontrib><creatorcontrib>Zhang, Yuting</creatorcontrib><creatorcontrib>Chen, Huiying</creatorcontrib><creatorcontrib>Liu, Cheng</creatorcontrib><creatorcontrib>Lu, Min</creatorcontrib><creatorcontrib>Ma, Lulin</creatorcontrib><creatorcontrib>Sun, Kai</creatorcontrib><creatorcontrib>Zhou, Xuezhi</creatorcontrib><creatorcontrib>Ye, Xiongjun</creatorcontrib><creatorcontrib>Wang, Lei</creatorcontrib><creatorcontrib>Tian, Jie</creatorcontrib><creatorcontrib>Lu, Jian</creatorcontrib><title>Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study</title><title>Cancers</title><description>Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients.</description><subject>Biopsy</subject><subject>Deep learning</subject><subject>Hospitals</subject><subject>Image processing</subject><subject>Magnetic resonance imaging</subject><subject>Medical prognosis</subject><subject>Metastasis</subject><subject>Neural networks</subject><subject>Pathology</subject><subject>Patients</subject><subject>Performance evaluation</subject><subject>Prediction models</subject><subject>Prostate cancer</subject><subject>Prostatectomy</subject><subject>Radiomics</subject><subject>Software</subject><subject>Surgery</subject><subject>Survival</subject><subject>Survival analysis</subject><subject>Tumors</subject><issn>2072-6694</issn><issn>2072-6694</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>8G5</sourceid><sourceid>BENPR</sourceid><sourceid>GUQSH</sourceid><sourceid>M2O</sourceid><recordid>eNpdkU1v1DAQhiMEolXpmaslLlxCHdtJbA5IZaFQaStKgXM0a8_uukrsrT-K9o_099ahFYLOxSPPM-98VdXrhr7jXNETDU5jiA1vGKdKPqsOGe1Z3XVKPP_HP6iOY7ymxThv-q5_WR1wwWjby-6wuvuEuCNLhOCs25DfNm3J9wwu2QTJ3iI5Q0g5YCR-TS5g4zBZTa4wejdXJ-cTbEoweXIZ0FidyEfr9RYnq2EsnM4h4AyW9Cswf34vg49FHXXy0_49OSUXeUy2XqBLGMiPlM3-VfViDWPE48f3qPp19vnn4mu9_PblfHG6rDVXMtVtazqxkkorNFwK03dUN0iNoMZIWYZcQ8doI7WQzaoHRjUA6l5oRWkrEfhR9eFBd5dXExpdWggwDrtgJwj7wYMd_o84ux02_naQjIuWqyLw9lEg-JuMMQ2TjRrHERz6HAfWCslVz9oZffMEvfY5uDLeTAnVSi5poU4eKF22FAOu_zbT0GE--_Dk7PweEEqisw</recordid><startdate>20210621</startdate><enddate>20210621</enddate><creator>Yan, Ye</creator><creator>Shao, Lizhi</creator><creator>Liu, Zhenyu</creator><creator>He, Wei</creator><creator>Yang, Guanyu</creator><creator>Liu, Jiangang</creator><creator>Xia, Haizhui</creator><creator>Zhang, Yuting</creator><creator>Chen, Huiying</creator><creator>Liu, Cheng</creator><creator>Lu, Min</creator><creator>Ma, Lulin</creator><creator>Sun, Kai</creator><creator>Zhou, Xuezhi</creator><creator>Ye, Xiongjun</creator><creator>Wang, Lei</creator><creator>Tian, Jie</creator><creator>Lu, Jian</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7T5</scope><scope>7TO</scope><scope>7XB</scope><scope>8FE</scope><scope>8FH</scope><scope>8FK</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>H94</scope><scope>HCIFZ</scope><scope>LK8</scope><scope>M2O</scope><scope>M7P</scope><scope>MBDVC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-0847-561X</orcidid><orcidid>https://orcid.org/0000-0001-7559-8519</orcidid><orcidid>https://orcid.org/0000-0002-9144-7486</orcidid></search><sort><creationdate>20210621</creationdate><title>Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study</title><author>Yan, Ye ; Shao, Lizhi ; Liu, Zhenyu ; He, Wei ; Yang, Guanyu ; Liu, Jiangang ; Xia, Haizhui ; Zhang, Yuting ; Chen, Huiying ; Liu, Cheng ; Lu, Min ; Ma, Lulin ; Sun, Kai ; Zhou, Xuezhi ; Ye, Xiongjun ; Wang, Lei ; Tian, Jie ; Lu, Jian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c398t-55d64b89c9ed384d760c1e0d40dd88420fa62018c481b7a20caaec74c90058ea3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Biopsy</topic><topic>Deep learning</topic><topic>Hospitals</topic><topic>Image processing</topic><topic>Magnetic resonance imaging</topic><topic>Medical prognosis</topic><topic>Metastasis</topic><topic>Neural networks</topic><topic>Pathology</topic><topic>Patients</topic><topic>Performance evaluation</topic><topic>Prediction models</topic><topic>Prostate cancer</topic><topic>Prostatectomy</topic><topic>Radiomics</topic><topic>Software</topic><topic>Surgery</topic><topic>Survival</topic><topic>Survival analysis</topic><topic>Tumors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yan, Ye</creatorcontrib><creatorcontrib>Shao, Lizhi</creatorcontrib><creatorcontrib>Liu, Zhenyu</creatorcontrib><creatorcontrib>He, Wei</creatorcontrib><creatorcontrib>Yang, Guanyu</creatorcontrib><creatorcontrib>Liu, Jiangang</creatorcontrib><creatorcontrib>Xia, Haizhui</creatorcontrib><creatorcontrib>Zhang, Yuting</creatorcontrib><creatorcontrib>Chen, Huiying</creatorcontrib><creatorcontrib>Liu, Cheng</creatorcontrib><creatorcontrib>Lu, Min</creatorcontrib><creatorcontrib>Ma, Lulin</creatorcontrib><creatorcontrib>Sun, Kai</creatorcontrib><creatorcontrib>Zhou, Xuezhi</creatorcontrib><creatorcontrib>Ye, Xiongjun</creatorcontrib><creatorcontrib>Wang, Lei</creatorcontrib><creatorcontrib>Tian, Jie</creatorcontrib><creatorcontrib>Lu, Jian</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Immunology Abstracts</collection><collection>Oncogenes and Growth Factors Abstracts</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Research Library (Alumni Edition)</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>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Biological Science Collection</collection><collection>Research Library</collection><collection>Biological Science Database</collection><collection>Research Library (Corporate)</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>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Cancers</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yan, Ye</au><au>Shao, Lizhi</au><au>Liu, Zhenyu</au><au>He, Wei</au><au>Yang, Guanyu</au><au>Liu, Jiangang</au><au>Xia, Haizhui</au><au>Zhang, Yuting</au><au>Chen, Huiying</au><au>Liu, Cheng</au><au>Lu, Min</au><au>Ma, Lulin</au><au>Sun, Kai</au><au>Zhou, Xuezhi</au><au>Ye, Xiongjun</au><au>Wang, Lei</au><au>Tian, Jie</au><au>Lu, Jian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study</atitle><jtitle>Cancers</jtitle><date>2021-06-21</date><risdate>2021</risdate><volume>13</volume><issue>12</issue><spage>3098</spage><pages>3098-</pages><issn>2072-6694</issn><eissn>2072-6694</eissn><abstract>Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>34205786</pmid><doi>10.3390/cancers13123098</doi><orcidid>https://orcid.org/0000-0003-0847-561X</orcidid><orcidid>https://orcid.org/0000-0001-7559-8519</orcidid><orcidid>https://orcid.org/0000-0002-9144-7486</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2072-6694 |
| ispartof | Cancers, 2021-06, Vol.13 (12), p.3098 |
| issn | 2072-6694 2072-6694 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8234539 |
| source | MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central; PubMed Central Open Access |
| subjects | Biopsy Deep learning Hospitals Image processing Magnetic resonance imaging Medical prognosis Metastasis Neural networks Pathology Patients Performance evaluation Prediction models Prostate cancer Prostatectomy Radiomics Software Surgery Survival Survival analysis Tumors |
| title | Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T08%3A04%3A13IST&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%20with%20Quantitative%20Features%20of%20Magnetic%20Resonance%20Images%20to%20Predict%20Biochemical%20Recurrence%20of%20Radical%20Prostatectomy:%20A%20Multi-Center%20Study&rft.jtitle=Cancers&rft.au=Yan,%20Ye&rft.date=2021-06-21&rft.volume=13&rft.issue=12&rft.spage=3098&rft.pages=3098-&rft.issn=2072-6694&rft.eissn=2072-6694&rft_id=info:doi/10.3390/cancers13123098&rft_dat=%3Cproquest_pubme%3E2548397259%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=2544958380&rft_id=info:pmid/34205786&rfr_iscdi=true |