Prognostic value of enhanced cine cardiac MRI-based radiomics in dilated cardiomyopathy
Early precise identification of high-risk dilated cardiomyopathy (DCM) phenotype is essential for clinical decision-making and patient surveillance. The aim of the study was to assess the prognostic value of enhanced cine cardiac magnetic resonance (CMR)-based radiomics in DCM. We prospectively enro...
Gespeichert in:
| Veröffentlicht in: | International journal of cardiology 2025-01, Vol.418, p.132617, Article 132617 |
|---|---|
| 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 | 132617 |
| container_title | International journal of cardiology |
| container_volume | 418 |
| creator | Li, Xue Xu, Yuanwei Chen, Xiaoyi Liu, Jing He, Wenzhang Wang, Simeng Yin, Hongkun Zhou, Xiaoyue Song, Yang Peng, Liqing Chen, Yucheng |
| description | Early precise identification of high-risk dilated cardiomyopathy (DCM) phenotype is essential for clinical decision-making and patient surveillance. The aim of the study was to assess the prognostic value of enhanced cine cardiac magnetic resonance (CMR)-based radiomics in DCM.
We prospectively enrolled 401 (training set: 281; test set: 120) DCM patients. Radiomic features were extracted from enhanced cine images of entire left ventricular wall and selected by the least absolute shrinkage and selection operator. Different predictive models were built using logistic regression classifier to predict all-cause mortality and heart transplantation. Model performances were compared with the area under the receiver operating characteristic curves (AUCs). Kaplan-Meier curves, log-rank test, and Cox regression were used for survival analysis.
Endpoint events occurred in 65 patients over a median follow-up period of 25.4 months. 13 radiomic features were finally selected. The Rad_Combined model integrating clinical characteristics, CMR parameters and radiomics features achieved the best performance with an AUC of 0.836 and 0.835 in the training and test sets, respectively. High-risk groups with endpoint events defined by the Rad_Combined model had significantly shorter survival time than low-risk group in both the training [Hazard Ratio (HR) = 7.74, P |
| doi_str_mv | 10.1016/j.ijcard.2024.132617 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3113747446</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0167527324012397</els_id><sourcerecordid>3113747446</sourcerecordid><originalsourceid>FETCH-LOGICAL-c241t-e9460a32f8fbd5e1227af6d3e575bdbcc6ad6212248e7486742336749fe8bee13</originalsourceid><addsrcrecordid>eNp9kF1LwzAUhoMobk7_gUgvvWltPtq0N4IMPwYTRRQvQ5qcuoy2mUk32L83pdNLb3LI4Tnn5TwIXeI0wSnOb9aJWSvpdEJSwhJMSY75EZrigrMY84wdo2nAeJwRTifozPt1mqasLItTNKEl5eHDp-jz1dmvzvreqGgnmy1Eto6gW8lOgY6U6SAaQoxU0fPbIq6kD20ntbGtUT4yXaRNI_uBHTDb7u1G9qv9OTqpZePh4lBn6OPh_n3-FC9fHhfzu2WsCMN9DCXLU0lJXdSVzgATwmWdawoZzypdKZVLnZPQZgVwVuScEUrDW9ZQVACYztD1uHfj7PcWfC9a4xU0jezAbr2gGFPOOGN5QNmIKme9d1CLjTOtdHuBUzEoFWsxKhWDUjEqDWNXh4Rt1YL-G_p1GIDbEYBw586AE14ZGPwZB6oX2pr_E34ARoqJPg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3113747446</pqid></control><display><type>article</type><title>Prognostic value of enhanced cine cardiac MRI-based radiomics in dilated cardiomyopathy</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals Complete</source><creator>Li, Xue ; Xu, Yuanwei ; Chen, Xiaoyi ; Liu, Jing ; He, Wenzhang ; Wang, Simeng ; Yin, Hongkun ; Zhou, Xiaoyue ; Song, Yang ; Peng, Liqing ; Chen, Yucheng</creator><creatorcontrib>Li, Xue ; Xu, Yuanwei ; Chen, Xiaoyi ; Liu, Jing ; He, Wenzhang ; Wang, Simeng ; Yin, Hongkun ; Zhou, Xiaoyue ; Song, Yang ; Peng, Liqing ; Chen, Yucheng</creatorcontrib><description>Early precise identification of high-risk dilated cardiomyopathy (DCM) phenotype is essential for clinical decision-making and patient surveillance. The aim of the study was to assess the prognostic value of enhanced cine cardiac magnetic resonance (CMR)-based radiomics in DCM.
We prospectively enrolled 401 (training set: 281; test set: 120) DCM patients. Radiomic features were extracted from enhanced cine images of entire left ventricular wall and selected by the least absolute shrinkage and selection operator. Different predictive models were built using logistic regression classifier to predict all-cause mortality and heart transplantation. Model performances were compared with the area under the receiver operating characteristic curves (AUCs). Kaplan-Meier curves, log-rank test, and Cox regression were used for survival analysis.
Endpoint events occurred in 65 patients over a median follow-up period of 25.4 months. 13 radiomic features were finally selected. The Rad_Combined model integrating clinical characteristics, CMR parameters and radiomics features achieved the best performance with an AUC of 0.836 and 0.835 in the training and test sets, respectively. High-risk groups with endpoint events defined by the Rad_Combined model had significantly shorter survival time than low-risk group in both the training [Hazard Ratio (HR) = 7.74, P < 0.001] and test sets (HR = 4.84, P < 0.001).
The Rad_Combined model might serve as an effective tool to help risk stratification and clinical decision-making for patients with DCM.
Chinese Clinical Trial Registry, ChiCTR1800017058 by the ethics committee of West China hospital,Sichuan University.
•Radiomics can mine medical image information for prognostic evaluation.•The Combined model mainly based on radiomics performed best among all models.•The Combined model could be useful for risk stratification in DCM patients.</description><identifier>ISSN: 0167-5273</identifier><identifier>ISSN: 1874-1754</identifier><identifier>EISSN: 1874-1754</identifier><identifier>DOI: 10.1016/j.ijcard.2024.132617</identifier><identifier>PMID: 39370047</identifier><language>eng</language><publisher>Netherlands: Elsevier B.V</publisher><subject>Adult ; All-cause mortality ; Cardiac magnetic resonance imaging ; Cardiomyopathy, Dilated - diagnostic imaging ; Dilated cardiomyopathy ; Female ; Follow-Up Studies ; Humans ; Magnetic Resonance Imaging, Cine - methods ; Male ; Middle Aged ; Prognosis ; Prospective Studies ; Radiomics</subject><ispartof>International journal of cardiology, 2025-01, Vol.418, p.132617, Article 132617</ispartof><rights>2024 Elsevier B.V.</rights><rights>Copyright © 2024 Elsevier B.V. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c241t-e9460a32f8fbd5e1227af6d3e575bdbcc6ad6212248e7486742336749fe8bee13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0167527324012397$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39370047$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Xue</creatorcontrib><creatorcontrib>Xu, Yuanwei</creatorcontrib><creatorcontrib>Chen, Xiaoyi</creatorcontrib><creatorcontrib>Liu, Jing</creatorcontrib><creatorcontrib>He, Wenzhang</creatorcontrib><creatorcontrib>Wang, Simeng</creatorcontrib><creatorcontrib>Yin, Hongkun</creatorcontrib><creatorcontrib>Zhou, Xiaoyue</creatorcontrib><creatorcontrib>Song, Yang</creatorcontrib><creatorcontrib>Peng, Liqing</creatorcontrib><creatorcontrib>Chen, Yucheng</creatorcontrib><title>Prognostic value of enhanced cine cardiac MRI-based radiomics in dilated cardiomyopathy</title><title>International journal of cardiology</title><addtitle>Int J Cardiol</addtitle><description>Early precise identification of high-risk dilated cardiomyopathy (DCM) phenotype is essential for clinical decision-making and patient surveillance. The aim of the study was to assess the prognostic value of enhanced cine cardiac magnetic resonance (CMR)-based radiomics in DCM.
We prospectively enrolled 401 (training set: 281; test set: 120) DCM patients. Radiomic features were extracted from enhanced cine images of entire left ventricular wall and selected by the least absolute shrinkage and selection operator. Different predictive models were built using logistic regression classifier to predict all-cause mortality and heart transplantation. Model performances were compared with the area under the receiver operating characteristic curves (AUCs). Kaplan-Meier curves, log-rank test, and Cox regression were used for survival analysis.
Endpoint events occurred in 65 patients over a median follow-up period of 25.4 months. 13 radiomic features were finally selected. The Rad_Combined model integrating clinical characteristics, CMR parameters and radiomics features achieved the best performance with an AUC of 0.836 and 0.835 in the training and test sets, respectively. High-risk groups with endpoint events defined by the Rad_Combined model had significantly shorter survival time than low-risk group in both the training [Hazard Ratio (HR) = 7.74, P < 0.001] and test sets (HR = 4.84, P < 0.001).
The Rad_Combined model might serve as an effective tool to help risk stratification and clinical decision-making for patients with DCM.
Chinese Clinical Trial Registry, ChiCTR1800017058 by the ethics committee of West China hospital,Sichuan University.
•Radiomics can mine medical image information for prognostic evaluation.•The Combined model mainly based on radiomics performed best among all models.•The Combined model could be useful for risk stratification in DCM patients.</description><subject>Adult</subject><subject>All-cause mortality</subject><subject>Cardiac magnetic resonance imaging</subject><subject>Cardiomyopathy, Dilated - diagnostic imaging</subject><subject>Dilated cardiomyopathy</subject><subject>Female</subject><subject>Follow-Up Studies</subject><subject>Humans</subject><subject>Magnetic Resonance Imaging, Cine - methods</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Prognosis</subject><subject>Prospective Studies</subject><subject>Radiomics</subject><issn>0167-5273</issn><issn>1874-1754</issn><issn>1874-1754</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2025</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kF1LwzAUhoMobk7_gUgvvWltPtq0N4IMPwYTRRQvQ5qcuoy2mUk32L83pdNLb3LI4Tnn5TwIXeI0wSnOb9aJWSvpdEJSwhJMSY75EZrigrMY84wdo2nAeJwRTifozPt1mqasLItTNKEl5eHDp-jz1dmvzvreqGgnmy1Eto6gW8lOgY6U6SAaQoxU0fPbIq6kD20ntbGtUT4yXaRNI_uBHTDb7u1G9qv9OTqpZePh4lBn6OPh_n3-FC9fHhfzu2WsCMN9DCXLU0lJXdSVzgATwmWdawoZzypdKZVLnZPQZgVwVuScEUrDW9ZQVACYztD1uHfj7PcWfC9a4xU0jezAbr2gGFPOOGN5QNmIKme9d1CLjTOtdHuBUzEoFWsxKhWDUjEqDWNXh4Rt1YL-G_p1GIDbEYBw586AE14ZGPwZB6oX2pr_E34ARoqJPg</recordid><startdate>20250101</startdate><enddate>20250101</enddate><creator>Li, Xue</creator><creator>Xu, Yuanwei</creator><creator>Chen, Xiaoyi</creator><creator>Liu, Jing</creator><creator>He, Wenzhang</creator><creator>Wang, Simeng</creator><creator>Yin, Hongkun</creator><creator>Zhou, Xiaoyue</creator><creator>Song, Yang</creator><creator>Peng, Liqing</creator><creator>Chen, Yucheng</creator><general>Elsevier B.V</general><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>7X8</scope></search><sort><creationdate>20250101</creationdate><title>Prognostic value of enhanced cine cardiac MRI-based radiomics in dilated cardiomyopathy</title><author>Li, Xue ; Xu, Yuanwei ; Chen, Xiaoyi ; Liu, Jing ; He, Wenzhang ; Wang, Simeng ; Yin, Hongkun ; Zhou, Xiaoyue ; Song, Yang ; Peng, Liqing ; Chen, Yucheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c241t-e9460a32f8fbd5e1227af6d3e575bdbcc6ad6212248e7486742336749fe8bee13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2025</creationdate><topic>Adult</topic><topic>All-cause mortality</topic><topic>Cardiac magnetic resonance imaging</topic><topic>Cardiomyopathy, Dilated - diagnostic imaging</topic><topic>Dilated cardiomyopathy</topic><topic>Female</topic><topic>Follow-Up Studies</topic><topic>Humans</topic><topic>Magnetic Resonance Imaging, Cine - methods</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Prognosis</topic><topic>Prospective Studies</topic><topic>Radiomics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Xue</creatorcontrib><creatorcontrib>Xu, Yuanwei</creatorcontrib><creatorcontrib>Chen, Xiaoyi</creatorcontrib><creatorcontrib>Liu, Jing</creatorcontrib><creatorcontrib>He, Wenzhang</creatorcontrib><creatorcontrib>Wang, Simeng</creatorcontrib><creatorcontrib>Yin, Hongkun</creatorcontrib><creatorcontrib>Zhou, Xiaoyue</creatorcontrib><creatorcontrib>Song, Yang</creatorcontrib><creatorcontrib>Peng, Liqing</creatorcontrib><creatorcontrib>Chen, Yucheng</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>International journal of cardiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Xue</au><au>Xu, Yuanwei</au><au>Chen, Xiaoyi</au><au>Liu, Jing</au><au>He, Wenzhang</au><au>Wang, Simeng</au><au>Yin, Hongkun</au><au>Zhou, Xiaoyue</au><au>Song, Yang</au><au>Peng, Liqing</au><au>Chen, Yucheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prognostic value of enhanced cine cardiac MRI-based radiomics in dilated cardiomyopathy</atitle><jtitle>International journal of cardiology</jtitle><addtitle>Int J Cardiol</addtitle><date>2025-01-01</date><risdate>2025</risdate><volume>418</volume><spage>132617</spage><pages>132617-</pages><artnum>132617</artnum><issn>0167-5273</issn><issn>1874-1754</issn><eissn>1874-1754</eissn><abstract>Early precise identification of high-risk dilated cardiomyopathy (DCM) phenotype is essential for clinical decision-making and patient surveillance. The aim of the study was to assess the prognostic value of enhanced cine cardiac magnetic resonance (CMR)-based radiomics in DCM.
We prospectively enrolled 401 (training set: 281; test set: 120) DCM patients. Radiomic features were extracted from enhanced cine images of entire left ventricular wall and selected by the least absolute shrinkage and selection operator. Different predictive models were built using logistic regression classifier to predict all-cause mortality and heart transplantation. Model performances were compared with the area under the receiver operating characteristic curves (AUCs). Kaplan-Meier curves, log-rank test, and Cox regression were used for survival analysis.
Endpoint events occurred in 65 patients over a median follow-up period of 25.4 months. 13 radiomic features were finally selected. The Rad_Combined model integrating clinical characteristics, CMR parameters and radiomics features achieved the best performance with an AUC of 0.836 and 0.835 in the training and test sets, respectively. High-risk groups with endpoint events defined by the Rad_Combined model had significantly shorter survival time than low-risk group in both the training [Hazard Ratio (HR) = 7.74, P < 0.001] and test sets (HR = 4.84, P < 0.001).
The Rad_Combined model might serve as an effective tool to help risk stratification and clinical decision-making for patients with DCM.
Chinese Clinical Trial Registry, ChiCTR1800017058 by the ethics committee of West China hospital,Sichuan University.
•Radiomics can mine medical image information for prognostic evaluation.•The Combined model mainly based on radiomics performed best among all models.•The Combined model could be useful for risk stratification in DCM patients.</abstract><cop>Netherlands</cop><pub>Elsevier B.V</pub><pmid>39370047</pmid><doi>10.1016/j.ijcard.2024.132617</doi></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0167-5273 |
| ispartof | International journal of cardiology, 2025-01, Vol.418, p.132617, Article 132617 |
| issn | 0167-5273 1874-1754 1874-1754 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_3113747446 |
| source | MEDLINE; Elsevier ScienceDirect Journals Complete |
| subjects | Adult All-cause mortality Cardiac magnetic resonance imaging Cardiomyopathy, Dilated - diagnostic imaging Dilated cardiomyopathy Female Follow-Up Studies Humans Magnetic Resonance Imaging, Cine - methods Male Middle Aged Prognosis Prospective Studies Radiomics |
| title | Prognostic value of enhanced cine cardiac MRI-based radiomics in dilated cardiomyopathy |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T22%3A47%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prognostic%20value%20of%20enhanced%20cine%20cardiac%20MRI-based%20radiomics%20in%20dilated%20cardiomyopathy&rft.jtitle=International%20journal%20of%20cardiology&rft.au=Li,%20Xue&rft.date=2025-01-01&rft.volume=418&rft.spage=132617&rft.pages=132617-&rft.artnum=132617&rft.issn=0167-5273&rft.eissn=1874-1754&rft_id=info:doi/10.1016/j.ijcard.2024.132617&rft_dat=%3Cproquest_cross%3E3113747446%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3113747446&rft_id=info:pmid/39370047&rft_els_id=S0167527324012397&rfr_iscdi=true |