A radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure in patients with hepatocellular carcinoma
To develop and validate a radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC). One hundred twelve consecutive HCC patients who underwent hepatectomy were included in the study pool (training cohort: n = 80,...
Gespeichert in:
| Veröffentlicht in: | Surgical oncology 2019-03, Vol.28, p.78-85 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 85 |
|---|---|
| container_issue | |
| container_start_page | 78 |
| container_title | Surgical oncology |
| container_volume | 28 |
| creator | Cai, Wei He, Baochun Hu, Min Zhang, Wenyu Xiao, Deqiang Yu, Hao Song, Qi Xiang, Nan Yang, Jian He, Songsheng Huang, Yaohuan Huang, Wenjie Jia, Fucang Fang, Chihua |
| description | To develop and validate a radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC).
One hundred twelve consecutive HCC patients who underwent hepatectomy were included in the study pool (training cohort: n = 80, validation cohort: n = 32), and another 13 patients were included in a pilot prospective analysis. A total of 713 radiomics features were extracted from portal-phase computed tomography (CT) images. A logistic regression was used to construct a radiomics score (Rad-score). Then a nomogram, including Rad-score and other risk factors, was built with a multivariate logistic regression model. The discrimination, calibration and clinical utility of nomogram were evaluated.
The Rad-score could predict PHLF with an AUC of 0.822 (95% CI, 0.726–0.917) in the training cohort and of 0.762 (95% CI, 0.576–0.948) in the validation cohort; however, the approach could not completely outmatch the existing methods (CP [Child-Pugh], MELD [Model of End Stage Liver Disease], ALBI [albumin-bilirubin]). The individual predictive nomogram that included the Rad-score, MELD and performance status (PS) showed better discrimination with an AUC of 0.864 (95% CI, 0.786–0.942), which was higher than the AUCs of the conventional methods (nomogram vs CP, MELD, and ALBI at P |
| doi_str_mv | 10.1016/j.suronc.2018.11.013 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2190093150</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0960740418302305</els_id><sourcerecordid>2308516124</sourcerecordid><originalsourceid>FETCH-LOGICAL-c390t-d448b7b120133f3350305de216a0d9bc9902b82f24c293fae60a9b4332e492ab3</originalsourceid><addsrcrecordid>eNp9kUFv1DAQhS0Eotst_wAhS1y4JJ2xvUl8QaoqKEiVeqFny3Em1KskDnZS1B_A_8a7Wzhw4GRZ_vzmzXuMvUUoEbC63JdpjWFypQBsSsQSUL5gG2xqXUgp4CXbgK6gqBWoM3ae0h4Aqlrga3YmodmhxnrDfl3xaDsfRu9S0dpEHZ_CGL5HO_I-RL48EJ8jhZmiXfzj8dJ5t_gw8dDzOaRMzHYht4TxiQ8Ziby3flgjcT_x_ORpWhL_6ZcHfkSDo2FYBxu5s9H5PM5esFe9HRK9eT637P7zp2_XX4rbu5uv11e3hZMalqJTqmnrFvPGUvZS7kDCriOBlYVOt05rEG0jeqGc0LK3VIHVrcppkNLCtnLLPpx05xh-rJQWM_p0sGMnCmsyAjWAlpiFt-z9P-g-rHHK7ow4xlehUJlSJ8rFkFKk3szRjzY-GQRzqMnszakmc6jJIJqD9y179yy-tiN1fz_96SUDH08A5TQePUWTXM7R5exjjtp0wf9_wm86vqeb</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2308516124</pqid></control><display><type>article</type><title>A radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure in patients with hepatocellular carcinoma</title><source>Elsevier ScienceDirect Journals</source><creator>Cai, Wei ; He, Baochun ; Hu, Min ; Zhang, Wenyu ; Xiao, Deqiang ; Yu, Hao ; Song, Qi ; Xiang, Nan ; Yang, Jian ; He, Songsheng ; Huang, Yaohuan ; Huang, Wenjie ; Jia, Fucang ; Fang, Chihua</creator><creatorcontrib>Cai, Wei ; He, Baochun ; Hu, Min ; Zhang, Wenyu ; Xiao, Deqiang ; Yu, Hao ; Song, Qi ; Xiang, Nan ; Yang, Jian ; He, Songsheng ; Huang, Yaohuan ; Huang, Wenjie ; Jia, Fucang ; Fang, Chihua</creatorcontrib><description>To develop and validate a radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC).
One hundred twelve consecutive HCC patients who underwent hepatectomy were included in the study pool (training cohort: n = 80, validation cohort: n = 32), and another 13 patients were included in a pilot prospective analysis. A total of 713 radiomics features were extracted from portal-phase computed tomography (CT) images. A logistic regression was used to construct a radiomics score (Rad-score). Then a nomogram, including Rad-score and other risk factors, was built with a multivariate logistic regression model. The discrimination, calibration and clinical utility of nomogram were evaluated.
The Rad-score could predict PHLF with an AUC of 0.822 (95% CI, 0.726–0.917) in the training cohort and of 0.762 (95% CI, 0.576–0.948) in the validation cohort; however, the approach could not completely outmatch the existing methods (CP [Child-Pugh], MELD [Model of End Stage Liver Disease], ALBI [albumin-bilirubin]). The individual predictive nomogram that included the Rad-score, MELD and performance status (PS) showed better discrimination with an AUC of 0.864 (95% CI, 0.786–0.942), which was higher than the AUCs of the conventional methods (nomogram vs CP, MELD, and ALBI at P < 0.001, P < 0.005, and P < 0.005, respectively). In the validation cohort, the nomogram discrimination was also superior to those of the other three methods (AUC: 0.896; 95% CI, 0.774–1.000). The calibration curves showed good agreement in both cohorts, and the decision curve analysis of the entire cohort revealed that the nomogram was clinically useful. A pilot prospective analysis showed that the radiomics nomogram could predict PHLF with an AUC of 0.833 (95% CI, 0.591–1.000).
A nomogram based on the Rad-score, MELD, and PS can predict PHLF.
•Hepatectomy is a mainstay of treatment for patients with hepatocellular carcinoma (HCC).•Identification of patients at risk of posthepatectomy liver failure (PHLF) before surgery is important.•PHLF could be accurately predicted in a radiomics approach at low cost.</description><identifier>ISSN: 0960-7404</identifier><identifier>EISSN: 1879-3320</identifier><identifier>DOI: 10.1016/j.suronc.2018.11.013</identifier><identifier>PMID: 30851917</identifier><language>eng</language><publisher>Netherlands: Elsevier Ltd</publisher><subject>Albumins ; Bilirubin ; Body mass index ; Calibration ; Computed tomography ; Decision analysis ; Feature extraction ; Hepatectomy ; Hepatitis ; Hepatocellular carcinoma ; Liver ; Liver cancer ; Liver diseases ; Liver failure ; Nomogram ; Nomograms ; Patients ; Predictions ; Radiomics ; Regression analysis ; Regression models ; Risk analysis ; Risk factors ; Training</subject><ispartof>Surgical oncology, 2019-03, Vol.28, p.78-85</ispartof><rights>2018 Elsevier Ltd</rights><rights>Copyright © 2018 Elsevier Ltd. All rights reserved.</rights><rights>2018. Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c390t-d448b7b120133f3350305de216a0d9bc9902b82f24c293fae60a9b4332e492ab3</citedby><cites>FETCH-LOGICAL-c390t-d448b7b120133f3350305de216a0d9bc9902b82f24c293fae60a9b4332e492ab3</cites><orcidid>0000-0002-1726-7858</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0960740418302305$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30851917$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Cai, Wei</creatorcontrib><creatorcontrib>He, Baochun</creatorcontrib><creatorcontrib>Hu, Min</creatorcontrib><creatorcontrib>Zhang, Wenyu</creatorcontrib><creatorcontrib>Xiao, Deqiang</creatorcontrib><creatorcontrib>Yu, Hao</creatorcontrib><creatorcontrib>Song, Qi</creatorcontrib><creatorcontrib>Xiang, Nan</creatorcontrib><creatorcontrib>Yang, Jian</creatorcontrib><creatorcontrib>He, Songsheng</creatorcontrib><creatorcontrib>Huang, Yaohuan</creatorcontrib><creatorcontrib>Huang, Wenjie</creatorcontrib><creatorcontrib>Jia, Fucang</creatorcontrib><creatorcontrib>Fang, Chihua</creatorcontrib><title>A radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure in patients with hepatocellular carcinoma</title><title>Surgical oncology</title><addtitle>Surg Oncol</addtitle><description>To develop and validate a radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC).
One hundred twelve consecutive HCC patients who underwent hepatectomy were included in the study pool (training cohort: n = 80, validation cohort: n = 32), and another 13 patients were included in a pilot prospective analysis. A total of 713 radiomics features were extracted from portal-phase computed tomography (CT) images. A logistic regression was used to construct a radiomics score (Rad-score). Then a nomogram, including Rad-score and other risk factors, was built with a multivariate logistic regression model. The discrimination, calibration and clinical utility of nomogram were evaluated.
The Rad-score could predict PHLF with an AUC of 0.822 (95% CI, 0.726–0.917) in the training cohort and of 0.762 (95% CI, 0.576–0.948) in the validation cohort; however, the approach could not completely outmatch the existing methods (CP [Child-Pugh], MELD [Model of End Stage Liver Disease], ALBI [albumin-bilirubin]). The individual predictive nomogram that included the Rad-score, MELD and performance status (PS) showed better discrimination with an AUC of 0.864 (95% CI, 0.786–0.942), which was higher than the AUCs of the conventional methods (nomogram vs CP, MELD, and ALBI at P < 0.001, P < 0.005, and P < 0.005, respectively). In the validation cohort, the nomogram discrimination was also superior to those of the other three methods (AUC: 0.896; 95% CI, 0.774–1.000). The calibration curves showed good agreement in both cohorts, and the decision curve analysis of the entire cohort revealed that the nomogram was clinically useful. A pilot prospective analysis showed that the radiomics nomogram could predict PHLF with an AUC of 0.833 (95% CI, 0.591–1.000).
A nomogram based on the Rad-score, MELD, and PS can predict PHLF.
•Hepatectomy is a mainstay of treatment for patients with hepatocellular carcinoma (HCC).•Identification of patients at risk of posthepatectomy liver failure (PHLF) before surgery is important.•PHLF could be accurately predicted in a radiomics approach at low cost.</description><subject>Albumins</subject><subject>Bilirubin</subject><subject>Body mass index</subject><subject>Calibration</subject><subject>Computed tomography</subject><subject>Decision analysis</subject><subject>Feature extraction</subject><subject>Hepatectomy</subject><subject>Hepatitis</subject><subject>Hepatocellular carcinoma</subject><subject>Liver</subject><subject>Liver cancer</subject><subject>Liver diseases</subject><subject>Liver failure</subject><subject>Nomogram</subject><subject>Nomograms</subject><subject>Patients</subject><subject>Predictions</subject><subject>Radiomics</subject><subject>Regression analysis</subject><subject>Regression models</subject><subject>Risk analysis</subject><subject>Risk factors</subject><subject>Training</subject><issn>0960-7404</issn><issn>1879-3320</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp9kUFv1DAQhS0Eotst_wAhS1y4JJ2xvUl8QaoqKEiVeqFny3Em1KskDnZS1B_A_8a7Wzhw4GRZ_vzmzXuMvUUoEbC63JdpjWFypQBsSsQSUL5gG2xqXUgp4CXbgK6gqBWoM3ae0h4Aqlrga3YmodmhxnrDfl3xaDsfRu9S0dpEHZ_CGL5HO_I-RL48EJ8jhZmiXfzj8dJ5t_gw8dDzOaRMzHYht4TxiQ8Ziby3flgjcT_x_ORpWhL_6ZcHfkSDo2FYBxu5s9H5PM5esFe9HRK9eT637P7zp2_XX4rbu5uv11e3hZMalqJTqmnrFvPGUvZS7kDCriOBlYVOt05rEG0jeqGc0LK3VIHVrcppkNLCtnLLPpx05xh-rJQWM_p0sGMnCmsyAjWAlpiFt-z9P-g-rHHK7ow4xlehUJlSJ8rFkFKk3szRjzY-GQRzqMnszakmc6jJIJqD9y179yy-tiN1fz_96SUDH08A5TQePUWTXM7R5exjjtp0wf9_wm86vqeb</recordid><startdate>201903</startdate><enddate>201903</enddate><creator>Cai, Wei</creator><creator>He, Baochun</creator><creator>Hu, Min</creator><creator>Zhang, Wenyu</creator><creator>Xiao, Deqiang</creator><creator>Yu, Hao</creator><creator>Song, Qi</creator><creator>Xiang, Nan</creator><creator>Yang, Jian</creator><creator>He, Songsheng</creator><creator>Huang, Yaohuan</creator><creator>Huang, Wenjie</creator><creator>Jia, Fucang</creator><creator>Fang, Chihua</creator><general>Elsevier Ltd</general><general>Elsevier Limited</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>8FD</scope><scope>FR3</scope><scope>K9.</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-1726-7858</orcidid></search><sort><creationdate>201903</creationdate><title>A radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure in patients with hepatocellular carcinoma</title><author>Cai, Wei ; He, Baochun ; Hu, Min ; Zhang, Wenyu ; Xiao, Deqiang ; Yu, Hao ; Song, Qi ; Xiang, Nan ; Yang, Jian ; He, Songsheng ; Huang, Yaohuan ; Huang, Wenjie ; Jia, Fucang ; Fang, Chihua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c390t-d448b7b120133f3350305de216a0d9bc9902b82f24c293fae60a9b4332e492ab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Albumins</topic><topic>Bilirubin</topic><topic>Body mass index</topic><topic>Calibration</topic><topic>Computed tomography</topic><topic>Decision analysis</topic><topic>Feature extraction</topic><topic>Hepatectomy</topic><topic>Hepatitis</topic><topic>Hepatocellular carcinoma</topic><topic>Liver</topic><topic>Liver cancer</topic><topic>Liver diseases</topic><topic>Liver failure</topic><topic>Nomogram</topic><topic>Nomograms</topic><topic>Patients</topic><topic>Predictions</topic><topic>Radiomics</topic><topic>Regression analysis</topic><topic>Regression models</topic><topic>Risk analysis</topic><topic>Risk factors</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cai, Wei</creatorcontrib><creatorcontrib>He, Baochun</creatorcontrib><creatorcontrib>Hu, Min</creatorcontrib><creatorcontrib>Zhang, Wenyu</creatorcontrib><creatorcontrib>Xiao, Deqiang</creatorcontrib><creatorcontrib>Yu, Hao</creatorcontrib><creatorcontrib>Song, Qi</creatorcontrib><creatorcontrib>Xiang, Nan</creatorcontrib><creatorcontrib>Yang, Jian</creatorcontrib><creatorcontrib>He, Songsheng</creatorcontrib><creatorcontrib>Huang, Yaohuan</creatorcontrib><creatorcontrib>Huang, Wenjie</creatorcontrib><creatorcontrib>Jia, Fucang</creatorcontrib><creatorcontrib>Fang, Chihua</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Surgical oncology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cai, Wei</au><au>He, Baochun</au><au>Hu, Min</au><au>Zhang, Wenyu</au><au>Xiao, Deqiang</au><au>Yu, Hao</au><au>Song, Qi</au><au>Xiang, Nan</au><au>Yang, Jian</au><au>He, Songsheng</au><au>Huang, Yaohuan</au><au>Huang, Wenjie</au><au>Jia, Fucang</au><au>Fang, Chihua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure in patients with hepatocellular carcinoma</atitle><jtitle>Surgical oncology</jtitle><addtitle>Surg Oncol</addtitle><date>2019-03</date><risdate>2019</risdate><volume>28</volume><spage>78</spage><epage>85</epage><pages>78-85</pages><issn>0960-7404</issn><eissn>1879-3320</eissn><abstract>To develop and validate a radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC).
One hundred twelve consecutive HCC patients who underwent hepatectomy were included in the study pool (training cohort: n = 80, validation cohort: n = 32), and another 13 patients were included in a pilot prospective analysis. A total of 713 radiomics features were extracted from portal-phase computed tomography (CT) images. A logistic regression was used to construct a radiomics score (Rad-score). Then a nomogram, including Rad-score and other risk factors, was built with a multivariate logistic regression model. The discrimination, calibration and clinical utility of nomogram were evaluated.
The Rad-score could predict PHLF with an AUC of 0.822 (95% CI, 0.726–0.917) in the training cohort and of 0.762 (95% CI, 0.576–0.948) in the validation cohort; however, the approach could not completely outmatch the existing methods (CP [Child-Pugh], MELD [Model of End Stage Liver Disease], ALBI [albumin-bilirubin]). The individual predictive nomogram that included the Rad-score, MELD and performance status (PS) showed better discrimination with an AUC of 0.864 (95% CI, 0.786–0.942), which was higher than the AUCs of the conventional methods (nomogram vs CP, MELD, and ALBI at P < 0.001, P < 0.005, and P < 0.005, respectively). In the validation cohort, the nomogram discrimination was also superior to those of the other three methods (AUC: 0.896; 95% CI, 0.774–1.000). The calibration curves showed good agreement in both cohorts, and the decision curve analysis of the entire cohort revealed that the nomogram was clinically useful. A pilot prospective analysis showed that the radiomics nomogram could predict PHLF with an AUC of 0.833 (95% CI, 0.591–1.000).
A nomogram based on the Rad-score, MELD, and PS can predict PHLF.
•Hepatectomy is a mainstay of treatment for patients with hepatocellular carcinoma (HCC).•Identification of patients at risk of posthepatectomy liver failure (PHLF) before surgery is important.•PHLF could be accurately predicted in a radiomics approach at low cost.</abstract><cop>Netherlands</cop><pub>Elsevier Ltd</pub><pmid>30851917</pmid><doi>10.1016/j.suronc.2018.11.013</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-1726-7858</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0960-7404 |
| ispartof | Surgical oncology, 2019-03, Vol.28, p.78-85 |
| issn | 0960-7404 1879-3320 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2190093150 |
| source | Elsevier ScienceDirect Journals |
| subjects | Albumins Bilirubin Body mass index Calibration Computed tomography Decision analysis Feature extraction Hepatectomy Hepatitis Hepatocellular carcinoma Liver Liver cancer Liver diseases Liver failure Nomogram Nomograms Patients Predictions Radiomics Regression analysis Regression models Risk analysis Risk factors Training |
| title | A radiomics-based nomogram for the preoperative prediction of posthepatectomy liver failure in patients with hepatocellular carcinoma |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T06%3A35%3A17IST&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=A%20radiomics-based%20nomogram%20for%20the%20preoperative%20prediction%20of%20posthepatectomy%20liver%20failure%20in%20patients%20with%20hepatocellular%20carcinoma&rft.jtitle=Surgical%20oncology&rft.au=Cai,%20Wei&rft.date=2019-03&rft.volume=28&rft.spage=78&rft.epage=85&rft.pages=78-85&rft.issn=0960-7404&rft.eissn=1879-3320&rft_id=info:doi/10.1016/j.suronc.2018.11.013&rft_dat=%3Cproquest_cross%3E2308516124%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=2308516124&rft_id=info:pmid/30851917&rft_els_id=S0960740418302305&rfr_iscdi=true |