117 283

Cited 8 times in

Cycle-consistent adversarial networks improves generalizability of radiomics model in grading meningiomas on external validation

DC Field Value Language
dc.contributor.author박예원-
dc.contributor.author안성수-
dc.contributor.author유승찬-
dc.contributor.author이승구-
dc.date.accessioned2022-12-22T01:52:18Z-
dc.date.available2022-12-22T01:52:18Z-
dc.date.issued2022-04-
dc.identifier.urihttps://ir.ymlib.yonsei.ac.kr/handle/22282913/191370-
dc.description.abstractThe heterogeneity of MRI is one of the major reasons for decreased performance of a radiomics model on external validation, limiting the model's generalizability and clinical application. We aimed to establish a generalizable radiomics model to predict meningioma grade on external validation through leveraging Cycle-Consistent Adversarial Networks (CycleGAN). In this retrospective study, 257 patients with meningioma were included in the institutional training set. Radiomic features (n = 214) were extracted from T2-weighted (T2) and contrast-enhanced T1 (T1C) images. After radiomics feature selection, extreme gradient boosting classifiers were developed. The models were validated in the external validation set consisting of 61 patients with meningiomas. To reduce the gap in generalization associated with the inter-institutional heterogeneity of MRI, the smaller image set style of the external validation was translated into the larger image set style of the institutional training set using CycleGAN. On external validation before CycleGAN application, the performance of the combined T2 and T1C models showed an area under the curve (AUC), accuracy, and F1 score of 0.77 (95% confidence interval 0.63-0.91), 70.7%, and 0.54, respectively. After applying CycleGAN, the performance of the combined T2 and T1C models increased, with an AUC, accuracy, and F1 score of 0.83 (95% confidence interval 0.70-0.97), 73.2%, and 0.59, respectively. Quantitative metrics (by Fréchet Inception Distance) showed that CycleGAN can decrease inter-institutional image heterogeneity while preserving predictive information. In conclusion, leveraging CycleGAN may be helpful to increase the generalizability of a radiomics model in differentiating meningioma grade on external validation.-
dc.description.statementOfResponsibilityopen-
dc.languageEnglish-
dc.publisherNature Publishing Group-
dc.relation.isPartOfSCIENTIFIC REPORTS-
dc.rightsCC BY-NC-ND 2.0 KR-
dc.subject.MESHArea Under Curve-
dc.subject.MESHHumans-
dc.subject.MESHMagnetic Resonance Imaging-
dc.subject.MESHMeningeal Neoplasms* / diagnostic imaging-
dc.subject.MESHMeningioma* / diagnostic imaging-
dc.subject.MESHRetrospective Studies-
dc.titleCycle-consistent adversarial networks improves generalizability of radiomics model in grading meningiomas on external validation-
dc.typeArticle-
dc.contributor.collegeCollege of Medicine (의과대학)-
dc.contributor.departmentDept. of Radiology (영상의학교실)-
dc.contributor.googleauthorYae Won Park-
dc.contributor.googleauthorSeo Jeong Shin-
dc.contributor.googleauthorJihwan Eom-
dc.contributor.googleauthorHeirim Lee-
dc.contributor.googleauthorSeng Chan You-
dc.contributor.googleauthorSung Soo Ahn-
dc.contributor.googleauthorSoo Mee Lim-
dc.contributor.googleauthorRae Woong Park-
dc.contributor.googleauthorSeung-Koo Lee-
dc.identifier.doi10.1038/s41598-022-10956-9-
dc.contributor.localIdA05330-
dc.contributor.localIdA02234-
dc.contributor.localIdA02478-
dc.contributor.localIdA02912-
dc.relation.journalcodeJ02646-
dc.identifier.eissn2045-2322-
dc.identifier.pmid35488007-
dc.contributor.alternativeNamePark, Yae-Won-
dc.contributor.affiliatedAuthor박예원-
dc.contributor.affiliatedAuthor안성수-
dc.contributor.affiliatedAuthor유승찬-
dc.contributor.affiliatedAuthor이승구-
dc.citation.volume12-
dc.citation.number1-
dc.citation.startPage7042-
dc.identifier.bibliographicCitationSCIENTIFIC REPORTS, Vol.12(1) : 7042, 2022-04-
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Biomedical Systems Informatics (의생명시스템정보학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.