Cited 7 times in
Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김휘영 | - |
dc.contributor.author | 안성수 | - |
dc.contributor.author | 이승구 | - |
dc.contributor.author | 주비오 | - |
dc.contributor.author | 한경화 | - |
dc.date.accessioned | 2023-07-12T03:06:49Z | - |
dc.date.available | 2023-07-12T03:06:49Z | - |
dc.date.issued | 2023-06 | - |
dc.identifier.issn | 0150-9861 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/195503 | - |
dc.description.abstract | Background and purpose: To investigate the diagnostic performance of fully automated radiomics-based models for multiclass classification of a single enhancing brain tumor among glioblastoma, central nervous system lymphoma, and metastasis. Materials and methods: The training and test sets were comprised of 538 cases (300 glioblastomas, 73 lymphomas, and 165 metastases) and 169 cases (101 glioblastomas, 29 lymphomas, and 39 metastases), respectively. After fully automated segmentation, radiomic features were extracted. Three conventional machine learning classifiers, including least absolute shrinkage and selection operator (LASSO), adaptive boosting (Adaboost), and support vector machine with the linear kernel (SVC), combined with one of four feature selection methods, including forward sequential feature selection, F score, mutual information, and LASSO, were trained. Additionally, one ensemble classifier based on the three classifiers was used. The diagnostic performance of the optimized models was tested in the test set using the accuracy, F1-macro score, and the area under the receiver operating characteristic curve (AUCROC). Results: The best performance was achieved when the LASSO was used as a feature selection method. In the test set, the best performance was achieved by the ensemble classifier, showing an accuracy of 76.3% (95% CI, 70.0-82.7), a F1-macro score of 0.704, and an AUCROC of 0.878. Conclusion: Our fully automated radiomics-based models for multiclass classification might be useful for differential diagnosis of a single enhancing brain tumor with a good diagnostic performance and generalizability. | - |
dc.description.statementOfResponsibility | restriction | - |
dc.language | English, French | - |
dc.publisher | Masson. | - |
dc.relation.isPartOf | JOURNAL OF NEURORADIOLOGY | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.subject.MESH | Brain Neoplasms* / pathology | - |
dc.subject.MESH | Glioblastoma* / diagnostic imaging | - |
dc.subject.MESH | Glioblastoma* / pathology | - |
dc.subject.MESH | Humans | - |
dc.subject.MESH | Lymphoma* / diagnostic imaging | - |
dc.subject.MESH | Machine Learning | - |
dc.subject.MESH | Retrospective Studies | - |
dc.title | Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Dept. of Biomedical Systems Informatics (의생명시스템정보학교실) | - |
dc.contributor.googleauthor | Bio Joo | - |
dc.contributor.googleauthor | Sung Soo Ahn | - |
dc.contributor.googleauthor | Chansik An | - |
dc.contributor.googleauthor | Kyunghwa Han | - |
dc.contributor.googleauthor | Dongmin Choi | - |
dc.contributor.googleauthor | Hwiyoung Kim | - |
dc.contributor.googleauthor | Ji Eun Park | - |
dc.contributor.googleauthor | Ho Sung Kim | - |
dc.contributor.googleauthor | Seung-Koo Lee | - |
dc.identifier.doi | 10.1016/j.neurad.2022.11.001 | - |
dc.contributor.localId | A05971 | - |
dc.contributor.localId | A02234 | - |
dc.contributor.localId | A02912 | - |
dc.contributor.localId | A05842 | - |
dc.contributor.localId | A04267 | - |
dc.relation.journalcode | J03937 | - |
dc.identifier.pmid | 36370829 | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S0150986122001663 | - |
dc.subject.keyword | Brain metastasis | - |
dc.subject.keyword | Brain tumor | - |
dc.subject.keyword | Central nervous system lymphoma | - |
dc.subject.keyword | Glioblastoma | - |
dc.subject.keyword | Machine learning | - |
dc.subject.keyword | Radiomics | - |
dc.contributor.alternativeName | Kim, Hwiyoung | - |
dc.contributor.affiliatedAuthor | 김휘영 | - |
dc.contributor.affiliatedAuthor | 안성수 | - |
dc.contributor.affiliatedAuthor | 이승구 | - |
dc.contributor.affiliatedAuthor | 주비오 | - |
dc.contributor.affiliatedAuthor | 한경화 | - |
dc.citation.volume | 50 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 388 | - |
dc.citation.endPage | 395 | - |
dc.identifier.bibliographicCitation | JOURNAL OF NEURORADIOLOGY, Vol.50(4) : 388-395, 2023-06 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.