Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, KS | - |
dc.contributor.author | Seung Hong Choi | - |
dc.contributor.author | Jeong, B | - |
dc.date.available | 2020-01-31T00:55:10Z | - |
dc.date.created | 2019-11-18 | - |
dc.date.issued | 2019-09 | - |
dc.identifier.issn | 1522-8517 | - |
dc.identifier.uri | https://pr.ibs.re.kr/handle/8788114/6883 | - |
dc.description.abstract | © 2019 The Author(s). Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved.Background: The aim of this study was to predict isocitrate dehydrogenase (IDH) genotypes of gliomas using an interpretable deep learning application for dynamic susceptibility contrast (DSC) perfusion MRI. Methods: Four hundred sixty-three patients with gliomas who underwent preoperative MRI were enrolled in the study. All the patients had immunohistopathologic diagnoses of either IDH-wildtype or IDH-mutant gliomas. Tumor subregions were segmented using a convolutional neural network followed by manual correction. DSC perfusion MRI was performed to obtain T2∗ susceptibility signal intensity-time curves from each subregion of the tumors: enhancing tumor, non-enhancing tumor, peritumoral edema, and whole tumor. These, with arterial input functions, were fed into a neural network as multidimensional inputs. A convolutional long short-term memory model with an attention mechanism was developed to predict IDH genotypes. Receiver operating characteristics analysis was performed to evaluate the model. Results: The IDH genotype predictions had an accuracy, sensitivity, and specificity of 92.8%, 92.6%, and 93.1%, respectively, in the validation set (area under the curve [AUC], 0.98; 95% confidence interval [CI], 0.969-0.991) and 91.7%, 92.1%, and 91.5%, respectively, in the test set (AUC, 0.95; 95% CI, 0.898-0.982). In temporal feature analysis, T2∗ susceptibility signal intensity-time curves obtained from DSC perfusion MRI with attention weights demonstrated high attention on the combination of the end of the pre-contrast baseline, up/downslopes of signal drops, and/or post-bolus plateaus for the curves used to predict IDH genotype. Conclusions: We developed an explainable recurrent neural network model based on DSC perfusion MRI to predict IDH genotypes in gliomas | - |
dc.description.uri | 1 | - |
dc.language | 영어 | - |
dc.publisher | OXFORD UNIV PRESS INC | - |
dc.subject | Angiogenesis | - |
dc.subject | Dynamic susceptibility contrast perfusion-weighted imaging | - |
dc.subject | Gliomas | - |
dc.subject | Isocitrate dehydrogenase mutations | - |
dc.subject | Recurrent neural network | - |
dc.title | Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.identifier.wosid | 000493070900014 | - |
dc.identifier.scopusid | 2-s2.0-85073448728 | - |
dc.identifier.rimsid | 70398 | - |
dc.contributor.affiliatedAuthor | Seung Hong Choi | - |
dc.identifier.doi | 10.1093/neuonc/noz095 | - |
dc.identifier.bibliographicCitation | NEURO-ONCOLOGY, v.21, no.9, pp.1197 - 1209 | - |
dc.citation.title | NEURO-ONCOLOGY | - |
dc.citation.volume | 21 | - |
dc.citation.number | 9 | - |
dc.citation.startPage | 1197 | - |
dc.citation.endPage | 1209 | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | HIGH-GRADE GLIOMAS | - |
dc.subject.keywordPlus | CENTRAL-NERVOUS-SYSTEM | - |
dc.subject.keywordPlus | MUTATION STATUS | - |
dc.subject.keywordPlus | BRAIN | - |
dc.subject.keywordPlus | TEMOZOLOMIDE | - |
dc.subject.keywordPlus | SURVIVAL | - |
dc.subject.keywordPlus | TUMORS | - |
dc.subject.keywordAuthor | angiogenesis | - |
dc.subject.keywordAuthor | dynamic susceptibility contrast perfusion-weighted imaging | - |
dc.subject.keywordAuthor | gliomas | - |
dc.subject.keywordAuthor | isocitrate dehydrogenase mutations | - |
dc.subject.keywordAuthor | recurrent neural network | - |