Literature DB >> 31127834

Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network.

Kyu Sung Choi1,2,3, Seung Hong Choi4,5,6, Bumseok Jeong1,2,3.   

Abstract

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 were immunohistopathologically diagnosed with 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 multi-dimensional 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, 0.969-0.991) and 91.7%, 92.1%, and 91.5%, respectively, in the test set (AUC, 0.95; 95% confidence interval, 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.
© The Author(s) 2019. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Entities:  

Keywords:  Angiogenesis; Dehydrogenase Mutations; Dynamic Susceptibility Contrast Perfusion-Weighted Imaging; Gliomas; Isocitrate; Recurrent Neural Network

Year:  2019        PMID: 31127834     DOI: 10.1093/neuonc/noz095

Source DB:  PubMed          Journal:  Neuro Oncol        ISSN: 1522-8517            Impact factor:   12.300


  19 in total

Review 1.  Designing deep learning studies in cancer diagnostics.

Authors:  Andreas Kleppe; Ole-Johan Skrede; Sepp De Raedt; Knut Liestøl; David J Kerr; Håvard E Danielsen
Journal:  Nat Rev Cancer       Date:  2021-01-29       Impact factor: 60.716

2.  Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics.

Authors:  Yoon Seong Choi; Sohi Bae; Jong Hee Chang; Seok-Gu Kang; Se Hoon Kim; Jinna Kim; Tyler Hyungtaek Rim; Seung Hong Choi; Rajan Jain; Seung-Koo Lee
Journal:  Neuro Oncol       Date:  2021-02-25       Impact factor: 12.300

3.  Vessel Size Imaging is Associated with IDH Mutation and Patient Survival in Diffuse Lower-Grade Glioma.

Authors:  Houyi Kang; Peng Chen; Hong Guo; Letian Zhang; Yong Tan; Hualiang Xiao; Ao Yang; Jingqin Fang; Weiguo Zhang
Journal:  Cancer Manag Res       Date:  2020-10-08       Impact factor: 3.989

4.  IDH glioma radiogenomics in the era of deep learning.

Authors:  David C Gutman; Robert J Young
Journal:  Neuro Oncol       Date:  2021-02-25       Impact factor: 12.300

5.  Radiomics-based neural network predicts recurrence patterns in glioblastoma using dynamic susceptibility contrast-enhanced MRI.

Authors:  Ka Young Shim; Sung Won Chung; Jae Hak Jeong; Inpyeong Hwang; Chul-Kee Park; Tae Min Kim; Sung-Hye Park; Jae Kyung Won; Joo Ho Lee; Soon-Tae Lee; Roh-Eul Yoo; Koung Mi Kang; Tae Jin Yun; Ji-Hoon Kim; Chul-Ho Sohn; Kyu Sung Choi; Seung Hong Choi
Journal:  Sci Rep       Date:  2021-05-11       Impact factor: 4.379

6.  Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation.

Authors:  Ji Eun Park; Ho Sung Kim; Junkyu Lee; E-Nae Cheong; Ilah Shin; Sung Soo Ahn; Woo Hyun Shim
Journal:  Sci Rep       Date:  2020-12-08       Impact factor: 4.379

7.  Factors Associated With Dysfunction of Glymphatic System in Patients With Glioma.

Authors:  Cheng Hong Toh; Tiing Yee Siow
Journal:  Front Oncol       Date:  2021-09-23       Impact factor: 6.244

Review 8.  Imaging-Genomics in Glioblastoma: Combining Molecular and Imaging Signatures.

Authors:  Dongming Liu; Jiu Chen; Xinhua Hu; Kun Yang; Yong Liu; Guanjie Hu; Honglin Ge; Wenbin Zhang; Hongyi Liu
Journal:  Front Oncol       Date:  2021-07-06       Impact factor: 6.244

9.  Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients.

Authors:  Jing Yan; Bin Zhang; Shuaitong Zhang; Jingliang Cheng; Xianzhi Liu; Weiwei Wang; Yuhao Dong; Lu Zhang; Xiaokai Mo; Qiuying Chen; Jin Fang; Fei Wang; Jie Tian; Shuixing Zhang; Zhenyu Zhang
Journal:  NPJ Precis Oncol       Date:  2021-07-26

10.  Attitudes of the Surgical Team Toward Artificial Intelligence in Neurosurgery: International 2-Stage Cross-Sectional Survey.

Authors:  Hugo Layard Horsfall; Paolo Palmisciano; Danyal Z Khan; William Muirhead; Chan Hee Koh; Danail Stoyanov; Hani J Marcus
Journal:  World Neurosurg       Date:  2020-11-25       Impact factor: 2.104

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.