Development of a Machine Learning Classifier Based on Radiomic Features Extracted From Post-Contrast 3D T1-Weighted MR Images to Distinguish Glioblastoma From Solitary Brain Metastasis

Frontiers in Oncology

Samy Ammari¹  Frederic Dhermain³  Eric Deutsch³  Sylvain Reuzé³  Alexandre Carré³  Charlotte Robert³  Catherine Oppenheim⁴  Myriam Edjlali⁴  Alix de Causans⁴  Alexandre Roux⁷  Johan Pallud⁷  Edouard Dezamis⁷  Arnault Tauziède-Espariat⁸  Pascale Varlet⁹ 

[1] BioMaps UMR1281, Université Paris-Saclay, CNRS, INSERM, CEA, Orsay, France;Département de Radiologie, Gustave Roussy, Université Paris Saclay, Villejuif, France;Département de Radiothérapie, Gustave Roussy, Université Paris Saclay, Villejuif, France;Inserm, UMR1266, IMA-Brain, Institut de Psychiatrie et Neurosciences, Paris, France;Neuroradiology Department, Hôpital Sainte-Anne, GHU-Paris Psychiatrie et Neurosciences, Paris, France;Radiothérapie Moléculaire et Innovation Thérapeutique, INSERM UMR1030, Gustave Roussy Cancer Campus, Université Paris Saclay, Villejuif, France;Service de Neurochirurgie, GHU Paris – Psychiatrie et Neurosciences – Hôpital Sainte-Anne, Paris, France;Service de Neuropathologie, GHU Paris – Psychiatrie et Neurosciences – Hôpital Sainte-Anne, Paris, France;Université de Paris, Paris, France;

关键词: radiomics;    machine learning;    glioblastoma;    brain metastasis;    diagnostic decision support system;   

DOI  :  10.3389/fonc.2021.638262

来源: DOAJ

【 摘 要 】

ObjectivesTo differentiate Glioblastomas (GBM) and Brain Metastases (BM) using a radiomic features-based Machine Learning (ML) classifier trained from post-contrast three-dimensional T1-weighted (post-contrast 3DT1) MR imaging, and compare its performance in medical diagnosis versus human experts, on a testing cohort.MethodsWe enrolled 143 patients (71 GBM and 72 BM) in a retrospective bicentric study from January 2010 to May 2019 to train the classifier. Post-contrast 3DT1 MR images were performed on a 3-Tesla MR unit and 100 radiomic features were extracted. Selection and optimization of the Machine Learning (ML) classifier was performed using a nested cross-validation. Sensitivity, specificity, balanced accuracy, and area under the receiver operating characteristic curve (AUC) were calculated as performance metrics. The model final performance was cross-validated, then evaluated on a test set of 37 patients, and compared to human blind reading using a McNemar’s test.ResultsThe ML classifier had a mean [95% confidence interval] sensitivity of 85% [77; 94], a specificity of 87% [78; 97], a balanced accuracy of 86% [80; 92], and an AUC of 92% [87; 97] with cross-validation. Sensitivity, specificity, balanced accuracy and AUC were equal to 75, 86, 80 and 85% on the test set. Sphericity 3D radiomic index highlighted the highest coefficient in the logistic regression model. There were no statistical significant differences observed between the performance of the classifier and the experts’ blinded examination.ConclusionsThe proposed diagnostic support system based on radiomic features extracted from post-contrast 3DT1 MR images helps in differentiating solitary BM from GBM with high diagnosis performance and generalizability.

【 授权许可】

Unknown