Machine‐learning based radiogenomics analysis of
            MRI
            features and metagenes in glioblastoma multiforme patients with different survival time

Abstract BACKGROUND Previously, we have shown that combined whole-exome sequencing (WES) and genome-wide somatic copy number alteration (SCNA) information can separate IDH1/2-wildtype glioblastoma into two prognostic molecular subtypes (Group 1 and Group 2) and that these subtypes cannot be distinguished by epigenetic or clinical features. However, the potential for radiographic features to discriminate between these molecular subtypes has not been established. METHODS Radiogenomic features (n=35,400) were extracted from 46 multiparametric, pre-operative magnetic resonance imaging (MRI) of IDH1/2-wildtype glioblastoma patients from The Cancer Imaging Archive, all of whom have corresponding WES and SCNA data in The Cancer Genome Atlas. We developed a novel feature selection method that leverages the structure of extracted radiogenomic MRI features to mitigate the dimensionality challenge posed by the disparity between the number of features and patients in our cohort. Seven traditional machine learning classifiers were trained to distinguish Group 1 versus Group 2 using our feature selection method. Our feature selection was compared to lasso feature selection, recursive feature elimination, and variance thresholding. RESULTS We are able to classify Group 1 versus Group 2 glioblastomas with a cross-validated area under the curve (AUC) score of 0.82 using ridge logistic regression and our proposed feature selection method, which reduces the size of our feature set from 35,400 to 288. An interrogation of the selected features suggests that features describing contours in the T2 abnormality region on the FLAIR MRI modality may best distinguish these two groups from one another. CONCLUSIONS We successfully trained a machine learning model that allows for relevant targeted feature extraction from standard MRI to accurately predict molecularly-defined risk-stratifying IDH1/2-wildtype glioblastoma patient groups. This algorithm may be applied to future prospective studies to assess the utility of MRI as a surrogate for costly prognostic genomic studies.

Download Full-text

Radiogenomic modeling predicts survival-associated prognostic groups in glioblastoma

Neuro-Oncology Advances ◽

10.1093/noajnl/vdab004 ◽

2021 ◽

Vol 3 (1) ◽

Author(s):

Nicholas Nuechterlein ◽

Beibin Li ◽

Abdullah Feroze ◽

Eric C Holland ◽

Linda Shapiro ◽

...

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Molecular Subtypes ◽

Feature Selection Method ◽

Area Under The Curve ◽

Selection Method ◽

Recursive Feature Elimination ◽

Signal Abnormality ◽

Mri Features ◽

Mri Scans

Abstract Background Combined whole-exome sequencing (WES) and somatic copy number alteration (SCNA) information can separate isocitrate dehydrogenase (IDH)1/2-wildtype glioblastoma into two prognostic molecular subtypes, which cannot be distinguished by epigenetic or clinical features. The potential for radiographic features to discriminate between these molecular subtypes has yet to be established. Methods Radiologic features (n = 35 340) were extracted from 46 multisequence, pre-operative magnetic resonance imaging (MRI) scans of IDH1/2-wildtype glioblastoma patients from The Cancer Imaging Archive (TCIA), all of whom have corresponding WES/SCNA data. We developed a novel feature selection method that leverages the structure of extracted MRI features to mitigate the dimensionality challenge posed by the disparity between a large number of features and the limited patients in our cohort. Six traditional machine learning classifiers were trained to distinguish molecular subtypes using our feature selection method, which was compared to least absolute shrinkage and selection operator (LASSO) feature selection, recursive feature elimination, and variance thresholding. Results We were able to classify glioblastomas into two prognostic subgroups with a cross-validated area under the curve score of 0.80 (±0.03) using ridge logistic regression on the 15-dimensional principle component analysis (PCA) embedding of the features selected by our novel feature selection method. An interrogation of the selected features suggested that features describing contours in the T2 signal abnormality region on the T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI sequence may best distinguish these two groups from one another. Conclusions We successfully trained a machine learning model that allows for relevant targeted feature extraction from standard MRI to accurately predict molecularly-defined risk-stratifying IDH1/2-wildtype glioblastoma patient groups.

Download Full-text

Improved outcome prediction of oropharyngeal cancer by combining clinical and MRI features in machine learning models

European Journal of Radiology ◽

10.1016/j.ejrad.2021.109701 ◽

2021 ◽

pp. 109701

Author(s):

Paula Bos ◽

Michiel W.M. van den Brekel ◽

Zeno A.R. Gouw ◽

Abrahim Al-Mamgani ◽

Marjaneh Taghavi ◽

...

Keyword(s):

Machine Learning ◽

Oropharyngeal Cancer ◽

Outcome Prediction ◽

Learning Models ◽

Mri Features ◽

Improved Outcome ◽

Machine Learning Models

Download Full-text

NCOG-31. DEVELOPMENT AND EVALUATION OF PROGNOSTIC MODELS TO PREDICT SURVIVAL OF PATIENTS WITH GLIOBLASTOMA MULTIFORME

Neuro-Oncology ◽

10.1093/neuonc/noaa215.569 ◽

2020 ◽

Vol 22 (Supplement_2) ◽

pp. ii135-ii136

Author(s):

John Lin ◽

Michelle Mai ◽

Saba Paracha

Keyword(s):

Machine Learning ◽

Decision Support ◽

Glioblastoma Multiforme ◽

Random Forest ◽

Regression Model ◽

Clinical Decision Support ◽

Multivariate Regression ◽

Visual Analysis ◽

Clinical Decision ◽

Prognostic Models

Abstract Glioblastoma multiforme (GBM), the most common form of glioma, is a malignant tumor with a high risk of mortality. By providing accurate survival estimates, prognostic models have been identified as promising tools in clinical decision support. In this study, we produced and validated two machine learning-based models to predict survival time for GBM patients. Publicly available clinical and genomic data from The Cancer Genome Atlas (TCGA) and Broad Institute GDAC Firehouse were obtained through cBioPortal. Random forest and multivariate regression models were created to predict survival. Predictive accuracy was assessed and compared through mean absolute error (MAE) and root mean square error (RMSE) calculations. 619 GBM patients were included in the dataset. There were 381 (62.9%) cases of recurrence/progression and 53 (8.7%) cases of disease-free survival. The MAE and RMSE values were 0.553 and 0.887 years respectively for the random forest regression model, and they were 1.756 and 2.451 years respectively for the multivariate regression model. Both models accurately predicted overall survival. Comparison of models through MAE, RMSE, and visual analysis produced higher accuracy values for random forest than multivariate linear regression. Further investigation on feature selection and model optimization may improve predictive power. These findings suggest that using machine learning in GBM prognostic modeling will improve clinical decision support. *Co-first authors.

Download Full-text

MRI-based machine learning for determining quantitative and qualitative characteristics affecting the survival of glioblastoma multiforme

Magnetic Resonance Imaging ◽

10.1016/j.mri.2021.10.023 ◽

2021 ◽

Author(s):

Mahdie Jajroudi ◽

Milad Enferadi ◽

Amir Azar Homayoun ◽

Reza Reiazi

Keyword(s):

Machine Learning ◽

Glioblastoma Multiforme ◽

Qualitative Characteristics

Download Full-text

Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients

Frontiers in Neurology ◽

10.3389/fneur.2021.642241 ◽

2021 ◽

Vol 12 ◽

Author(s):

Bidhan Lamichhane ◽

Andy G. S. Daniel ◽

John J. Lee ◽

Daniel S. Marcus ◽

Joshua S. Shimony ◽

...

Keyword(s):

Machine Learning ◽

Glioblastoma Multiforme ◽

Functional Connectivity ◽

Resting State ◽

Learning Analytics ◽

Support Vector ◽

Resting State Functional Connectivity ◽

Term Survival ◽

Long Term Survival

Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, non-invasive techniques to help inform pre-treatment planning, patient counseling, and improve outcomes. In this study we determined the feasibility of resting-state functional connectivity (rsFC) to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature selection method whereby features were first filtered using correlations between rsFC and OS, and then using the established method of recursive feature elimination (RFE) to select the optimal feature subset. Leave-one-subject-out cross-validation evaluated the performance of models. Classification between short- and long-term survival accuracy was 71.9%. Sensitivity and specificity were 77.1 and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC may predict GBM survival. Taken together, the findings of this study support that resting-state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.

Download Full-text