Machine-Learning-Based Radiomics for Classifying Glioma Grade from Magnetic Resonance Images of the Brain

Aug 5, 2026

Upload by Finn

Glioma grading is essential for prognosis and survival, yet manual radiological assessment based on semantic features is subjective, requires complex multiparametric MRI workflows, and can lead to misdiagnosis. A machine-learning radiomics strategy was applied to classify glioma grade using MRI data from 83 histopathologically confirmed patients, with TexRad-based manual T2W segmentation and 42 extracted radiomics features. Feature selection relied on recursive feature elimination with a random forest framework, and models were evaluated via 10-fold cross-validation using AUC, accuracy, precision, recall, and F1 score. The random forest model achieved strong test performance and supports a non-invasive preoperative approach.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Glioma grading and clinical significance

Imaging and MRI-based tumor characterization

Article Machine-Learning-Based Radiomics for Classifying Glioma Grade from Magnetic Resonance Images of the Brain Anuj Kumar 1, Ashish Kumar Jha 2, Jai Prakash Agarwal 1, Manender Yadav 1, Suvarna Badhe 1, Ayushi Sahay 3, Sridhar Epari 3, Arpita Sahu 4, Kajari Bhattacharya 4, Abhishek Chatterjee 1, Balaji Ganeshan 5, Venkatesh Rangarajan 2, Aliasgar Moyiadi 6, Tejpal Gupta 1 and Jayant S. Goda 1, * Citation: Kumar, A.; Jha, A.K.; Agarwal, J.P.; Yadav, M.; Badhe, S.; Sahay, A.; Epari, S.; Sahu, A.; Bhattacharya, K.; Chatterjee, A.; et al. Machine-Learning-Based Radiomics for Classifying Glioma Grade from Magnetic Resonance Images of the Brain. J. Pers. Med. 2023, 13, 920 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)jpm13060920 Academic Editor: Quintino Giorgio D'Alessandris Received: 24 April 2023 Revised: 22 May 2023 Accepted: 25 May 2023 Published: 30 May 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Radiation Oncology, Tata Memorial Centre, Homi Bhaba National Institute, Mumbai 400012, India 2 Department of Nuclear Medicine, Tata Memorial Centre, Homi Bhaba National Institute, Mumbai 400012, India 3 Department of Pathology, Tata Memorial Centre, Homi Bhaba National Institute, Mumbai 400012, India 4 Department of Radiodiagnosis, Tata Memorial Centre, Homi Bhaba National Institute, Mumbai 400012, India 5 Institute of Nuclear Medicine, University College London Hospital, 235 Euston Road, London NW1 2BU, UK 6 Department of Neurosurgery, Tata Memorial Centre, Homi Bhaba National Institute, Mumbai 400012, India * Correspondence: [godajayantsastri@gmail.com or jgoda@actrec.gov.in](godajayantsastri@gmail.com or jgoda@actrec.gov.in) Abstract: Grading of gliomas is a piece of critical information related to prognosis and survival. Classifying glioma grade by semantic radiological features is subjective, requires multiple MRI sequences, is quite complex and clinically demanding, and can very often result in erroneous radiological diagnosis. We used a radiomics approach with machine learning classiﬁers to determine the grade of gliomas. Eighty-three patients with histopathologically proven gliomas underwent MRI of the brain. Whenever available, immunohistochemistry was additionally used to augment the histopathological diagnosis. Segmentation was performed manually on the T2W MR sequence using the TexRad texture analysis softwareTM, Version 3.10 . Forty-two radiomics features, which included ﬁrst-order features and shape features, were derived and compared between high-grade and low-grade gliomas. Features were selected by recursive feature elimination using a random forest algorithm method. The classiﬁcation performance of the models was measured using accuracy, precision, recall, f1 score, and area under the curve (AUC) of the receiver operating characteristic curve. A 10-fold cross-validation was adopted to separate the training and the test data. The selected features were used to build ﬁveclassiﬁer models: support vector machine, random forest, gradient boost, naive Bayes, and AdaBoost classiﬁers. The random forest model performed the best, achieving an AUC of 0.81, an accuracy of 0.83, f1 score of 0.88, a recall of 0.93, and a precision of 0.85 for the test cohort. The results suggest that machine-learning-based radiomics features extracted from multiparametric MRI images can provide a non-invasive method for predicting glioma grades preoperatively. In the present study, we extracted the radiomics features from a single cross-sectional image of the T2W MRI sequence and utilized these features to build a fairly robust model to cla

FAQs

Why is glioma grading clinically important?

Glioma grading is critical for prognosis and survival, helping predict outcomes and guide management decisions.

How were radiomics features extracted and selected in the study?

Manual segmentation on the T2W MRI sequence using TexRad produced 42 radiomics features. Recursive feature elimination with a random forest approach selected the most informative features.

Which machine-learning model performed best and how was performance evaluated?

The random forest model performed best on the test cohort, evaluated using AUC, accuracy, precision, recall, and F1 score with 10-fold cross-validation.

Aug 5, 2026

Upload by Finn