Glioma tumor grading using radiomics on conventional MRI: A comparative study of WHO 2021 and WHO 2016 classification of central nervous tumors

 

Abstract

 

Background
 
Glioma grading transformed in World Health Organization (WHO) 2021 CNS tumor classification, integrating molecular markers. However, the impact of this change on radiomics‐based machine learning (ML) classifiers remains unexplored.
 
Purpose
 
To assess the performance of ML in classifying glioma tumor grades based on various WHO criteria.
Study Type
Retrospective.
 
Subjects
 
A neuropathologist regraded gliomas of 237 patients into WHO 2016 and 2021 from 2007 criteria.
 
Field Strength/Sequence
 
Multicentric 0.5 to 3 Tesla; pre‐ and post‐contrast T1‐weighted, T2‐weighted, and fluid‐attenuated inversion recovery.
 
Assessment
 
Radiomic features were selected using random forest‐recursive feature elimination. The synthetic minority over‐sampling technique (SMOTE) was implemented for data augmentation. Stratified 10‐fold cross‐validation with and without SMOTE was used to …
Keywords:

Glioma Tumor, Grading , Radiomics, Conventional MRI, WHO
Authors:

Farzan Moodi, Fereshteh Khodadadi Shoushtari, Delaram J Ghadimi, Gelareh Valizadeh, Ehsan Khormali, Hanieh Mobarak Salari, Mohammad Amin Dabbagh Ohadi, Yalda Nilipour, Amin Jahanbakhshi, Hamidreza Saligheh Rad
Journal:

Journal of Magnetic Resonance Imaging
Scroll to Top