Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment

<i>Background and Objectives</i>: Gliomas are characterized by high disability rates, frequent recurrence, and low survival rates, posing a significant threat to human health. Accurate grading of gliomas is crucial for treatment plan selection and prognostic assessment. Previous studies...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Qin, Wei You, Yulong Wang, Yu Zhang, Zhijie Xu, Qingling Li, Yuelong Zhao, Zhiwei Mou, Yitao Mao
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Medicina
Subjects:
Online Access:https://www.mdpi.com/1648-9144/61/6/1034
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432241344610304
author Yan Qin
Wei You
Yulong Wang
Yu Zhang
Zhijie Xu
Qingling Li
Yuelong Zhao
Zhiwei Mou
Yitao Mao
author_facet Yan Qin
Wei You
Yulong Wang
Yu Zhang
Zhijie Xu
Qingling Li
Yuelong Zhao
Zhiwei Mou
Yitao Mao
author_sort Yan Qin
collection DOAJ
description <i>Background and Objectives</i>: Gliomas are characterized by high disability rates, frequent recurrence, and low survival rates, posing a significant threat to human health. Accurate grading of gliomas is crucial for treatment plan selection and prognostic assessment. Previous studies have primarily focused on the binary classification (i.e., high grade vs. low grade) of gliomas. In order to perform the four-grade (grades I, II, III, and IV) glioma classification preoperatively, we constructed an artificial neural network (ANN) model using magnetic resonance imaging data. <i>Materials and Methods</i>: We reviewed and included patients with gliomas who underwent preoperative MRI examinations. Radiomics features were derived from contrast-enhanced T1-weighted images (CE-T<sub>1</sub>WI) using Pyradiomics and were selected based on their Spearman’s rank correlation with glioma grades. We developed an ANN model to classify the four pathological grades of glioma, assigning training and validation sets at a 3:1 ratio. A diagnostic confusion matrix was employed to demonstrate the model’s diagnostic performance intuitively. <i>Results</i>: Among the 362-patient cohort, the ANN model’s diagnostic performance plateaued after incorporating the first 19 of the 530 extracted radiomic features. At this point, the average overall diagnostic accuracy ratings for the training and validation sets were 91.28% and 87.04%, respectively, with corresponding coefficients of variation (CVs) of 0.0190 and 0.0272. The diagnostic accuracies for grades I, II, III, and IV in the training set were 91.9%, 89.9%, 92.1%, and 90.7%, respectively. The diagnostic accuracies for grades I, II, III, and IV in the validation set were 88.7%, 87.1%, 86.5%, and 86.9%, respectively. <i>Conclusions</i>: The MRI radiomics-based ANN model shows promising potential for the four-type classification of glioma grading, offering an objective and noninvasive method for more refined glioma grading. This model could aid in clinical decision making regarding the treatment of patients with various grades of gliomas.
format Article
id doaj-art-e7b193a41cd146d991b29b73edbfdba5
institution Kabale University
issn 1010-660X
1648-9144
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Medicina
spelling doaj-art-e7b193a41cd146d991b29b73edbfdba52025-08-20T03:27:25ZengMDPI AGMedicina1010-660X1648-91442025-06-01616103410.3390/medicina61061034Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading AssessmentYan Qin0Wei You1Yulong Wang2Yu Zhang3Zhijie Xu4Qingling Li5Yuelong Zhao6Zhiwei Mou7Yitao Mao8Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, ChinaDepartment of Radiology, Xiangya Hospital, Central South University, Changsha 410008, ChinaDepartment of Radiology, Xiangya Hospital, Central South University, Changsha 410008, ChinaCommunication Sciences and Disorders, Oklahoma State University, Stillwater, OK 74075, USADepartment of Pathology, Xiangya Hospital, Central South University, Changsha 410008, ChinaDepartment of Pathology, Xiangya Hospital, Central South University, Changsha 410008, ChinaSchool of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, ChinaDepartment of Rehabilitation, The First Affiliated Hospital of Jinan University, Guangzhou 510630, ChinaDepartment of Radiology, Xiangya Hospital, Central South University, Changsha 410008, China<i>Background and Objectives</i>: Gliomas are characterized by high disability rates, frequent recurrence, and low survival rates, posing a significant threat to human health. Accurate grading of gliomas is crucial for treatment plan selection and prognostic assessment. Previous studies have primarily focused on the binary classification (i.e., high grade vs. low grade) of gliomas. In order to perform the four-grade (grades I, II, III, and IV) glioma classification preoperatively, we constructed an artificial neural network (ANN) model using magnetic resonance imaging data. <i>Materials and Methods</i>: We reviewed and included patients with gliomas who underwent preoperative MRI examinations. Radiomics features were derived from contrast-enhanced T1-weighted images (CE-T<sub>1</sub>WI) using Pyradiomics and were selected based on their Spearman’s rank correlation with glioma grades. We developed an ANN model to classify the four pathological grades of glioma, assigning training and validation sets at a 3:1 ratio. A diagnostic confusion matrix was employed to demonstrate the model’s diagnostic performance intuitively. <i>Results</i>: Among the 362-patient cohort, the ANN model’s diagnostic performance plateaued after incorporating the first 19 of the 530 extracted radiomic features. At this point, the average overall diagnostic accuracy ratings for the training and validation sets were 91.28% and 87.04%, respectively, with corresponding coefficients of variation (CVs) of 0.0190 and 0.0272. The diagnostic accuracies for grades I, II, III, and IV in the training set were 91.9%, 89.9%, 92.1%, and 90.7%, respectively. The diagnostic accuracies for grades I, II, III, and IV in the validation set were 88.7%, 87.1%, 86.5%, and 86.9%, respectively. <i>Conclusions</i>: The MRI radiomics-based ANN model shows promising potential for the four-type classification of glioma grading, offering an objective and noninvasive method for more refined glioma grading. This model could aid in clinical decision making regarding the treatment of patients with various grades of gliomas.https://www.mdpi.com/1648-9144/61/6/1034MRIradiomicsgliomagradingartificial neural network model
spellingShingle Yan Qin
Wei You
Yulong Wang
Yu Zhang
Zhijie Xu
Qingling Li
Yuelong Zhao
Zhiwei Mou
Yitao Mao
Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment
Medicina
MRI
radiomics
glioma
grading
artificial neural network model
title Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment
title_full Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment
title_fullStr Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment
title_full_unstemmed Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment
title_short Magnetic Resonance Imaging Radiomics-Driven Artificial Neural Network Model for Advanced Glioma Grading Assessment
title_sort magnetic resonance imaging radiomics driven artificial neural network model for advanced glioma grading assessment
topic MRI
radiomics
glioma
grading
artificial neural network model
url https://www.mdpi.com/1648-9144/61/6/1034
work_keys_str_mv AT yanqin magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT weiyou magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT yulongwang magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT yuzhang magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT zhijiexu magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT qinglingli magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT yuelongzhao magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT zhiweimou magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment
AT yitaomao magneticresonanceimagingradiomicsdrivenartificialneuralnetworkmodelforadvancedgliomagradingassessment