Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias

Glioblastoma, IDH-wildtype (GBM), is the most aggressive and complex brain tumour classified by the World Health Organization (WHO), characterised by high mortality rates and diagnostic limitations inherent to invasive conventional procedures. Early detection is essential for improving patient outco...

Full description

Saved in:
Bibliographic Details
Main Authors: Kebin Contreras, Julio Gutierrez-Rengifo, Oscar Casanova-Carvajal, Angel Luis Alvarez, Patricia E. Vélez-Varela, Ana Lorena Urbano-Bojorge
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129531154726912
author Kebin Contreras
Julio Gutierrez-Rengifo
Oscar Casanova-Carvajal
Angel Luis Alvarez
Patricia E. Vélez-Varela
Ana Lorena Urbano-Bojorge
author_facet Kebin Contreras
Julio Gutierrez-Rengifo
Oscar Casanova-Carvajal
Angel Luis Alvarez
Patricia E. Vélez-Varela
Ana Lorena Urbano-Bojorge
author_sort Kebin Contreras
collection DOAJ
description Glioblastoma, IDH-wildtype (GBM), is the most aggressive and complex brain tumour classified by the World Health Organization (WHO), characterised by high mortality rates and diagnostic limitations inherent to invasive conventional procedures. Early detection is essential for improving patient outcomes, underscoring the need for non-invasive diagnostic tools. This study presents a convolutional neural network (CNN) specifically optimised for GBM detection from T1-weighted magnetic resonance imaging (MRI), with systematic evaluations of layer depth, activation functions, and hyperparameters. The model was trained on the RSNA-MICCAI data set and externally validated on the Erasmus Glioma Database (EGD), which includes gliomas of various grades and preserves cranial structures, unlike the skull-stripped RSNA-MICCAI images. This morphological discrepancy demonstrates the generalisation capacity of the model across anatomical and acquisition differences, achieving an F1-score of 0.88. Furthermore, statistical tests, such as Shapiro–Wilk, Mann–Whitney U, and Chi-square, confirmed the absence of demographic bias in model predictions, based on <i>p</i>-values, confidence intervals, and statistical power analyses supporting its demographic fairness. The proposed model achieved an area under the curve–receiver operating characteristic (AUC-ROC) of 0.63 on the RSNA-MICCAI test set, surpassing all prior results submitted to the BraTS 2021 challenge, and establishing a reliable and generalisable approach for non-invasive GBM detection.
format Article
id doaj-art-ce006a32fb7d49aeb28a75c23acde2f5
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ce006a32fb7d49aeb28a75c23acde2f52025-08-20T02:32:56ZengMDPI AGApplied Sciences2076-34172025-06-011511627410.3390/app15116274Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic BiasKebin Contreras0Julio Gutierrez-Rengifo1Oscar Casanova-Carvajal2Angel Luis Alvarez3Patricia E. Vélez-Varela4Ana Lorena Urbano-Bojorge5Departamento de Biología, Facultad de Ciencias Naturales, Exactas y de la Educación FACNED, Universidad del Cauca, Popayan 190002, ColombiaDepartamento de Ciencias de la Computación, Universidad Industrial de Santander, Bucaramanga 680006, ColombiaCentro de Tecnología Biomédica, Campus de Montegancedo, Universidad Politécnica de Madrid, 28040 Madrid, SpainEscuela de Ingeniería de Fuenlabrada, Universidad Rey Juan Carlos, 28922 Madrid, SpainDepartamento de Biología, Facultad de Ciencias Naturales, Exactas y de la Educación FACNED, Universidad del Cauca, Popayan 190002, ColombiaDepartamento de Biología, Facultad de Ciencias Naturales, Exactas y de la Educación FACNED, Universidad del Cauca, Popayan 190002, ColombiaGlioblastoma, IDH-wildtype (GBM), is the most aggressive and complex brain tumour classified by the World Health Organization (WHO), characterised by high mortality rates and diagnostic limitations inherent to invasive conventional procedures. Early detection is essential for improving patient outcomes, underscoring the need for non-invasive diagnostic tools. This study presents a convolutional neural network (CNN) specifically optimised for GBM detection from T1-weighted magnetic resonance imaging (MRI), with systematic evaluations of layer depth, activation functions, and hyperparameters. The model was trained on the RSNA-MICCAI data set and externally validated on the Erasmus Glioma Database (EGD), which includes gliomas of various grades and preserves cranial structures, unlike the skull-stripped RSNA-MICCAI images. This morphological discrepancy demonstrates the generalisation capacity of the model across anatomical and acquisition differences, achieving an F1-score of 0.88. Furthermore, statistical tests, such as Shapiro–Wilk, Mann–Whitney U, and Chi-square, confirmed the absence of demographic bias in model predictions, based on <i>p</i>-values, confidence intervals, and statistical power analyses supporting its demographic fairness. The proposed model achieved an area under the curve–receiver operating characteristic (AUC-ROC) of 0.63 on the RSNA-MICCAI test set, surpassing all prior results submitted to the BraTS 2021 challenge, and establishing a reliable and generalisable approach for non-invasive GBM detection.https://www.mdpi.com/2076-3417/15/11/6274glioblastoma multiformebiasstatisticconvolutional neural networksmagnetic resonance imagingdeep learning
spellingShingle Kebin Contreras
Julio Gutierrez-Rengifo
Oscar Casanova-Carvajal
Angel Luis Alvarez
Patricia E. Vélez-Varela
Ana Lorena Urbano-Bojorge
Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias
Applied Sciences
glioblastoma multiforme
bias
statistic
convolutional neural networks
magnetic resonance imaging
deep learning
title Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias
title_full Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias
title_fullStr Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias
title_full_unstemmed Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias
title_short Deep Learning for Glioblastoma Multiforme Detection from MRI: A Statistical Analysis for Demographic Bias
title_sort deep learning for glioblastoma multiforme detection from mri a statistical analysis for demographic bias
topic glioblastoma multiforme
bias
statistic
convolutional neural networks
magnetic resonance imaging
deep learning
url https://www.mdpi.com/2076-3417/15/11/6274
work_keys_str_mv AT kebincontreras deeplearningforglioblastomamultiformedetectionfrommriastatisticalanalysisfordemographicbias
AT juliogutierrezrengifo deeplearningforglioblastomamultiformedetectionfrommriastatisticalanalysisfordemographicbias
AT oscarcasanovacarvajal deeplearningforglioblastomamultiformedetectionfrommriastatisticalanalysisfordemographicbias
AT angelluisalvarez deeplearningforglioblastomamultiformedetectionfrommriastatisticalanalysisfordemographicbias
AT patriciaevelezvarela deeplearningforglioblastomamultiformedetectionfrommriastatisticalanalysisfordemographicbias
AT analorenaurbanobojorge deeplearningforglioblastomamultiformedetectionfrommriastatisticalanalysisfordemographicbias