A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images

The life span and quality of a patient are greatly diminished by a brain tumor, a type of cancer. For patients, early diagnosis and effective treatment are very significant in this respect. To assist medical professionals in this difficult and error-prone process and improve both the accuracy and in...

Full description

Saved in:
Bibliographic Details
Main Author: Esra Gundogan
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5412
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257688982716416
author Esra Gundogan
author_facet Esra Gundogan
author_sort Esra Gundogan
collection DOAJ
description The life span and quality of a patient are greatly diminished by a brain tumor, a type of cancer. For patients, early diagnosis and effective treatment are very significant in this respect. To assist medical professionals in this difficult and error-prone process and improve both the accuracy and interpretability of the model, this study proposes a new hybrid deep learning model enhanced with explainable artificial intelligence for brain tumor multi-classification from MRI images. It integrates a customized CNN model for feature extraction from images and the optimized XGBoost method with high classification success. It also incorporates Grad-CAM, which makes the black-box structure of the model transparent and the decision-making process more understandable. The proposed model classified four different brain tumors, namely glioma, meningioma, notumor and pituitary, with 99.77% accuracy and demonstrated superior performance when compared with existing methods. The results show that a robust, interpretable and high-performance hybrid classification model has been developed for brain tumor detection.
format Article
id doaj-art-af7b23e46a7649b2aaf47c9099dba78c
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-af7b23e46a7649b2aaf47c9099dba78c2025-08-20T01:56:20ZengMDPI AGApplied Sciences2076-34172025-05-011510541210.3390/app15105412A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI ImagesEsra Gundogan0Software Engineering Department, Firat University, 23190 Elazig, TurkeyThe life span and quality of a patient are greatly diminished by a brain tumor, a type of cancer. For patients, early diagnosis and effective treatment are very significant in this respect. To assist medical professionals in this difficult and error-prone process and improve both the accuracy and interpretability of the model, this study proposes a new hybrid deep learning model enhanced with explainable artificial intelligence for brain tumor multi-classification from MRI images. It integrates a customized CNN model for feature extraction from images and the optimized XGBoost method with high classification success. It also incorporates Grad-CAM, which makes the black-box structure of the model transparent and the decision-making process more understandable. The proposed model classified four different brain tumors, namely glioma, meningioma, notumor and pituitary, with 99.77% accuracy and demonstrated superior performance when compared with existing methods. The results show that a robust, interpretable and high-performance hybrid classification model has been developed for brain tumor detection.https://www.mdpi.com/2076-3417/15/10/5412brain tumor classificationdeep learningGrad-CAMXAIXGBoost
spellingShingle Esra Gundogan
A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images
Applied Sciences
brain tumor classification
deep learning
Grad-CAM
XAI
XGBoost
title A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images
title_full A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images
title_fullStr A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images
title_full_unstemmed A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images
title_short A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images
title_sort novel hybrid deep learning model enhanced with explainable ai for brain tumor multi classification from mri images
topic brain tumor classification
deep learning
Grad-CAM
XAI
XGBoost
url https://www.mdpi.com/2076-3417/15/10/5412
work_keys_str_mv AT esragundogan anovelhybriddeeplearningmodelenhancedwithexplainableaiforbraintumormulticlassificationfrommriimages
AT esragundogan novelhybriddeeplearningmodelenhancedwithexplainableaiforbraintumormulticlassificationfrommriimages