A web modular AI interface for brain tumor MRI classification using deep learning models
- 1Department of Engineering (Biomedical Engineering), Holy Spirit University of Kaslik
- 2Hamad Medical Corporation
Abstract
In order to improve patient outcomes and treatment processes, early and precise diagnosis of brain tumors is crucial. Despite the strong performance shown by deep learning models in classifying brain tumors from MRI scans, integrating these models into user-friendly clinical workflows remains challenging. This study presents a web-based AI platform designed for brain tumor classification using MRI images. The platform enables users to upload MRI scans, apply standardized preprocessing, select between different deep learning models, and receive real-time predictions. A custom convolutional neural network (CNN), pretrained VGG19, and pretrained Xception were evaluated using a publicly available T1-weighted contrast-enhanced brain MRI dataset of approximately 7,000 images across four classes: glioma, meningioma, pituitary tumor, and no tumor. The dataset lacks patient demographic and clinical metadata, limiting assessment of clinical generalizability. The models achieved test accuracies of 96.03%, 98%, and 96%, respectively, with VGG19 demonstrating the best performance. The study is limited by the use of a single public, slice-based dataset and the absence of external clinical validation; future work will focus on multi-sequence MRI and independent clinical cohorts.
Related
- Multi-task deep learning framework for brain tumor classification and segmentation using ensemble feature extraction
- Spatial Neurophysiological Gradients at High Resolution Differentiate Tumor Types in the Human Cortex at the Tumor-Brain Interface
- Radiomics analysis of brain–tumor interface on multiparametric MRI for prediction of brain metastasis primary site
- Boundary-aware multi-scale residual learning with hybrid radiomic–deep fusion for lung tumor segmentation and classification
- DualXBrNet: A Hybrid Dual-Path Cross-Level Fusion Framework for Multiclass Brain Tumor Classification Using MRI Images
BibTeX
@article{hamalaya2026modular,
title = {{A web modular AI interface for brain tumor MRI classification using deep learning models}},
author = {Jennifer Hamalaya and Hadi Fayad and Tarraf Torfeh and Sandy Rihana},
journal = {BMC Biomedical Engineering},
year = {2026},
month = oct,
doi = {10.1186/s42490-026-00123-w},
url = {https://doi.org/10.1186/s42490-026-00123-w},
note = {CC BY},
}
RIS
TY - JOUR
TI - A web modular AI interface for brain tumor MRI classification using deep learning models
AU - Jennifer Hamalaya
AU - Hadi Fayad
AU - Tarraf Torfeh
AU - Sandy Rihana
PY - 2026
DA - 2026/10/25
JO - BMC Biomedical Engineering
DO - 10.1186/s42490-026-00123-w
UR - https://doi.org/10.1186/s42490-026-00123-w
AB - In order to improve patient outcomes and treatment processes, early and precise diagnosis of brain tumors is crucial. Despite the strong performance shown by deep learning models in classifying brain tumors from MRI scans, integrating these models into user-friendly clinical workflows remains challenging. This study presents a web-based AI platform designed for brain tumor classification using MRI images. The platform enables users to upload MRI scans, apply standardized preprocessing, select between different deep learning models, and receive real-time predictions. A custom convolutional neural network (CNN), pretrained VGG19, and pretrained Xception were evaluated using a publicly available T1-weighted contrast-enhanced brain MRI dataset of approximately 7,000 images across four classes: glioma, meningioma, pituitary tumor, and no tumor. The dataset lacks patient demographic and clinical metadata, limiting assessment of clinical generalizability. The models achieved test accuracies of 96.03%, 98%, and 96%, respectively, with VGG19 demonstrating the best performance. The study is limited by the use of a single public, slice-based dataset and the absence of external clinical validation; future work will focus on multi-sequence MRI and independent clinical cohorts.
SN - 2524-4426
ER -