EventsThe 13th International Electronic Conference on Sensors and Applications
Published
This submission belongs to the session S4. Sensors and Artificial Intelligence of the event The 13th International Electronic Conference on Sensors and Applications
Published date
16 Nov, 2026
Academic Editor
author-avatarStefano Mariani
Citation
Namratha Sharma N, Palpandi S, Vijayalakshmi Sankaran, MRI-Based Automated Multi-Class Brain Tumor Classification using Deep Convolutional Models, in Proceedings of The 13th International Electronic Conference on Sensors and Applications, 18 November–20 November 2026, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

MRI-Based Automated Multi-Class Brain Tumor Classification using Deep Convolutional Models

1. Department of Computer Science, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India - 600062
2. Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India - 600062
Abstract

Brain tumours is one of the most life-threatening neurological disorders which is characterized by the anomalous proliferation of cells within the brain that may manifest as either benign or malignant growths. Additionally, the malignant tumours are particularly critical due to their rapid progression and metastatic potential. In this regard, it is essential to diagnose early and accurately for effective therapeutic intervention. Magnetic Resonance Imaging (MRI) remains the gold standard for structural brain visualization however, delineation of tumour in a precise manner continues to be a clinical challenge. Also, the conventional diagnostic approaches highly relies on manual radiological interpretation and traditional image processing techniques thereby creates a critical demand for robust computational frameworks. In this work, a deep learning framework for automated brain tumour classification using MRI images from the BraTS 2019 Kaggle dataset is proposed. Furthermore, the three different tumours such as glioma, pituitary, meningioma and no-tumour brain images are partitioned in a 70:30 ratio for training and testing of deep learning models. The classification is performed using a hybrid Convolutional Neural Network (CNN)-Transformer architecture, DenseNet-121 and Vision Transformer (ViT) is employed and comparatively evaluated for tumour classification. Results demonstrate that the proposed DenseNet 121 model achieves a classification accuracy of 98.5% with superior precision, recall, and F1-score standard metrics which significantly outperforms the other two deep learning methods. The proposed work demonstrates the efficacy of deep learning approaches for reliable, interpretable and clinically deployable brain tumour analysis.

Keywords
Automated Tumour Diagnosis
Brain Tumour Detection
Clinical Decision Support Systems
Computer Aided Diagnosis
Deep Learning
Multi-Class Classification
Magnetic Resonance Imaging
Manuscript
[Sciforum-198908] - [Manuscript PDF] - [Poster contribution - file uploaded].pdf
Poster
Sciforum-198908.pdf
Interference sensor with a robust 3-stage noise-resilient algorithm for fringes pattern analysis
Optimization of purification modes and evaluation of the degree of purification of sunflower protein concentrates using piezoelectric sensors