Automated Multi-Class Brain Tumor Classification from MRI Images Using a Tree-Hierarchical Deep Convolutional Neural Network with Optimized Image Processing

DOI

10.2991/978-94-6463-940-7_12How to use a DOI?

Keywords

Brain tumor classification; MRI images; deep learning; Tree-Hierarchical CNN; Bayesian Boundary Trend Filtering; Medical image processing; Smart healthcare; Tumor detection

Abstract

Brain tumors represent one of the most critical challenges in medical diagnosis due to their high mortality rate and complex structure, and early and accurate detection is essential to improve treatment outcomes and survival rates. However, brain tumor detection and classification from MRI images remain highly challenging because MRI scans often suffer from noise, low contrast, and intensity inhomogeneity, which obscure critical tumor boundaries and reduce diagnostic accuracy. This research is motivated by the urgent need for automation in neuro-oncology, as the growing number of brain tumor cases makes reliance on manual radiological assessment unsustainable. To address these issues, we propose a novel framework that integrates Bayesian Boundary Trend Filtering (BBTF) for optimized pre-processing with a Tree-Hierarchical Deep Convolutional Neural Network (THDCNN) capable of capturing both local and global features. Unlike conventional CNNs and ANNs, the hierarchical design of THDCNN ensures robust multi-scale feature learning, while BBTF preserves tumor boundaries during noise reduction, resulting in cleaner and more reliable inputs. Experimental validation shows that the proposed model achieves 6–8% higher accuracy, precision, and recall compared to existing CNN, ANN, and FCM-SVM methods. This combination of advanced pre-processing, novel architecture, and superior performance makes the framework a promising solution for real-time, privacy-preserving smart healthcare and next-generation neuro-oncology applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kranthisudha Burgupalli
AU  - Kamepalli Sujatha
PY  - 2025
DA  - 2025/12/31
TI  - Automated Multi-Class Brain Tumor Classification from MRI Images Using a Tree-Hierarchical Deep Convolutional Neural Network with Optimized Image Processing
BT  - Proceedings of the Conference on Social and Sustainable Innovation in Technology & Engineering (SASI-ITE 2025)
PB  - Atlantis Press
SP  - 160
EP  - 173
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-940-7_12
DO  - 10.2991/978-94-6463-940-7_12
ID  - Burgupalli2025
ER  -