Title: Deep feature fusion and ensemble learning to create an effective CNN brain tumour classification model

Authors: B. Sathees Kumar

Addresses: Department of Computer Science, Bishop Heber College (Autonomous), Trichy, Tamil Nadu, India; Affiliated to: Bharathidasan University, India

Abstract: Early brain tumour exploration can streamline treatment. Some automated diagnosis system aids radiologists in distinguishing between normal and abnormal brain tissues, simplifying clinical and diagnostic processes. However, categorising MRI images is challenging due to low contrast, noise, tumour shape and localisation dissimilarity, and similarity between ordinary and cancerous regions of interest (ROIs). This study uses a deep convolutional neural network with feature blending and ensemble learning to analyse MRI abnormalities, followed by detection and classification tasks. The ensemble learning method effectively distinguishes between ordinary and cancerous tumour ROIs, yielding reliable results. Feature fusion identifies discriminative features between classes. To address overfitting in smaller datasets, depth-wise separable convolution and spatial drop-out techniques are explored for MRI brain image classification. The proposed approach has been validated on two freely available datasets, Kaggle and BrATS, with the BrATS dataset showing superior outcomes in accuracy, specificity, and sensitivity (0.995, 0.996, 0.996).

Keywords: brain tumour; feature fusion; computer-aided diagnosis; CAD; ensemble learning; brain tumour classification; regions of interest; ROIs; psychological health; malignant primary brain tumours; international agency for research.

DOI: 10.1504/IJBRA.2025.149725

International Journal of Bioinformatics Research and Applications, 2025 Vol.21 No.5, pp.522 - 546

Received: 31 Mar 2024
Accepted: 01 Aug 2024
Published online: 11 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article