Optimizing brain tumor classification with hybrid CNN architecture: Balancing accuracy and efficiency through oneAPI optimization

Abstract

A brain tumour is a malignant condition that spreads extremely quickly and requires rapid detection. In recent years, it has become apparent that deep learning is a promising technique for classifying brain tumours. To identify these tumours, this work proposes a hybrid CNN architecture, implementing InceptionV3, ResNet-50, VGG16, and DenseNet. To evaluate this approach, a total of 3929 images was obtained from Kaggle, including 2556 non-tumorigenic and 1373 tumorigenic specimens. Initially, the method extracts features from MRI pictures, then segments the tumour using the mask images. Subsequently, the segmented tumour image is fused with the original image, and finally the fused image is classified with the assistance of four distinct CNN models, specifically InceptionV3, ResNet, DenseNet, and VGG16. To enhance the performance of the hybrid architecture, these models were further optimized with oneAPI, which allows a comparative analysis of each individual model for classification. To evaluate the effectiveness of medical image classification models, a variety of evaluation criteria have been utilized extensively. We highlight the use of mean Intersection over Union (mIoU) as a more acceptable and intuitive statistic for evaluating the balance between true positives, false positives, and false negatives. This is in response to recent breakthroughs that have been made.