CSMEC-based deep learning model for detection and classification of brain tumours in MR images

• Published in: Neural computing & applications 2024-10, Vol.36 (29), p.18479-18498
• Main Authors: Beaulah Princiba, D., Ezhilarasi, P., Rajeshkannan, S.
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Brain; Brain cancer; Classification; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data augmentation; Data Mining and Knowledge Discovery; Deep learning; Heterogeneity; Image enhancement; Image Processing and Computer Vision; Image quality; Machine learning; Magnetic resonance imaging; Maximum entropy; Medical imaging; Original Article; Probability and Statistics in Computer Science; State-of-the-art reviews; Tumors
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-024-10168-4

Brain tumours are anomalous growths or clusters of cells in or encircling the brain. These tumours are perhaps detected and classified using magnetic resonance imaging (MRI), which plays an influential role in the identification of tumours. Brain tumours are suspiciously difficult to classify because of their heterogeneity. The manual detection of tumours is a time-wasting and complex process that can lead to a misdiagnosis. To overcome these drawbacks, the progression of deep learning (DL)-based convolutional neural network models is used to diagnose brain tumours using MRI. This research proposes a compound scaling with maximum entropy classifier-based deep learning model to classify brain tumours as pituitary, meningioma, glioma, and no tumour. To enhance the quality of the images, various pre-processing techniques are used. Data augmentation techniques are used to add up the number of images to enrich the training of our proposed model. With and without augmentation results are compared and showed that the proposed model with augmentation gives excellent results for classification. Experimental results show that the proposed model achieves 99.86% accuracy during training, 99.65% accuracy during validation, and a great classification accuracy of 99.24% during testing. In addition to the F1 score, recall, precision, micro-average, macro-average, and weighted average were used in this study. The existing state-of-the-art DL algorithms such as VGG16, VGG19, ResNet50, InceptionV3, and DenseNet121 are used for comparative analysis.