A deep learning approach for brain tumor detection using magnetic resonance imaging

Abstract

The growth of abnormal cells in the brain’s tissue causes brain tumors. Brain tumors are considered one of the most dangerous disorders in children and adults. It develops quickly, and the patient’s survival prospects are slim if not appropriately treated. Proper treatment planning and precise diagnoses are essential to improving a patient’s life expectancy. Brain tumors are mainly diagnosed using magnetic resonance imaging (MRI). As part of a convolution neural network (CNN)-based illustration, an architecture containing five convolution layers, five max-pooling layers, a Flatten layer, and two dense layers has been proposed for detecting brain tumors from MRI images. The proposed model includes an automatic feature extractor, modified hidden layer architecture, and activation function. Several test cases were performed, and the proposed model achieved 98.6% accuracy and 97.8% precision score with a low cross-entropy rate. Compared with other approaches such as adjacent feature propagation network (AFPNet), mask region-based CNN (mask RCNN), YOLOv5, and Fourier CNN (FCNN), the proposed model has performed better in detecting brain tumors.

Fuzzy Deep Learning Approach for the Early Detection of Degenerative Disease

“…The results suggest that the effectiveness of the proposed method exceeds that of recent studies documented in the literature. According to study [10], their proposed model surpasses existing models in accuracy, achieving 99.48% for binary classification and 96.86% for multi-class classification. In contrast to existing models that encounter difficulties such as substantial computational expenses and restricted generalizability attributed to insufficient training data, our model tackles these challenges by being lightweight, employing cross-validation for enhanced generalizability, and undergoing training on extensive and diverse datasets.…”

“…Furthermore, an alternative model employing CNN integrates an automated feature extractor, modified hidden layer architecture, and activation function. Various test scenarios were executed, and the proposed model achieved a precision score of 97.8%, coupled with a low cross-entropy rate [10] In research [11], the researchers focused on assessing the classification accuracy of cranial MR images using ELM-LRF, achieving a precision rate of 97.18%. The results suggest that the effectiveness of the proposed method exceeds that of recent studies documented in the literature.…”

Brain Tumor Detection Using Deep Learning Technique

“…This model has a 14-stage, 9-layer CNN model. In the work proposed in [8], an automatic feature extractor, a modified hidden layer architecture and an activation function. Compared to other methods like Fourier CNN, Mask Region-Based CNN (R-CNN) and Adjacent Features Propagation networks (AFPNet) better in detecting brain tumors.…”

Distance Analysis and Dimensionality Reduction using PCA on Brain Tumour MRI Scans

“…These techniques analyze data to identify the most informative features contributing to the classification task. One commonly used technique for feature extraction in brain tumor MRI scans is the Discrete Wavelet Transform [9]. This technique allows for the extraction of important image features usable for classification purposes.…”