A Deep Analysis of Brain Tumor Detection from MR Images Using Deep Learning Networks

Abstract

Creating machines that behave and work in a way similar to humans is the objective of artificial intelligence (AI). In addition to pattern recognition, planning, and problem-solving, computer activities with artificial intelligence include other activities. A group of algorithms called “deep learning” is used in machine learning. With the aid of magnetic resonance imaging (MRI), deep learning is utilized to create models for the detection and categorization of brain tumors. This allows for the quick and simple identification of brain tumors. Brain disorders are mostly the result of aberrant brain cell proliferation, which can harm the structure of the brain and ultimately result in malignant brain cancer. The early identification of brain tumors and the subsequent appropriate treatment may lower the death rate. In this study, we suggest a convolutional neural network (CNN) architecture for the efficient identification of brain tumors using MR images. This paper also discusses various models such as ResNet-50, VGG16, and Inception V3 and conducts a comparison between the proposed architecture and these models. To analyze the performance of the models, we considered different metrics such as the accuracy, recall, loss, and area under the curve (AUC). As a result of analyzing different models with our proposed model using these metrics, we concluded that the proposed model performed better than the others. Using a dataset of 3264 MR images, we found that the CNN model had an accuracy of 93.3%, an AUC of 98.43%, a recall of 91.19%, and a loss of 0.25. We may infer that the proposed model is reliable for the early detection of a variety of brain tumors after comparing it to the other models.

Brain Tumor Detection and Categorization with Segmentation of Improved Unsupervised Clustering Approach and Machine Learning Classifier

“…Comparing this proposed classifier with existing studies, Saeedi et al [ 41 ] achieved an accuracy of 96.46%, demonstrating slightly lower performance than the proposed model. Kalam et al [ 42 ] and Mahmud et al [ 62 ] also reported accuracies of 98.35% and 93.53%, respectively, placing them in line with or slightly below the proposed classifier. Woźniak et al [ 63 ] obtained an accuracy of 96.46%, and Reyes et al [ 64 ] achieved an accuracy of 98.03%.…”

“…Figure 9 shows the performance comparison of the various performance metrics, such as accuracy, precision, and recall, for four classes between the proposed and the existing models [ 41 , 42 , 62 , 63 , 64 ]. In the evaluation of various classifiers for brain tumor classification, the proposed classifier demonstrates commendable performance across multiple metrics.…”

Advanced AI-driven approach for enhanced brain tumor detection from MRI images utilizing EfficientNetB2 with equalization and homomorphic filtering

“… Mahmud, M.I. et al, (2023) [ 3 ] A collection of 3,264 MRI brain tumor images, encompassing categories such as Glioma, Meningioma, Pituitary, and No tumor. 98.43% Implement deep learning with a CNN architecture to identify and classify brain tumors and compare the results with those obtained using transfer learning models like ResNet-50, VGG16, and Inception V3.…”

Two-headed UNetEfficientNets for parallel execution of segmentation and classification of brain tumors: incorporating postprocessing techniques with connected component labelling

“…This demonstrates the effectiveness of LBP features and CNN models for accurate brain tumor classification in MRI images. Mahmud et al ( 2023 ) employed a CNN model for brain tumor classification on a relatively large dataset of 3264 MRI images. The CNN model was trained to learn discriminative features and classify the input images into different tumor categories.…”