MRI-Based Effective Ensemble Frameworks for Predicting Human Brain Tumor

Abstract

The diagnosis of brain tumors at an early stage is an exigent task for radiologists. Untreated patients rarely survive more than six months. It is a potential cause of mortality that can occur very quickly. Because of this, the early and effective diagnosis of brain tumors requires the use of an automated method. This study aims at the early detection of brain tumors using brain magnetic resonance imaging (MRI) data and efficient learning paradigms. In visual feature extraction, convolutional neural networks (CNN) have achieved significant breakthroughs. The study involves features extraction by deep convolutional layers for the efficient classification of brain tumor victims from the normal group. The deep convolutional neural network was implemented to extract features that represent the image more comprehensively for model training. Using deep convolutional features helps to increase the precision of tumor and non-tumor patient classifications. In this paper, we experimented with five machine learnings (ML) to heighten the understanding and enhance the scope and significance of brain tumor classification. Further, we proposed an ensemble of three high-performing individual ML models, namely Extreme Gradient Boosting, Ada-Boost, and Random Forest (XG-Ada-RF), to derive binary class classification output for detecting brain tumors in images. The proposed voting classifier, along with convoluted features, produced results that showed the highest accuracy of 95.9% for tumor and 94.9% for normal. Compared to individual methods, the proposed ensemble approach demonstrated improved accuracy and outperformed the individual methods.

Skin Cancer Segmentation and Classification Using Vision Transformer for Automatic Analysis in Dermatoscopy-Based Noninvasive Digital System

“…Gulzar and Khan [ 72 ] conducted a comparative study on U-Net and attention-based methods for skin lesion image segmentation, attaining 92.11% accuracy with a superior hybrid TransUNet. Khan et al [ 73 ] proposed an ensemble (XG-Ada-RF) on extreme gradient boosting, Ada-boost, and random forest, achieving 95.9% accuracy for tumor detection and 94.9% for normal brain tumor images. Mehmood et al [ 74 ] presented SBXception, a modified model for the HAM10000 dataset, achieving 96.97% accuracy on a holdout test set.…”

A Novel Ensemble Framework for Multi-Classification of Brain Tumors Using Magnetic Resonance Imaging

“…Ensemble models have been proposed by some researchers to detect brain tumor types [1,[37][38][39][40][41][42]. Aurna et al [1] proposed a two-stage method for brain tumor classification.…”

“…In their study, Patil and Kirange [39] combined SCNN and VGG16 models in the feature extraction phase using ensemble learning. Extreme Gradient Boosting, Ada-Boost, and Random Forest (XG-Ada RF) are three high-performance individual machine learning models that Khan et al [40] suggested as an ensemble for binary classification. Tantel et al [41] combined five CNN (AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50) architectures with ensemble techniques for binary tumor classification.…”

“…When the existing studies are examined, there are many studies using scratch models [19][20][21][22][23][24][25], transfer learning [26][27][28][29][30][31][32][33][34][35][36], ensemble learning [1,[37][38][39][40][41][42], and different optimization algorithms [4,[43][44][45][46][47][48][49][50][51][52][53][54]. Table 1 summarizes related studies on brain tumor classification in terms of method, dataset, classification type, and results.…”

Enhancing Autism Severity Classification: Integrating LSTM into CNNs for Multisite Meltdown Grading

“…In recent times, the pervasive influence of artificial intelligence (AI) has become increasingly apparent, bringing about transformative changes across a spectrum of fields and enriching various facets of our everyday existence [4,5]. It has redefined how we approach education [6], fine-tuned financial strategies [7], simplified agricultural workflows [8][9][10][11][12][13][14][15][16], and elevated healthcare diagnostics to new heights [17][18][19][20][21][22][23]. As it seamlessly integrates into these diverse sectors, AI continues to demonstrate its capacity for generating unparalleled efficiencies, refining decision-making procedures, and addressing intricate challenges with a precision derived from data-driven insights [24,25].…”