An automated metaheuristic-optimized approach for diagnosing and classifying brain tumors based on a convolutional neural network

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102459 - 102459

Published: June 28, 2024

Brain tumors must be classified to determine their severity and appropriate therapy. Applying Artificial Intelligence medical imaging has enabled remarkable developments. The presented framework classifies patients with brain high accuracy efficiency using CNN, pre-trained models, the Manta Ray Foraging Optimization (MRFO) algorithm on X-ray MRI images. Additionally, CNN Transfer Learning (TL) hyperparameters will optimized through MRFO, resulting in improved performance of model. Two public datasets from Kaggle were used build models. first dataset consists two classes, while 2nd includes three contrast-enhanced T1-weighted classes. First, a patient should diagnosed as "Healthy" (or "Tumor"). When scan returns result "Healthy," no abnormalities brain. If reveals that tumor, an performed them. After that, type tumor (i.e., meningioma, pituitary, glioma) identified second proposed classifier. A comparative analysis models two-class showed VGG16's model outperformed other Besides, Xception achieved best results three-class dataset. manual review misclassifications was conducted reasons for correct evaluation suggested architecture yielded 99.96% X-rays 98.64% MRIs. deep learning most current

Language: Английский

---

Brain tumor detection with integrating traditional and computational intelligence approaches across diverse imaging modalities - Challenges and future directions

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 175, P. 108412 - 108412

Published: April 16, 2024

Language: Английский

---

Multimodal brain tumor segmentation and classification from MRI scans based on optimized DeepLabV3+ and interpreted networks information fusion empowered with explainable AI

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 182, P. 109183 - 109183

Published: Oct. 2, 2024

Language: Английский

---

Coati optimization algorithm for brain tumor identification based on MRI with utilizing phase-aware composite deep neural network

Electromagnetic Biology and Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 18

Published: Jan. 21, 2025

Brain tumors can cause difficulties in normal brain function and are capable of developing various regions the brain. Malignant tumours develop quickly, pass through neighboring tissues, extend to further or central nervous system. In contrast, healthy typically slowly do not invade surrounding tissues. Individuals frequently struggle with sensory abnormalities, motor deficiencies affecting coordination, cognitive impairments memory focus. this research, Utilizing Phase-aware Composite Deep Neural Network Optimized Coati Algorithm for Tumor Identification Based on Magnetic resonance imaging (PACDNN-COA-BTI-MRI) is proposed. First, input images taken from tumour Dataset. To execute this, image pre-processed using Multivariate Fast Iterative Filtering (MFIF) it reduces occurrence over-fitting collected dataset; then feature extraction Self-Supervised Nonlinear Transform (SSNT) extract essential features like model, shape, intensity. Then, proposed PACDNN-COA-BTI-MRI implemented Matlab performance metrics Recall, Accuracy, F1-Score, Precision Specificity ROC analysed. Performance approach attains 16.7%, 20.6% 30.5% higher accuracy; 19.9%, 22.2% 30.1% recall 21.9% 30.8% precision when analysed existing techniques tumor identification MRI-Based Learning Approach Efficient Classification (MRI-DLA-ECBT), Detection Convolutional Methods Chosen Machine Techniques (MRI-BTD-CDMLT) Image CNN-Based Method (MRI-BTID-CNN) methods, respectively.

Language: Английский

---

Utilizing customized CNN for brain tumor prediction with explainable AI

Heliyon, Journal Year: 2024, Volume and Issue: 10(20), P. e38997 - e38997

Published: Oct. 1, 2024

Timely diagnosis of brain tumors using MRI and its potential impact on patient survival are critical issues addressed in this study. Traditional DL models often lack transparency, leading to skepticism among medical experts owing their "black box" nature. This study addresses gap by presenting an innovative approach for tumor detection. It utilizes a customized Convolutional Neural Network (CNN) model empowered three advanced explainable artificial intelligence (XAI) techniques: Shapley Additive Explana-tions (SHAP), Local Interpretable Model-agnostic Explanations (LIME), Gradient-weighted Class Activation Mapping (Grad-CAM). The utilized the BR35H dataset, which includes 3060 images encompassing both tumorous non-tumorous cases. proposed achieved remarkable training accuracy 100 % validation 98.67 %. Precision, recall, F1 score metrics demonstrated exceptional performance at 98.50 %, confirming Detailed result analysis, including confusion matrix, comparison with existing models, generalizability tests other datasets, establishes superiority sets new benchmark accuracy. By integrating CNN XAI techniques, research enhances trust AI-driven diagnostics offers promising pathway early detection potentially life-saving interventions.

Language: Английский

---

Cancerous and Non-Cancerous MRI Classification Using Dual DCNN Approach

Bioengineering, Journal Year: 2024, Volume and Issue: 11(5), P. 410 - 410

Published: April 23, 2024

Brain cancer is a life-threatening disease requiring close attention. Early and accurate diagnosis using non-invasive medical imaging critical for successful treatment patient survival. However, manual by radiologist experts time-consuming has limitations in processing large datasets efficiently. Therefore, efficient systems capable of analyzing vast amounts data early tumor detection are urgently needed. Deep learning (DL) with deep convolutional neural networks (DCNNs) emerges as promising tool understanding diseases like brain through modalities, especially MRI, which provides detailed soft tissue contrast visualizing tumors organs. DL techniques have become more popular current research on detection. Unlike traditional machine methods feature extraction, models adept at handling complex MRIs excel classification tasks, making them well-suited image analysis applications. This study presents novel Dual DCNN model that can accurately classify cancerous non-cancerous MRI samples. Our uses two well-performed models, i.e., inceptionV3 denseNet121. Features extracted from these appending global max pooling layer. The features then utilized to train the addition five fully connected layers finally samples or non-cancerous. retrained learn better accuracy. technique achieves 99%, 98%, 99% accuracy, precision, recall, f1-scores, respectively. Furthermore, this compares DCNN’s performance against various well-known including DenseNet121, InceptionV3, ResNet architectures, EfficientNetB2, SqueezeNet, VGG16, AlexNet, LeNet-5, different rates. indicates our proposed approach outperforms established terms performance.

Language: Английский

---

Advancing glioma diagnosis: Integrating custom U-Net and VGG-16 for improved grading in MR imaging

Mathematical Biosciences & Engineering, Journal Year: 2024, Volume and Issue: 21(3), P. 4328 - 4350

Published: Jan. 1, 2024

<abstract> <p>In the realm of medical imaging, precise segmentation and classification gliomas represent fundamental challenges with profound clinical implications. Leveraging BraTS 2018 dataset as a standard benchmark, this study delves into potential advanced deep learning models for addressing these challenges. We propose novel approach that integrates customized U-Net VGG-16 classification. The U-Net, its tailored encoder-decoder pathways, accurately identifies glioma regions, thus improving tumor localization. fine-tuned VGG-16, featuring output layer, precisely differentiates between low-grade high-grade gliomas. To ensure consistency in data pre-processing, standardized methodology involving gamma correction, augmentation, normalization is introduced. This integration surpasses existing methods, offering significantly improved diagnosis, validated by high dice scores (WT: 0.96, TC: 0.92, ET: 0.89), remarkable overall accuracy 97.89%. experimental findings underscore integrating learning-based methodologies enhancing diagnosis formulating subsequent treatment strategies.</p> </abstract>

Language: Английский

---

Neutrosophic Morphological Segmented Gaussian Regressive Deep Convolutional Network for MRI Images Brain Tumor Classification

Sensing and Imaging, Journal Year: 2025, Volume and Issue: 26(1)

Published: Jan. 25, 2025

Language: Английский

---

M-C&M-BL: a novel classification model for brain tumor classification: multi-CNN and multi-BiLSTM

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(3)

Published: Feb. 14, 2025

Language: Английский

---

FusionNet: Dual Input Feature Fusion Network with Ensemble Based Filter Feature Selection for Enhanced Brain Tumor Classification

Brain Research, Journal Year: 2025, Volume and Issue: unknown, P. 149507 - 149507

Published: Feb. 1, 2025

Language: Английский

---