Meta-Learning Based Softmax Average of Convolutional Neural Networks Using Multi-Layer Perceptron for Brain Tumour Classification

Array, Journal Year: 2025, Volume and Issue: unknown, P. 100398 - 100398

Published: April 1, 2025

Language: Английский

---

Explainable deep stacking ensemble model for accurate and transparent brain tumor diagnosis

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 191, P. 110166 - 110166

Published: April 17, 2025

Early detection of brain tumors in MRI images is vital for improving treatment results. However, deep learning models face challenges like limited dataset diversity, class imbalance, and insufficient interpretability. Most studies rely on small, single-source datasets do not combine different feature extraction techniques better classification. To address these challenges, we propose a robust explainable stacking ensemble model multiclass tumor that combines EfficientNetB0, MobileNetV2, GoogleNet, Multi-level CapsuleNet, using CatBoost as the meta-learner improved aggregation classification accuracy. This approach captures complex characteristics while enhancing robustness The proposed integrates CapsuleNet within framework, utilizing to improve We created two large by merging data from four sources: BraTS, Msoud, Br35H, SARTAJ. tackle applied Borderline-SMOTE augmentation. also utilized methods, along with PCA Gray Wolf Optimization (GWO). Our was validated through confidence interval analysis statistical tests, demonstrating superior performance. Error revealed misclassification trends, assessed computational efficiency regarding inference speed resource usage. achieved 97.81% F1 score 98.75% PR AUC M1, 98.32% 99.34% M2. Moreover, consistently surpassed state-of-the-art CNNs, Vision Transformers, other methods classifying across individual datasets. Finally, developed web-based diagnostic tool enables clinicians interact visualize decision-critical regions scans Explainable Artificial Intelligence (XAI). study connects high-performing AI real clinical applications, providing reliable, scalable, efficient solution

Language: Английский

---

Advancements in Brain Tumour Analysis: A Review of Machine Learning, Deep Learning, Image Processing, and Explainable AI Techniques

Operations Research Forum, Journal Year: 2025, Volume and Issue: 6(2)

Published: May 5, 2025

Language: Английский

---

Efficient and accurate brain tumor detection and classification using advanced hybrid filtering and self-attention generative adversarial networks

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: May 7, 2025

Language: Английский

---

Brain Tumor Detection and Classification Using an Optimized Convolutional Neural Network

Diagnostics, Journal Year: 2024, Volume and Issue: 14(16), P. 1714 - 1714

Published: Aug. 7, 2024

Brain tumors are a leading cause of death globally, with numerous types varying in malignancy, and only 12% adults diagnosed brain cancer survive beyond five years. This research introduces hyperparametric convolutional neural network (CNN) model to identify tumors, significant practical implications. By fine-tuning the hyperparameters CNN model, we optimize feature extraction systematically reduce complexity, thereby enhancing accuracy tumor diagnosis. The critical include batch size, layer counts, learning rate, activation functions, pooling strategies, padding, filter size. hyperparameter-tuned was trained on three different MRI datasets available at Kaggle, producing outstanding performance scores, an average value 97% for accuracy, precision, recall, F1-score. Our optimized is effective, as demonstrated by our methodical comparisons state-of-the-art approaches. hyperparameter modifications enhanced strengthened its capacity generalization, giving medical practitioners more accurate effective tool making crucial judgments regarding step right direction toward trustworthy diagnosis, implications improving patient outcomes.

Language: Английский

---

MRI-Based Brain Tumour Classification Using Convolutional Neural Networks: A Systematic Review and Meta-Analysis

British Journal of Computer Networking and Information Technology, Journal Year: 2024, Volume and Issue: 7(4), P. 27 - 46

Published: Oct. 9, 2024

This research assessed advancements in brain tumour classification using convolutional neural networks (CNNs) and MRI data. An analysis of 37 studies highlighted the effectiveness CNN architectures pre-processing methods accurately categorising tumours. Issues such as class disparities model interpretability were identified, prompting recommendations for advanced deep learning techniques, ensemble methods, diverse datasets to enhance diagnostic accuracy. The findings underscored importance these achieving high accuracy, with a maximum rate 98.80% from 154 images. systematic study also included meta-analysis 2018 2022, revealing patterns cases across demographics providing insights into healthcare trends.

Language: Английский

---

IMPA-Net: Interpretable Multi-Part Attention Network for Trustworthy Brain Tumor Classification from MRI

Diagnostics, Journal Year: 2024, Volume and Issue: 14(10), P. 997 - 997

Published: May 11, 2024

Deep learning (DL) networks have shown attractive performance in medical image processing tasks such as brain tumor classification. However, they are often criticized mysterious "black boxes". The opaqueness of the model and reasoning process make it difficult for health workers to decide whether trust prediction outcomes. In this study, we develop an interpretable multi-part attention network (IMPA-Net) classification enhance interpretability trustworthiness proposed not only predicts grade but also provides a global explanation local justification proffered prediction. Global is represented group feature patterns that learns distinguish high-grade glioma (HGG) low-grade (LGG) classes. Local interprets individual by calculating similarity between prototypical parts pre-learned task-related features. Experiments conducted on BraTS2017 dataset demonstrate IMPA-Net verifiable task. A percentage 86% were assessed two radiologists be valid representing task-relevant shows accuracy 92.12%, which 81.17% evaluated trustworthy based explanations. Our can used decision aids Compared with black-box CNNs, allows patients understand

Language: Английский

---

Brain tumor classification utilizing pixel distribution and spatial dependencies higher-order statistical measurements through explainable ML models

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 28, 2024

Brain tumors are among the most fatal and devastating diseases, they often result in a significant reduction life expectancy. The devising of treatment plans that can extend lives affected individuals hinges on an accurate diagnosis these tumors. Identifying analyzing large volumes magnetic resonance imaging (MRI) data manually proves to be both challenging time-consuming. As result, there exists pressing need for reliable machine-learning approach accurately diagnose brain tumors, numerous methods have already been proposed over last decade. In this paper, novel, comprehensive is identifying classifying given MR image as abnormal. Three common namely glioma, meningioma, pituitary tumor, chosen abnormal brains, Figshare MRI dataset was collected from Kaggle IEEE websites. method initiated by employing 1st-order statistics, 2nd-order higher-order transformed (DWT) feature extraction extract features images. Then missing addressed handled using KNNImputer, followed application ExtratreesClassifier PCA selection identify relevant reduce dimensions features. Subsequently, reduced submitted seven machine learning models, RF, GB, CB, SVM, LGBM, DT, LR. strategy k-fold cross-validation utilized enhance performance those models. Finally, models evaluated XAI approaches, which ensure transparent decision-making processes provide insights into model's predictions. Remarkably, our achieves highest accuracy, precision, recall, F1 score, MCC, Kappa, AUC-ROC, R2, well lowest loss, evaluated, proving its effectiveness applicability multiple analytic applications relying publicly available datasets.

Language: Английский

---

Optimized attention-based lightweight CNN using particle swarm optimization for brain tumor classification

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 100, P. 107126 - 107126

Published: Nov. 14, 2024

Language: Английский

---

Remote sensing image scene recognition based on densenet-169

Published: June 13, 2024

Scene classification has become an effective technique for classifying high spatial resolution remote sensing images. However, in the traditional deep learning convolutional neural network, as image passes through layers some of features will be gradually lost, resulting a significant decrease accuracy and precision scene recognition, there is problem underutilization features. In addition, images themselves have complexity. To overcome these challenges, we adopt DenseNet network. Specifically, first train from UCMerced dataset network inputs. Then, introduced DenseNet-169 model based on migration learning. Compared with DenseNet-121, more layers, this difference mainly manifested number dense blocks.DenseNet-169 which increases complexity parameters model, bringing following advantages: stronger expressive power, enables extraction complex feature patterns; faster training time, thanks to densely-connected nature, efficiently utilizes gradient flow; better generalization ability, especially large-scale datasets. our experiments, shows excellent performance compared other state-of-the-art networks dataset, 95.14%, 95.31%, Kappa coefficient 94.90%, F1-score 95.11%. The experimental results show that method can make full use good visual effect, providing recognition.

Language: Английский

---