A hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 10, 2025

Brain tumors present a significant global health challenge, and their early detection accurate classification are crucial for effective treatment strategies. This study presents novel approach combining lightweight parallel depthwise separable convolutional neural network (PDSCNN) hybrid ridge regression extreme learning machine (RRELM) accurately classifying four types of brain (glioma, meningioma, no tumor, pituitary) based on MRI images. The proposed enhances the visibility clarity tumor features in images by employing contrast-limited adaptive histogram equalization (CLAHE). A PDSCNN is then employed to extract relevant tumor-specific patterns while minimizing computational complexity. RRELM model proposed, enhancing traditional ELM improved performance. framework compared with various state-of-the-art models terms accuracy, parameters, layer sizes. achieved remarkable average precision, recall, accuracy values 99.35%, 99.30%, 99.22%, respectively, through five-fold cross-validation. PDSCNN-RRELM outperformed pseudoinverse (PELM) exhibited superior introduction led enhancements performance parameters sizes those models. Additionally, interpretability was demonstrated using Shapley Additive Explanations (SHAP), providing insights into decision-making process increasing confidence real-world diagnosis.

Язык: Английский

---

An Advanced Deep Learning Framework for Multi-Class Diagnosis from Chest X-ray Images

J — Multidisciplinary Scientific Journal, Год журнала: 2024, Номер 7(1), С. 48 - 71

Опубликована: Янв. 22, 2024

Chest X-ray imaging plays a vital and indispensable role in the diagnosis of lungs, enabling healthcare professionals to swiftly accurately identify lung abnormalities. Deep learning (DL) approaches have attained popularity recent years shown promising results automated medical image analysis, particularly field chest radiology. This paper presents novel DL framework specifically designed for multi-class diseases, including fibrosis, opacity, tuberculosis, normal, viral pneumonia, COVID-19 using images, aiming address need efficient accessible diagnostic tools. The employs convolutional neural network (CNN) architecture with custom blocks enhance feature maps learn discriminative features from images. proposed is evaluated on large-scale dataset, demonstrating superior performance lung. In order evaluate effectiveness presented approach, thorough experiments are conducted against pre-existing state-of-the-art methods, revealing significant accuracy, sensitivity, specificity improvements. findings study showcased remarkable achieving 98.88%. metrics precision, recall, F1-score, Area Under Curve (AUC) averaged 0.9870, 0.9904, 0.9887, 0.9939 across six-class categorization system. research contributes provides foundation future advancements DL-based systems diseases.

Язык: Английский

---

Improving Malaria diagnosis through interpretable customized CNNs architectures

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 22, 2025

Abstract Malaria, which is spread via female Anopheles mosquitoes and brought on by the Plasmodium parasite, persists as a serious illness, especially in areas with high mosquito density. Traditional detection techniques, like examining blood samples microscope, tend to be labor-intensive, unreliable necessitate specialized individuals. To address these challenges, we employed several customized convolutional neural networks (CNNs), including Parallel network (PCNN), Soft Attention Convolutional Neural Networks (SPCNN), after Functional Block (SFPCNN), improve effectiveness of malaria diagnosis. Among these, SPCNN emerged most successful model, outperforming all other models evaluation metrics. The achieved precision 99.38 $$\pm$$ 0.21%, recall 99.37 F1 score accuracy ± 0.30%, an area under receiver operating characteristic curve (AUC) 99.95 0.01%, demonstrating its robustness detecting parasites. Furthermore, various transfer learning (TL) algorithms, VGG16, ResNet152, MobileNetV3Small, EfficientNetB6, EfficientNetB7, DenseNet201, Vision Transformer (ViT), Data-efficient Image (DeiT), ImageIntern, Swin (versions v1 v2). proposed model surpassed TL methods every measure. 2.207 million parameters size 26 MB, more complex than PCNN but simpler SFPCNN. Despite this, exhibited fastest testing times (0.00252 s), making it computationally efficient both We assessed interpretability using feature activation maps, Gradient-weighted Class Activation Mapping (Grad-CAM) SHapley Additive exPlanations (SHAP) visualizations for three architectures, illustrating why outperformed others. findings from our experiments show significant improvement parasite approach outperforms traditional manual microscopy terms speed. This study highlights importance utilizing cutting-edge technologies develop robust effective diagnostic tools prevention.

Язык: Английский

---

Transparent and Accurate COVID-19 Diagnosis: Integrating Explainable AI with Advanced Deep Learning in CT Imaging

Computer Modeling in Engineering & Sciences, Год журнала: 2024, Номер 139(3), С. 3101 - 3123

Опубликована: Янв. 1, 2024

In the current landscape of COVID-19 pandemic, utilization deep learning in medical imaging, especially chest computed tomography (CT) scan analysis for virus detection, has become increasingly significant.Despite its potential, learning's "black box" nature been a major impediment to broader acceptance clinical environments, where transparency decision-making is imperative.To bridge this gap, our research integrates Explainable AI (XAI) techniques, specifically Local Interpretable Model-Agnostic Explanations (LIME) method, with advanced models.This integration forms sophisticated and transparent framework identification, enhancing capability standard Convolutional Neural Network (CNN) models through transfer data augmentation.Our approach leverages refined DenseNet201 architecture superior feature extraction employs augmentation strategies foster robust model generalization.The pivotal element methodology use LIME, which demystifies process, providing clinicians clear, interpretable insights into AI's reasoning.This unique combination an optimized Deep (DNN) LIME not only elevates precision detecting cases but also equips healthcare professionals deeper understanding diagnostic process.Our validated on SARS-COV-2 CT-Scan dataset, demonstrates exceptional accuracy, performance metrics that reinforce potential seamless modern systems.This innovative marks significant advancement creating explainable trustworthy tools decisionmaking ongoing battle against COVID-19.

Язык: Английский

---

Comparative Analysis of Kolmogorov-Inspired CNN and Traditional CNN Models for Pneumonia Detection: A Study on Chest CT Images

International Journal of Statistics in Medical Research, Год журнала: 2025, Номер 14, С. 38 - 44

Опубликована: Фев. 5, 2025

Aim: In this study, our goal is to compare the effectiveness of Kolmogorov Inspired Convolutional Neural Networks (KAN) with traditional (CNN) models in pneumonia detection and contribute development more efficient accurate diagnostic tools field medical imaging. Methods: Both are structured same layers hyperparameters ensure a fair comparison their performance. For robust evaluation, relevant dataset was divided into 80% for training 20% testing. Results Conclusion: Performance metrics KAN; 95.2% sensitivity, 97.6% specificity, 94.1% precision, 96.9% accuracy (Acc), 0.9466 F1 score (F1) 0. 9251 Matthews Correlation Coefficient (MCC), while CNN model found 92.5%, 96.4%, 91.2%, 95.3%, 0.9188 0.8858 criteria, indicating that KAN outperformed. This emphasizes has potential be effective chest CT images.

Язык: Английский

---

HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 18, 2025

Язык: Английский

---

Innovative deep learning solutions for Turkish butterfly species identification: a VGGNet enhancement study

Signal Image and Video Processing, Год журнала: 2025, Номер 19(5)

Опубликована: Март 10, 2025

Язык: Английский

---

Medivision: Empowering Colorectal Cancer Diagnosis and Tumor Localization Through Supervised Learning Classifications and Grad-CAM Visualization of Medical Colonoscopy Images

Cognitive Computation, Год журнала: 2025, Номер 17(2)

Опубликована: Март 21, 2025

Язык: Английский

---

Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 22, 2025

Abstract Accurate brain tumor segmentation is critical for clinical diagnosis and treatment planning. This study proposes an advanced framework that combines Multiscale Attention U-Net with the EfficientNetB4 encoder to enhance performance. Unlike conventional U-Net-based architectures, proposed model leverages EfficientNetB4’s compound scaling optimize feature extraction at multiple resolutions while maintaining low computational overhead. Additionally, Multi-Scale Mechanism (utilizing $$1\times 1, 3\times 3$$ , $$5\times 5$$ kernels) enhances representation by capturing boundaries across different scales, addressing limitations of existing CNN-based methods. Our approach effectively suppresses irrelevant regions localization through attention-enhanced skip connections residual attention blocks. Extensive experiments were conducted on publicly available Figshare dataset, comparing EfficientNet variants determine optimal architecture. demonstrated superior performance, achieving Accuracy 99.79%, MCR 0.21%, Dice Coefficient 0.9339, Intersection over Union (IoU) 0.8795, outperforming other in accuracy efficiency. The training process was analyzed using key metrics, including Coefficient, dice loss, precision, recall, specificity, IoU, showing stable convergence generalization. method evaluated against state-of-the-art approaches, surpassing them all accuracy, mean IoU. demonstrates effectiveness robust efficient tumors, positioning it as a valuable tool research applications.

Язык: Английский

---

Enhancing Clinical Documentation Through NLP-Driven Disease Categorization and Visualization: A Case Study Utilizing the Llama2 AI Model

Communications in computer and information science, Год журнала: 2025, Номер unknown, С. 193 - 209

Опубликована: Янв. 1, 2025

Язык: Английский

---