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

---

Class distance weighted cross entropy loss for classification of disease severity

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126372 - 126372

Опубликована: Янв. 1, 2025

Язык: Английский

---

Interpretable deep learning architecture for gastrointestinal disease detection: A Tri-stage approach with PCA and XAI

Computers in Biology and Medicine, Год журнала: 2024, Номер 185, С. 109503 - 109503

Опубликована: Дек. 7, 2024

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

---

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

---

An efficient fine tuning strategy of segment anything model for polyp segmentation

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

Опубликована: Апрель 23, 2025

Colon cancer is a prevalent disease on global scale, thus making its detection and prevention critical area in the medical field. In addressing challenges of high annotation costs need for improved accuracy colon polyp detection, this study explores segment anything model (SAM) application fine-tuning strategies segmentation. Conventional full approaches frequently result catastrophic forgetting, thereby compromising model's generalization capabilities. To address challenge, paper proposes an efficient method, PSF-SAM, which mitigates forgetting while enhancing performance few-shot scenarios. This achieved by freezing most SAM parameters optimizing only specific structures. The efficacy PSF-SAM substantiated experimental evaluations Kvasir-SEG CVC-ClinicDB datasets, demonstrate superior metrics such as mDice coefficients mIoU, well notable advantages learning scenarios when compared to existing methods.

Язык: Английский

---

Mixed attention ensemble for esophageal motility disorders classification

PLoS ONE, Год журнала: 2025, Номер 20(2), С. e0317912 - e0317912

Опубликована: Фев. 14, 2025

Esophageal motility disorders result from dysfunction of the lower esophageal sphincter and abnormalities in peristalsis, often presenting symptoms such as dysphagia, chest pain, or heartburn. High-resolution manometry currently serves primary diagnostic method for these disorders, but it has some shortcomings including technical complexity, high demands on diagnosticians, time-consuming process. Therefore, based ensemble learning with a mixed voting mechanism multi-dimensional attention enhancement mechanism, classification model is proposed named ensemble(MAE) this paper, which integrates four distinct base models, utilizing to extract important features being weighted mechanism. We conducted extensive experiments through exploring three different strategies validating our approach proprietary dataset. The MAE outperforms traditional ensembles multiple metrics, achieving an accuracy 98.48% while preserving low parameter. experimental results demonstrate effectiveness method, providing valuable reference pre-diagnosis physicians.

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

---

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

---

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

---