A novel CNN-ViT-based deep learning model for early skin cancer diagnosis

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 104, С. 107627 - 107627

Опубликована: Янв. 28, 2025

Язык: Английский

---

A robust deep learning framework for multiclass skin cancer classification

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

Опубликована: Фев. 10, 2025

Skin cancer represents a significant global health concern, where early and precise diagnosis plays pivotal role in improving treatment efficacy patient survival rates. Nonetheless, the inherent visual similarities between benign malignant lesions pose substantial challenges to accurate classification. To overcome these obstacles, this study proposes an innovative hybrid deep learning model that combines ConvNeXtV2 blocks separable self-attention mechanisms, tailored enhance feature extraction optimize classification performance. The inclusion of initial two stages is driven by their ability effectively capture fine-grained local features subtle patterns, which are critical for distinguishing visually similar lesion types. Meanwhile, adoption later allows selectively prioritize diagnostically relevant regions while minimizing computational complexity, addressing inefficiencies often associated with traditional mechanisms. was comprehensively trained validated on ISIC 2019 dataset, includes eight distinct skin categories. Advanced methodologies such as data augmentation transfer were employed further robustness reliability. proposed architecture achieved exceptional performance metrics, 93.48% accuracy, 93.24% precision, 90.70% recall, 91.82% F1-score, outperforming over ten Convolutional Neural Network (CNN) based Vision Transformer (ViT) models tested under comparable conditions. Despite its robust performance, maintains compact design only 21.92 million parameters, making it highly efficient suitable deployment. Proposed Model demonstrates accuracy generalizability across diverse classes, establishing reliable framework clinical practice.

Язык: Английский

---

A deep architecture based on attention mechanisms for effective end-to-end detection of early and mature malaria parasites in a realistic scenario

Computers in Biology and Medicine, Год журнала: 2025, Номер 186, С. 109704 - 109704

Опубликована: Янв. 26, 2025

Язык: Английский

---

Lung and Colon Cancer Classification Using Multiscale Deep Features Integration of Compact Convolutional Neural Networks and Feature Selection

Technologies, Год журнала: 2025, Номер 13(2), С. 54 - 54

Опубликована: Фев. 1, 2025

The automated and precise classification of lung colon cancer from histopathological photos continues to pose a significant challenge in medical diagnosis, as current computer-aided diagnosis (CAD) systems are frequently constrained by their dependence on singular deep learning architectures, elevated computational complexity, ineffectiveness utilising multiscale features. To this end, the present research introduces CAD system that integrates several lightweight convolutional neural networks (CNNs) with dual-layer feature extraction selection overcome aforementioned constraints. Initially, it extracts attributes two separate layers (pooling fully connected) three pre-trained CNNs (MobileNet, ResNet-18, EfficientNetB0). Second, uses benefits canonical correlation analysis for dimensionality reduction pooling layer reduce complexity. In addition, features encapsulate both high- low-level representations. Finally, benefit multiple network architectures while reducing proposed merges dual variables then applies variance (ANOVA) Chi-Squared most discriminative integrated CNN architectures. is assessed LC25000 dataset leveraging eight distinct classifiers, encompassing various Support Vector Machine (SVM) variants, Decision Trees, Linear Discriminant Analysis, k-nearest neighbours. experimental results exhibited outstanding performance, attaining 99.8% accuracy cubic SVM classifiers employing merely 50 ANOVA-selected features, exceeding performance individual markedly diminishing framework’s capacity sustain exceptional limited set renders especially advantageous clinical applications where diagnostic precision efficiency critical. These findings confirm efficacy multi-CNN, multi-layer methodology enhancing mitigating constraints systems.

Язык: Английский

---

An Innovative Deep Learning Framework for Skin Cancer Detection Employing ConvNeXtV2 and Focal Self-Attention Mechanisms

Results in Engineering, Год журнала: 2024, Номер unknown, С. 103692 - 103692

Опубликована: Дек. 1, 2024

Язык: Английский

---

Skin cancer classification leveraging multi-directional compact convolutional neural network ensembles and gabor wavelets

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Сен. 4, 2024

Язык: Английский

---

Can deep learning effectively diagnose cardiac amyloidosis with 99mTc-PYP scintigraphy?

Journal of Radioanalytical and Nuclear Chemistry, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 19, 2024

Язык: Английский

---

Cf-Wiad: Consistency Fusion with Weighted Instance and Adaptive Distribution for Enhanced Semi-Supervised Skin Lesion Classification

Опубликована: Янв. 1, 2025

Язык: Английский

---

Enhancing Skin Cancer Detection Through Category Representation and Fusion of Pre-Trained Models

Опубликована: Янв. 1, 2025

Язык: Английский

---

Enhancing Skin Cancer Diagnosis Through Fine‐Tuning of Pretrained Models: A Two‐Phase Transfer Learning Approach

International Journal of Breast Cancer, Год журнала: 2025, Номер 2025(1)

Опубликована: Янв. 1, 2025

Skin cancer is among the most prevalent types of worldwide, and early detection crucial for improving treatment outcomes patient survival rates. Traditional diagnostic methods, often reliant on visual examination manual evaluation, can be subjective time-consuming, leading to variability in accuracy. Recent developments machine learning, particularly using pretrained models fine-tuning techniques, offer promising advancements automating skin classification. This paper explores application a two-phase model HAM10000 dataset, which comprises wide range lesion images. The first phase employs transfer learning with frozen layers, followed by all layers second adapt more specifically dataset. I evaluate nine models, including VGG16, VGG19, InceptionV3, Xception (extreme inception), DenseNet121, assessing their performance based accuracy, precision, recall, F1 score metrics. VGG16 model, after fine-tuning, achieved highest test set accuracy 99.3%, highlighting its potential highly accurate study provides important insights clinicians researchers, demonstrating efficacy advanced enhancing supporting clinical decision-making dermatology.

Язык: Английский

---