Aug 2026· International journal of computer information systems and industrial management applications· Vol 18, pp. 1426-1443· 0 citations
TL;DR
The findings highlight the effectiveness of combining attention-based feature refinement and morphology-aware learning for robust disease detection, making the proposed framework suitable for real-world veterinary diagnostic applications.
Abstract
Lumpy Skin Disease (LSD) is a highly contagious viral disease that significantly impacts livestock productivity and agricultural economies worldwide. Traditional diagnostic approaches, including manual inspection and laboratory testing, are often time-consuming, resource-intensive, and unsuitable for rapid field-level deployment. To address these limitations, this study proposes M-LSA-Net, a hybrid morphology-aware deep learning framework for accurate and efficient detection of LSD from cattle skin images. The proposed model integrates MixUp-based data augmentation for improved generalization, LUMPNet-based region-focused feature extraction for capturing lesion-specific patterns, an Attention-Based Sparse Autoencoder (AB-SAE) for adaptive feature selection, and a Morphology-Aware Deep Classifier (MADC) for capturing both local texture and global structural patterns. The model was evaluated on a publicly available dataset using an 80:20 train–test split and assessed using standard performance metrics. Experimental results demonstrate that M-LSA-Net achieves an accuracy of 98.71%, precision of 98.68%, recall of 98.71%, F1-score of 98.69%, and ROC-AUC of 0.9978, outperforming baseline models such as CoAtNet, SwinT V2, and MaxViT. The findings highlight the effectiveness of combining attention-based feature refinement and morphology-aware learning for robust disease detection, making the proposed framework suitable for real-world veterinary diagnostic applications.
Lumpy skin disease (LSD) is a highly contagious viral infection that severely impacts cattle health and livestock productivity worldwide, necessitating reliable and automated diagnostic solutions. Recent advances in deep learning (DL) have demonstrated significant potential for image-based disease classification; however, achieving robust performance under real-world variability and class imbalance remains a critical challenge. In this study, we propose ConvNeXtLSD, a DL-based multi-class classification framework for automated cattle LSD diagnosis. The proposed model is built upon a modified ConvNeXt backbone architecture, consisting of a patchify stem followed by four hierarchical feature extraction stages composed of ConvNeXt blocks and downsampling layers, enabling effective multi-scale representation learning. To enhance class separability, the standard classification head is redesigned using feature flattening and layer normalization, which improves feature distribution stability and discriminative capability. Extensive experiments on a five-class cattle LSD dataset containing 8,014 images demonstrate that ConvNeXtLSD achieves superior classification performance, with an accuracy of 98.29%, a precision of 95.82%, an F1-score of 96.58%, and a Cohen’s Kappa coefficient of 97.51%. Moreover, the proposed framework maintains practical computational efficiency with 15.372 GFLOPs and a real-time inference speed of 90.18 FPS, demonstrating an effective balance between predictive performance and computational cost for real-world livestock disease diagnosis.
Mostafa Farouk Senussi, Abdelrahman S. Heikal, Asmaa Gamal Abdelbasset et al.· Scientific Reports· 0 citations
Skin cancer is considered a deadly disease globally, and the timely identification of the disease may save human life. This research presents a CNN–Transformer-based fusion framework for automated multi-class skin lesion classification. This approach combines ResNet50 and Vision Transformer (ViT) to categorize skin lesions using the HAM10000 dataset. To assess their efficacy, a comparison with CNN and ViT models is also carried out. Seven classes of skin cancer are used for training the models, and class weighting is used to correct dataset asymmetry. According to the experimental dataset, the suggested hybrid framework shows improved performance over CNN and ViT, considering the accuracy (0.97) and macro-averaged F1-score (0.95). Furthermore, the efficiency of the suggested model is demonstrated by the fact that it delivers performance that is competitive with several existing approaches. Overall results indicate that hybrid CNN–Transformer architectures present a viable path for automated skin lesion categorization. Grad-CAM++ is integrated to enhance model understanding and promote medical confidence by enabling physicians to view visualizations that show the areas impacting the model’s conclusions. But there are still issues, including poor generalization, computational complexity, and a lack of external validation. Future research will concentrate on enhancing interpretability for practical implementation, integrating clinical information, and evaluating several datasets.
Skin cancer is one of the most common forms of cancer globally, with melanoma being the most fatal form. Early and precise detection is crucial for improving treatment outcomes, as timely disease management dramatically increases survival rates. This study presents a reliable multimodal deep learning framework that integrates dermoscopic images, 3D Total Body Photography scans, and patient clinical data to enhance diagnostic accuracy in skin cancer classification. The dataset comprised a combination of publicly available sources, including the recently released ISIC 2024 dataset. An XGBoost algorithm is utilized to get the predictions from the clinical data. For image-based analysis, this study proposes a Modality-Specific Patch Embedding Data efficient image Transformer (MSPE-DeiT) that uses a modality-specific patch embedding layer to train on the dermoscopic and 3D-TBP images. MSPE-DeiT is capable of capturing both local and global contextual information from high-resolution lesion images. Furthermore, this work uses an Artificial Neural Network (ANN) architecture for clinical data classification. Bayesian optimization is applied to fine-tune the ANN’s hyperparameters, effectively mitigating vanishing gradient issues and improving model convergence. A Soft-Voting Ensemble classifier is used to integrate the results of all three models for better generalization on the unseen data. Experimental results demonstrate improvements in diagnostic accuracy on a multimodal held-out test set of around 80k images from the ISIC 2024 dataset, achieving an accuracy of 91.76%, an Area Under the Receiver Operating Characteristic Curve of 0.953, a specificity of 91.77%, and a sensitivity of 84.81%. The proposed approach is computationally inexpensive with an inference latency of 6.2 ms and a memory footprint of 83.59 MB, making it fit for deployment in clinical scenarios.
Uttam Mittal, S. Varpe, A. Sharma et al.· IEEE Access· 0 citations
The research explores the utilization of Stable Diffusion models for synthetic image augmentation aimed at generating an improved dataset to enhance the performance of deep learning models in diagnosing skin diseases. The study utilizes the HAM10000 dataset, which consists of seven skin lesion categories exhibiting severe class imbalance, to fine-tune a class-conditional Stable Diffusion model for minority-class image synthesis. The resultant synthetic images, evaluated at a Fréchet Inception Distance (FID) of 98.0, are combined with real training images to train a dual-branch hybrid architecture,SkinHybrid,fusing EfficientNet and Vision Transformer (ViT) representations. An ablation study demonstrates that incorporating Stable Diffusion-generated samples improves the weighted F1-score from 84.1% to 97.0%. Post-hoc explainability via Grad-CAM confirms that the model attends to clinically relevant dermoscopic morphology
Aman Babu Shrestha, Abhigan Babu Shrestha, Sajeena Shrestha· Islington Journal of Multidi...· 0 citations
A deep learning–based system for automated detection of viral and related skin diseases using image classification and segmentation techniques and integrates the trained model into a real-time Flask-based web application for practical deployment is presented.
Genevieve A. Pilongo, Christopher Josh L. Dellosa, Andre Miguel C. Bacaling et al.· International Conference on...· 0 citations
The recent re-emergence of Monkeypox emphasizes the critical importance of ensuring precise and prompt diagnostic capabilities. Traditional diagnosis typically depends on visually examining skin lesions and listening to patients describe their symptoms. However, this approach can be subjective and sometimes leads to misjudgment. To complicate matters further, Monkeypox shares many symptoms with other skin conditions and viral infections, making it difficult for doctors to identify the disease accurately in its early stages. In response, we present Tri-Net, a novel deep learning approach that integrates skin lesion analysis with symptom-based prediction for reliable detection of Monkeypox infection. The skin lesion module leverages an ensemble of three powerful architectures EfficientNetB4, Inception-ResNet V2, and DenseNet201 within the Tri-Net framework to classify images across different stages of the disease. Complementing this, a dedicated Convolutional Neural Network (CNN) processes patient-reported symptoms to further improve diagnostic precision. Our proposed Tri-Net model was trained on publicly available Monkeypox Skin Lesion Dataset (MSLD) comprises diverse dermatological lesion imagery and clinical symptom profiles. The combined approach demonstrated high accuracy, robustness, and significantly outperformed existing methods. Notably, the symptom-based module alone achieved a prediction accuracy of 97.86%. By uniting visual and clinical features, Tri-Net offers a non-invasive, rapid, and highly accurate diagnostic tool that supports early intervention and effective disease control. This study marks a meaningful step toward AI-driven diagnostics for emerging infectious diseases like Monkeypox.
S. Sudharsan, Prabu Selvam, Nirmala Veeramani et al.· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
