Detection and Classification of Dog Skin Disease using Deep Learning

Recent advances in deep learning have significantly transformed medical diagnostics, particularly in dermatology. Accurate skin disease detection and classification areessential for effective treatment and improved patient outcomes. This systematic review examines deep learning approaches, including Convolutional Neural Networks (CNNs) and transfer learning, for automated dermatological diagnosis. Public datasets such as HAM10000 and ISIC play a key role in training robust models; however, challenges including dataset imbalance, disease heterogeneity, and overfitting remain. Techniques such as ensemble learning, attention mechanisms, explainable artificial intelligence, data augmentation, hybrid models, and task-specific loss functions have been shown to enhance accuracy, robustness, and interpretability. This study follows a systematic review methodology in accordance with the PRISMA guidelines. The review synthesizes 17 studies published between 2021 and 2024, highlighting the potential of deep learning to support scalable and reliable dermatological diagnostic systems.

- Skin diseases are among the most prevalent health problems worldwide, affecting millions of people across different age groups and regions. Early and accurate diagnosis is essential to prevent severe complications, particularly in life-threatening cases such as melanoma. However, manual diagnosis through clinical examination or biopsy is often time-consuming, costly, and subjective, leading to inconsistent outcomes. To overcome these limitations, this study proposes an automated Skin Disease Diagnosis System using Machine Learning, which leverages Deep Learning (DL) and Transfer Learning (TL) techniques for precise classification of dermatological images. The proposed system employs a Convolutional Neural Network (CNN) architecture using pre-trained MobileNetV2 and EfficientNetB0 models, fine-tuned on a curated dataset of multiple skin disease classes including benign, malignant (melanoma), eczema, psoriasis, fungal, and normal skin. The images are preprocessed through resizing, normalization, and augmentation to enhance generalization and minimize overfitting. Keywords: Skin Disease Detection, Deep Learning, Machine Learning, MobileNetV2, EfficientNetB0, Transfer Learning, CNN, Image Classification.

Psoriasis is a chronic, noncontagious skin condition that cannot be cured but its early detection can help prevent serious life-threatening complications. The high visual similarity between normal skin and psoriasis has made the detection of psoriasis a very complex task. Moreover, it can be confused with different skin abnormalities like eczema, tinea corporis, lichen planus, pityriasis, dandruff, seborrheic dermatitis. Image processing using deep learning has proven better than other approaches in this context because of its automatic feature extractions with intelligent decisions and less chances of distorted features. In this paper, automated detection of psoriasis using deep learning has been proposed. To obtain good results for a small dataset transfer learning mechanism is used in which pre-trained deep learning models are applied on a dataset to obtain the required results. Firstly, different transfer learning models are applied on our data to work on the best-obtained accuracy. Among them, ResNeXt gave the best output for an appropriate accuracy to detect psoriasis from healthy skin as well as other skin diseases. Secondly, we have worked on facilitating the development of an automated system that classifies psoriasis, lichen planus, eczema, seborrheic dermatitis, pityriasis, normal skin, and tinea corporis diseases by applying and improving the final layers of the pre-trained model. We have obtained an accuracy of 94% on test images with 2 classifiers and output to show if the input image is classified as psoriasis or not. Finally, we have also applied the classifier on 3 classes; normal skin, psoriasis, and other skin diseases, and obtained good results

BackgroundThere is a high prevalence of skin diseases sub-Saharan Africa, including skin neglected tropical diseases (NTDs) that could lead to lifelong disabilities and deformities if not diagnosed and treated early. To achieve early detection and early treatment of these skin diseases, we developed a mobile health app, eSkinHealth.ObjectiveThis paper outlines a protocol for evaluating the effect of our eSkinHealth app in the early detection and effective management of skin diseases in Côte d’Ivoire.MethodsA mixed methods pilot trial will be conducted in Côte d’Ivoire and will consist of 3 phases: (1) the development and improvement of the eSkinHealth app, (2) a pilot trial to evaluate the usability of the eSkinHealth app for local medical staff in Côte d’Ivoire, and (3) a pilot trial to evaluate the effectiveness of early detection and case management of targeted skin NTDs (Buruli ulcer, leprosy, yaws, and lymphatic filariasis) with the eSkinHealth app in Côte d’Ivoire. The pilot study will be implemented as a 2-arm trial with local health care providers and patients with skin NTDs over a 3-month follow-up period. The local health care providers will be assigned to an intervention group receiving the eSkinHealth app to be used in their daily practices or a control group. Training will be provided on the use and implementation of the app and the diagnostic pipeline to the intervention group only, while both groups will receive training on skin diseases. Our primary outcome is to evaluate the early detection and effective management of skin diseases using the eSkinHealth app in Côte d’Ivoire by the number of cases diagnosed and managed. Additionally, we will evaluate the eSkinHealth app with validated questionnaires and in-depth interviews. Procedures of our methods have been reviewed and approved by the Institutional Review Board of the Ministry of Health, Côte d’Ivoire and by Tulane University in 2021.ResultsThis study was funded in 2021. We started the enrollment of patients in February 2022, and data collection is currently underway. We expect the first results to be submitted for publication in 2023.ConclusionsOur eSkinHealth app is a field-adapted platform that could provide both direct diagnostic and management assistance to health workers in remote settings. The study will provide evidence for the usability and the effectiveness of the eSkinHealth app to improve the early detection and case management of skin NTDs in Côte d’Ivoire and, furthermore, is expected to contribute to knowledge on mobile health approaches in the control of skin NTDs.Trial RegistrationClinicalTrials.gov NCT05300399; https://clinicaltrials.gov/ct2/show/study/NCT05300399International Registered Report Identifier (IRRID)DERR1-10.2196/39867

ObjectivesSkin diseases account for 1.79% of the global disease burden, though their impact may be underreported due to limited research. Raising awareness about early detection is essential, but tools to measure this are scarce. This study aimed to develop and validate a questionnaire assessing community awareness and early detection of common skin diseases, including leprosy, in Indonesia.MethodsThe questionnaire was drafted in English, translated into Bahasa Indonesia, and tested for face validity, content validity, and internal consistency. A pilot test with 25 participants and a field test with 680 participants were conducted. Results were analyzed using Cronbach alpha and descriptive methods.ResultsThe final questionnaire comprised 17 questions on skin disease: common knowledge, intentions on prevention and health-seeking behavior. Validity and internal consistency were confirmed during pilot testing, and no participants in the field test reported confusion. The Cronbach alpha score exceeded 0.70, confirming strong internal consistency.ConclusionThis validated questionnaire can assess public awareness of early skin disease detection. It is available for international adaptation and may help improve early detection and prevention in Indonesia’s healthcare system.

Hybrid deep learning architecture for skin disease classification

BackgroundOnchocerciasis (river-blindness) in Africa is targeted for elimination through mass drug administration (MDA) with ivermectin. Onchocerciasis may cause various types of skin and eye disease. Predicting the impact of MDA on onchocercal morbidity is useful for future policy development. Here, we introduce a new disease module within the established ONCHOSIM model to predict trends over time in prevalence of onchocercal morbidity.MethodsWe developed novel generic model concepts for development of symptoms due to cumulative exposure to dead microfilariae, accommodating both reversible (acute) and irreversible (chronic) symptoms. The model was calibrated to reproduce pre-control age patterns and associations between prevalences of infection, eye disease, and various types of skin disease as observed in a large set of population-based studies. We then used the new disease module to predict the impact of MDA on morbidity prevalence over a 30-year time frame for various scenarios.ResultsONCHOSIM reproduced observed age-patterns in disease and community-level associations between infection and disease reasonably well. For highly endemic settings with 30 years of annual MDA at 60% coverage, the model predicted a 70% to 89% reduction in prevalence of chronic morbidity. This relative decline was similar with higher MDA coverage and only somewhat higher for settings with lower pre-control endemicity. The decline in prevalence was lowest for mild depigmentation and visual impairment. The prevalence of acute clinical manifestations (severe itch, reactive skin disease) declined by 95% to 100% after 30 years of annual MDA, regardless of pre-control endemicity.ConclusionWe present generic model concepts for predicting trends in acute and chronic symptoms due to history of exposure to parasitic worm infections, and apply this to onchocerciasis. Our predictions suggest that onchocercal morbidity, in particular chronic manifestations, will remain a public health concern in many epidemiological settings in Africa, even after 30 years of MDA.

Accurate detection of skin diseases is essential for timely intervention and treatment. This article proposes a patch-based, interpretable deep learning framework for skin disease detection using wearable sensors and clinical data. Specifically, a fully convolutional residual neural network (FCRN) is employed to extract local features from high-resolution skin images captured via wearable sensors, using a patch-level training approach. Pre-processing techniques—including image resampling, intensity normalization, and noise reduction—standardize the input data to ensure consistency across sensor variations. To enhance local feature learning, the FCRN incorporates residual modules, which mitigate gradient vanishing and improve model performance. The framework generates disease probability maps that visualize regions of high diagnostic risk, providing interpretable insights into skin anomalies. In the proposed methodology, a convolutional neural network (CNN) integrates image-derived features with clinical data such as patient demographics, symptoms, and medical history. This CNN-based multimodal fusion approach improves the model’s ability to capture spatial relationships and enhances classification performance. Experimental evaluations demonstrate that the proposed framework achieves state-of-the-art results across multiple evaluation metrics, including accuracy, sensitivity, and specificity. The interpretable disease probability maps highlight affected skin regions, enhancing model transparency and clinical usability. This approach demonstrates the potential of combining wearable sensor technology with deep learning for efficient, scalable, and explainable skin disease detection, laying the foundation for real-time clinical applications.

Since skin disease is one of the most common human diseases, intelligent systems for classification of skin diseases have become a new line of research in deep learning, which is of great significance for both doctors and patients. Some skin-disease datasets have already been published, such as the SD-198 dataset, which contains 6584 clinical skin-disease images of 198 categories. However, because of the diversity of clinical dermatology, previous works have showed that the performance of deep visual features is not as good as or even worse than hand-crafted features for skin disease classification. In this paper, we propose an SD-198-P dataset, which includes additional high-level position information in the SD-198 dataset to guide the generation of better deep visual features. Our experiment shows that, after adding the position information, the performance of deep visual features is better than that of hand-crafted features. To the best of our knowledge, our method outperforms the current state-of-the-art clinical skin disease classification methods.

Dermatological disorders are prevalent all over the world, and the rate affects people of all ages. The ability to diagnose skin diseases is important, especially when the disease is diagnosed early enough. In this work, we present a new deep learning model for skin disease classification that involves various methods of data enhancement and preparation to improve the quality of the images used in the analysis. Our data set was tested to compare the performance of competitive deep learning architectures such as ResNet50, VGG16, Inception V3, and EfficientNet. The proposed method for this work got an accuracy of 93% from a test data of 5000 images and is more efficient than several existing skin disease detection frameworks. We have observed high accuracy in our proposed skin disease prediction model using deep learning techniques.

Skin diseases affect 30-70% of the world population, and globally, skin cancer rates are continuously increasing. In this respect, prevention programs and early detection of skin diseases are of particular importance. To screen sewer workers for skin diseases with regard to their work-related risk. Employees of the municipal utilities in Munich (Münchner Stadtentwässerung) underwent awhole-body examination of the skin, conducted by two dermatologists. In addition, all employees completed apaper-based questionnaire on risk behavior and preventive measures. We examined 81employees (79men, 2women, mean age 45.7 ± 9.5years). Skin lesions in need of treatment were found in 30.9% (n = 25): the most frequent diagnosis was mycosis pedis (16.1%). In addition, one employee was diagnosed with basal cell carcinoma and two with actinic keratoses. According to the questionnaire, 43.5% of the employees had undergone aphysician-led skin cancer screening in the past, whereas sun-protection practices were rarely applied. According to our findings, employee skin cancer screening seems to be beneficial for the detection of work-related skin diseases and is associated with a high participation rate. Furthermore, the study suggests that sewer workers have ahigh rate of mycosis pedis, possibly awork-related effect.

Citrus fruit crops are among the world’s most important agricultural products, but pests and diseases impact their cultivation, resulting in yield and quality losses. Computer vision and machine learning have been widely used to detect and classify plant diseases over the last decade, allowing for early disease detection and improving agricultural production. This paper presented an automatic system for the early detection and classification of citrus plant diseases based on a deep learning (DL) model, which improved accuracy while decreasing computational complexity. The most recent transfer learning-based models were applied to the Citrus Plant Dataset to improve classification accuracy. Using transfer learning, this study successfully proposed a Convolutional Neural Network (CNN)-based pre-trained model (EfficientNetB3, ResNet50, MobiNetV2, and InceptionV3) for the identification and categorization of citrus plant diseases. To evaluate the architecture’s performance, this study discovered that transferring an EfficientNetb3 model resulted in the highest training, validating, and testing accuracies, which were 99.43%, 99.48%, and 99.58%, respectively. In identifying and categorizing citrus plant diseases, the proposed CNN model outperforms other cutting-edge CNN model architectures developed previously in the literature.

Skin disorders are a leading global health problem. The exact diagnosis of melanoma will help to improve patient outcomes. Methods of diagnosis, such as visual inspection by a dermatologist, are widely used for diagnosing various types of skin disease. However, they tend to suffer from experts' subjectivity. It is also time-consuming and limited by the availability of medical expertise. To overcome the problems, this research paper proposes an automated skin illness classification system using DL (Deep Learning) methods, which can assist in reliable and efficient diagnosis. The system suggested using a CNN to classify skin diseases from dermoscopic images. The HAM10000 dataset is an established, clinically verified dataset containing images of seven common pigmented skin lesion categories, used to train and test the model. Before training models, images are preprocessed using steps such as resizing, normalisation, colour normalisation, and noise reduction. A pre-trained CNN architecture has been used to extract visual features via TL (Transfer Learning), achieving good performance with limited medical data. The Adam optimiser trains the model with categorical cross-entropy loss. To evaluate robustness across all disease classes, accuracy, precision, recall, F1-score, and confusion matrix are used. The skin lesions are accurately classified, proving that the method works. The approach has great diagnostic potential for dermatologists. This can be expanded to online or mobile apps for early identification of skin disease and greater accessibility.

It is a great challenge for doctors even with the existence of emerging technology, to diagnose the symptoms of a skin disease. Many people are exposed to serious skin diseases that require them to go to hospitals and go through a number of different expensive medical examinations which takes up to days. The prosed work can solve the above problem to an extent , through the design of a program by MATLAB, a method based on vertical image segmentation, and is proposed to identify three various types of skin diseases, namely, Acne, Cancer and Psoriasis dermatitis. The work is a key to detect a range of symptoms in just a few seconds, making the diagnosis more intuitive and realistic. The aim of this project is the classification of different diseases based on images given as input. The project is based on MATLAB software platform. The images are collected from various publicly available databases Dermnet, DermWeb, etc. Firstly, the sample images of four skin diseases need to be preprocessed. Secondly, the vertical image is segmented and made corresponding geometric transformation. Based on this, three types of skin diseases’ features are extracted, and their correlated parameters of feature texture and pixels of lesion areas are collected through image segmentation. Finally, the symptoms of Acne, Cancer and Psoriasis dermatitis are identified by utilizing the support vector machine (SVM) method in order to improve identification accuracy and provide an interface to doctors.

An in-depth analysis of Convolutional Neural Network architectures with transfer learning for skin disease diagnosis