DEEP TRANSFER LEARNING FOR DERMOSCOPIC SKIN LESION CLASSIFICATION: BENCHMARKING XCEPTION, INCEPTIONRESNETV2, MOBILENETV3LARGE, DENSENET121, AND NASNETMOBILE

Automated Skin Lesion Classification Using Efficientnet-B4 Deep Learning Architecture On The Ham10000 Dataset

Timely diagnosis of skin cancer is a key to longer life and better results of the treatment process; nevertheless, exploring dermoscopic images manually by the dermatologists is both time-consuming and has a high risk of diagnostic variability owing to the visual similarity of various types of skin lesions. In recent times, the development of deep learning has produced automated systems of image analysis as potentially useful tools in helping diagnose a medical illness. The current research provides a framework of deep learning-based classification of multiclass skin lesions with the help of the EfficientNet-B4 and HAM10000 models. The data set has dermoscopic images of seven classes of diagnoses, such as melanoma, basal cell carcinoma, benign keratosis, dermatofibroma, vascular lesion, actinic keratoses, and melanocytic nevus. The image preprocessing and augmentation methods are used to enhance the generalization and training efficiency of models whereas transfer learning is used to fine-tune the EfficientNet-B4 network to the task of classification. The provided model is experimentally tested to present the overall accuracy of 86.9% which proves the effectiveness of deep learning methods in assisting in early skin cancer screening and computerized dermatological diagnosis.

A Novel Deep Learning Framework for MultiClass Skin Cancer Classification Using ModifiedStacked Capsule Network

Skin cancer is one of the deadliest kinds of cancer because of it’s due to its visible onset and the potential forrapid progression and spread. Oncologists employ several techniques, including imaging and biopsies, to determinewhether skin cancer is present, but these are labor-intensive and time-consuming. Developing an automated andaccurate framework is essential for early skin cancer detection, which greatly increases the probability of a successfultreatment and recovery. Therefore, to address the aforementioned problems, this study aim to propose a novel DeepLearning (DL)-based multi-class skin cancer classification (MC-SC2) model for automatically diagnosing skin cancersusing dermoscopic images. Initially, the dermoscopic images are preprocessed using a Gaussian Filter (GF) toeffectively remove noise. To address the class imbalance issue, we applied advanced augmentation techniques tooversample minority classes, ensuring a uniform class distribution and enhancing the model's ability to generalize. Toextract the complex and dominant features, we propose a novel DL-based model called BAM-EfficientNet (BottleneckAttention Module with EfficientNetB7). In BAM-EfficientNet, we replace each Squeeze-and-Excitation (SE) attentionmodule with a BAM in the traditional EfficientNetB7; this modification enables the network to concentrate on the mostrelevant regions in the images. The extracted features fed into the proposed Modified Stacked Capsule Network(MSCNet) to classify a skin lesion image as AKIEC, BCC, BKL, DF, MEL, NV, and VASC. In the proposed MSCNetemploys the Disperse Dynamic Routing (DDR) algorithm to improve capsule networks performance, and network'sinitial weights and biases are fine-tuned using Pelican Optimization Algorithm (POA) to further enhance performance.The HAM10000 dataset is used to assess the suggested model. The findings indicate that our approach beats currentmethods with an accuracy of 99.21% in classifying the seven different types of skin cancer, yielding substantialoutcomes. These results demonstrate the potential of the suggested model as a quick, precise, and useful tool for earlyskin cancer diagnosis, providing important assistance in diagnosing skin cancer for medical professionals.

Multi-class skin disease classification using transfer learning architectures

Dermatological conditions are among the most common health problems worldwide, where delayed identification may increase disease severity and complicate treatment procedures. However, restricted access to dermatological expertise and insufficient public awareness often contribute to delayed diagnosis. This study proposes a multi-class skin disease classification approach using deep learning and transfer learning architectures based on digital skin images. The dataset, obtained from the babaruzair/kaggle-skin-disease repository, consists of 1,157 images categorized into eight skin disease classes. Image preprocessing techniques, including resizing, normalization, and data augmentation, were applied to improve data quality and model generalization. Three models were evaluated in this study, namely a baseline Convolutional Neural Network (CNN), MobileNetV2, and EfficientNetB0. Both transfer learning models utilized ImageNet pre-trained weights, followed by customized classification layers and fine-tuning of selected upper layers. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results show that the baseline CNN achieved an accuracy of 52.36%, while MobileNetV2 and EfficientNetB0 achieved accuracies of 88.84% and 95.28%, respectively. The findings demonstrate that transfer learning architectures significantly outperform conventional CNN models for limited medical image datasets, with EfficientNetB0 providing the best classification performance. These results indicate the potential of deep learning-based approaches to support early skin disease diagnosis and assist clinical decision-making

Skin Disease Detection Using Deep Learning

Early and accurate diagnosis of skin diseases is essential for effective treatment and improved patient outcomes. This paper presents SkinScan AI, a deep learning-based framework for automated skin disease detection and classification from dermoscopic images using the HAM10000 benchmark dataset. The proposed DenseNet121 model classifies skin lesions into seven clinically significant categories: Actinic Keratoses (akiec), Basal Cell Carcinoma (bcc), Benign Keratosis-like Lesions (bkl), Dermatofibroma (df), Melanoma (mel), Melanocytic Nevi (nv), and Vascular Lesions (vasc). To address dataset imbalance, the framework incorporates MixUp augmentation, focal loss with label smoothing, minority-class weighting, and oversampling. A two-stage fine-tuning strategy with Test-Time Augmentation (TTA) improves model generalization and prediction robustness. Comparative evaluation with a custom CNN baseline and EfficientNetB3 demonstrates that DenseNet121 achieves the best performance, obtaining 81.82% TTA accuracy, a weighted F1-score of 0.8096, and an AUC of 0.9441. Grad-CAM provides visual explanations by highlighting lesion-relevant regions, improving model interpretability and increasing user confidence in the prediction process. The trained model is deployed as a Flask-based web application with secure authentication, prediction history, severity assessment, medication guidance, doctor referral recommendations, and downloadable PDF reports. Experimental results demonstrate that the proposed framework effectively handles class imbalance while providing accurate, interpretable, and practical decision support for computer-aided skin disease diagnosis. The system offers a scalable and user-friendly solution that can assist healthcare professionals and improve access to reliable preliminary skin disease screening.

Deep Learning-Based Automated Skin Cancer Detection Using Dermoscopic Images

Vision Transformer Outperforms CNN Architectures in Binary Skin Lesion Classification: An Eight-Model Controlled Deep Learning Study

Skin cancer is one of the life-threatening malignancies in the world, timely detection of which is directly proportional to the survival of patients. Traditional dermoscopic diagnosis suffers inter-observer variability, lack of specialists and is not scalable in resource limited healthcare environments. The end-to-end hierarchical feature learning provided by deep learning is a transformative solution to the learned dermoscopic image corpora. The paper empirically comparatively examines eight binary skin lesion classifiers benign versus malignant of a dataset of 2,637 training images, and 661 held out test images. The assessed architectures are located on a wide design range a custom CNN trained using fresh data, two ResNet18 transfer learning pipelines, DenseNet121, MobileNetV3-Large, ViT-Small/16 (ImageNet-21K), ConvNeXt-Tiny (ImageNet-12K) and EfficientNetV2-S (ImageNet-21K). All the models are trained with the same conditions involving stratified splitting, Weighted Random Sampler, two-stage fine tuning with discriminative learning rates, Automatic Mixed Precision, and early stopping. It is evaluated using six metrics accuracy, per-class precision, recall, F1-score, ROC-AUC, and PR-AUC. The highest test accuracy (91.53) and macro-F1 (0.907) is attained with EfficientNetV2-S. ViT-Small/16 has the best ROC-AUC (0.9723) and PR-AUC (0.9699), which proves the effectiveness of Vision Transformer in threshold-free probabilistic discrimination the clinically decisive measure in screening applications. The three contemporary timm-based models have consistently reached ROC-AUC 0.95 and above, but the legacy CNN models are at 0.56 even though the legacy CNN models are at competitive accuracy of 89-90%. MobileNetV3-Large yields a false negative rate of 61 (20% miss rate), which highlights the clinical risk of aggressive model compression. The findings simplify the selection of the model in clinical studies in implementing dermoscopy, suggesting that ViT-Small/16 should be used as a probabilistic-ranked malignancy screening model, and EfficientNetV2-S should be used as a fixed threshold binary triage model in a telemedicine system.