A Survey on Deep Learning Techniques for Skin Lesion Classification

Skin lesion classification has recently attracted significant attention. Regularly, physicians take much time to analyze the skin lesions because of the high similarity between these skin lesions. An automated classification system using deep learning can assist physicians in detecting the skin lesion type and enhance the patient’s health. The skin lesion classification has become a hot research area with the evolution of deep learning architecture. In this study, we propose a novel method using a new segmentation approach and wide-ShuffleNet for skin lesion classification. First, we calculate the entropy-based weighting and first-order cumulative moment (EW-FCM) of the skin image. These values are used to separate the lesion from the background. Then, we input the segmentation result into a new deep learning structure wide-ShuffleNet and determine the skin lesion type. We evaluated the proposed method on two large datasets: HAM10000 and ISIC2019. Based on our numerical results, EW-FCM and wide-ShuffleNet achieve more accuracy than state-of-the-art approaches. Additionally, the proposed method is superior lightweight and suitable with a small system like a mobile healthcare system.

According to Skin Cancer Foundation, skin cancer is by far the most common type of cancer in the United States and worldwide. Early diagnosis of skin cancer is critical because proper treatment at early stages can increase the chance of cure and recovery. However, visual inspection of dermoscopic images by dermatologists is error-prone and time-consuming. To ensure accurate diagnosis and faster treatment of skin cancer, deep learning techniques have been utilized to conduct automated skin lesion segmentation and classification. In this paper, after image processing, a Mask R-CNN model is built for lesion segmentation, where transfer learning is utilized by using the pre-trained weights from Microsoft COCO dataset. The weights of the trained Mask R-CNN model are saved and transferred to the next task - skin lesion classification, to train a Mask R-CNN model for classification. Our experiments are conducted on the benchmark datasets from the International Skin Imaging Collaboration 2018 (ISIC 2018) and evaluated by the same metrics used in ISIC 2018. The lesion boundary segmentation and lesion classification have achieved an accuracy of 96% and a balanced multiclass accuracy of 80%, respectively.

<span lang="EN-US">One type of skin cancer that is considered a malignant tumor is melanoma. Such a dangerous disease can cause a lot of death in the world. The early detection of skin lesions becomes an important task in the diagnosis of skin cancer. Recently, a machine learning paradigm emerged known as deep learning (DL) utilized for skin lesions classification. However, in some previous studies by using seven class images diagnostic of skin lesions classification based on a single DL approach with CNNs architecture does not produce a satisfying performance. The DL approach allows the development of a medical image analysis system for improving performance, such as the deep convolutional neural networks (DCNNs) method. In this study, we propose an ensemble learning approach that combines three DCNNs architectures such as Inception V3, Inception ResNet V2 and DenseNet 201 for improving the performance in terms of accuracy, sensitivity, specificity, precision, and F1-score. Seven classes of dermoscopy image categories of skin lesions are utilized with 10015 dermoscopy images from well-known the HAM10000 dataset. The proposed model produces good classification performance with 97.23% accuracy, 90.12% sensitivity, 97.73% specificity, 82.01% precision, and 85.01% F1-Score. This method gives promising results in classifying skin lesions for cancer diagnosis.</span>

Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare

e22018 Background: The prevalence of skin cancer is increasing worldwide. According to World Health Organization (WHO),there is one in every three cancers diagnosed in US is a skin cancer. Traditional ways for skin cancer diagnosis have shown many limitations: inadequate accuracy, consume much time, and effort. In order to assist dermatologists for earlier and accurate diagnosis, we propose to develop a computer aided diagnosis systems for automatic classification of skin lesions. Deep learning architectures are used in this area based on a new convolutional neural network that can classify skin lesions with improved accuracy. Methods: A public dataset of skin lesions HAM10000 ("Human Against Machine with 10000 training images") is used for training and testing. For the validation of our work, a private dataset is collected from a dermatology office in Besançon (France). This dataset contains 45 different dermatoscopic images of skin lesions (Basal cell carcinoma, squamous cell carcinoma and Actinic keratosis) with their histology results. In this research, a three-phase approach was proposed and implemented: Phase one is preprocessing the data; by amputate missing values using the mean filling method. The dermoscopy images in the dataset were downscaled to 224X224 pixels. Then, data augmentation was applied to solve the imbalanced data problem. Finally, the ten-fold cross-validation method was applied to compare the performance of three CNN architectures used in literature: DenseNet 201, ResNet 152, and VGGNet with our proposed architecture. Results: Results obtained with our model show the highest classification accuracy 0.95, a sensitivity of 0, 96, a specificity of 0.94, and outperforms other algorithms in classifying these skin lesions. Conclusions: Our research improves the performance of computer aided diagnosis systems for skin lesions by giving an accurate classification. The use of this system helps dermatologists to make accurate classification with lower time, cost, and effort. Our future work will focus on generalizing the domain by developing a model that can classify various lesions using various types of data (dermoscopic images, histological images, clinical data, sensors data...etc) using the advanced techniques in literature of transfer learning and adaptors models.

In dermatology, accurate classification and segmentation of skin lesions remain important challenges due to variations in lesion appearance, low contrast in images, and overlapping features across disease types. Various traditional models pose some major difficulties in simultaneously capturing fine-grained local features and global environmental dependencies. Hence, this paper proposes a novel model that integrates a Residual Attention DeepLabV3 + Network for the segmentation, and a dual attention conformer for the classification, employing deep learning approaches to enhance both segmentation and classification performance of skin lesions. Publicly available skin disease image datasets are employed, with the pre-processing steps including Image rescaling and normalization, Histogram equalization, Gaussian blurring, edge detection, noise remover, and Contrast Limited Adaptive Histogram Equalization. To evaluate the performance of the model, the dataset is split using the holdout method, with a ratio of 80:10:10 for the training, testing, and validation phases. Based on the labeled ISIC dermatology image dataset, the simulation results show the excellent performance of the proposed model with 99.18%, 99.06%, and 98.92% accuracy, precision and recall. Overall, the proposed model achieves superior results in skin lesion classification and segmentation and offers promising potential for integration into medical diagnostic systems.

The success of deep learning in skin lesion classification mainly depends on the ultra-deep neural network and the significantly large training data set. Deep learning training is usually time-consuming, and large datasets with labels are hard to obtain, especially skin lesion images. Although pre-training and data augmentation can alleviate these issues, there are still some problems: (1) the data domain is not consistent, resulting in the slow convergence; and (2) low robustness to confusing skin lesions. To solve these problems, we propose an efficient structural pseudoinverse learning-based hierarchical representation learning method. Preliminary feature extraction, shallow network feature extraction and deep learning feature extraction are carried out respectively before the classification of skin lesion images. Gabor filter and pre-trained deep convolutional neural network are used for preliminary feature extraction. The structural pseudoinverse learning (S-PIL) algorithm is used to extract the shallow features. Then, S-PIL preliminarily identifies the skin lesion images that are difficult to be classified to form a new training set for deep learning feature extraction. Through the hierarchical representation learning, we analyze the features of skin lesion images layer by layer to improve the final classification. Our method not only avoid the slow convergence caused by inconsistency of data domain but also enhances the training of confusing examples. Without using additional data, our approach outperforms existing methods in the ISIC 2017 and ISIC 2018 datasets.

Skin cancer is the most commonly diagnosed cancer worldwide. It is estimated that there are over 5 million cases of skin cancer are diagnosed in the United States every year. Although less than 5% of all diagnosed skin cancers are melanoma it accounts for over 70% of skin cancer-related deaths. In the past decade, the number of melanoma cancer cases has increased by 53%. Recently, there has been significant work on segmentation and classification of skin lesions via deep learning. However, there is limited work on identifying attributes and clinically-meaningful visual skin lesion patterns from dermoscopic images. In this work, we propose to use conditional GANs for skin lesion segmentation and attribute detection and use these attributes to improve skin lesion classification. The proposed conditional GAN framework can generate segmentation and attribute masks from RGB dermoscopic images. The adversarial-image-to-image translation style architecture forces the generator to learn both local and global features. The Markovian discriminator classifies pairs of image and segmentation labels as being real or fake. Unlike previous approaches, such an architecture not only learns the mapping from dermoscopic images image to segmentation and attribute masks but also learns an optimal loss function to train such a mapping. We demonstrate that the such an approach significantly improves the Jaccard index for segmentation (with a 0.65 threshold) up to 0.893. Fusing the lesion attributes for classification of lesions yields a higher accuracy compared to those without predicted attributes.

BackgroundSkin cancer is one of the life threating diseases in the world. So, millions of lives can be saved by early detection of skin cancer. In addition, automating the computer‐aided system of skin lesion detection and classification (SLDC) will assist the medical practitioners to ensure more efficacious treatment of skin lesion disease.Material and MethodIn this article, a hybrid preprocessing‐based transfer learning model for SLDC is proposed, which is named as SLDCNet. Initially, the hybrid Gaussian filter (HGF) with connected component label (CCL) based fast march inpainting procedure is used for hair removal and denoising of skin lesions. Next, full resolution convolutional networks (FrCN) based segmentation method is adapted for detecting the cancer region. Then, feature extraction is performed using deep residual learning and finally, transfer learning mechanism is applied for classification of eight skin lesions.ResultsThe extensive simulation results shows that proposed SLDCNet resulted in a classification accuracy of 99.92%, sensitivity of 99%, and specificity of 99.36%, respectively.ConclusionFrom the obtained results, it is proven that proposed SLDCNet provides better performance as compared to state‐of‐art SLDC approaches, and even the standard ISIC‐2019 public challenge.

Pigmented skin lesions are common spots or growths on the skin that originate from melanocyte cells. Skin cancer occurs as a result of the uncontrolled division of melanocyte cells. Skin cancer is common worldwide and its incidence has been increasing. Timely and accurate diagnosis of skin cancer is important in reducing deaths. Skin cancer cases are diagnosed by expert dermatologists, but the number of experts is insufficient for the population. Dermoscopy is one of the most commonly used methods for imaging skin lesions. Sometimes misdiagnosis can occur in the interpretation of dermoscopic images by human experts. Computer-aided systems help to make accurate and objective decisions in the diagnosis of skin lesions. Convolutional neural network(CNN) is a deep learning technique commonly used in the field of computer vision and is also widely used in medical image analysis In this study, a CNN model was proposed to classify seven different skin lesions in the HAM10000 dataset. The model provided a classification accuracy of 91.51%. The performance of the model was compared with similar studies in the literature and it was found that it showed higher success than most studies. The model was connected to a web application and evaluated in two phases by seven expert dermatologists. In the first phase, it was concluded that the model could diagnose skin lesions with 90.28% accuracy in practice. In the second phase, the model corrected the experts' misdiagnoses by 11.14%.

Due to the rising occurrence of skin cancer and inadequate clinical expertise, it is needed to design Artificial Intelligence (AI) based tools to diagnose skin cancer at an earlier stage. Since massive skin lesion datasets have existed in the literature, the AI-based Deep Learning (DL) models find useful to differentiate benign and malignant skin lesions using dermoscopic images. This study develops an Automated Seeded Growing Segmentation with Optimal EfficientNet (ARGS-OEN) technique for skin lesion segmentation and classification. The proposed ASRGS-OEN technique involves the design of an optimal EfficientNet model in which the hyper-parameter tuning process takes place using the Flower Pollination Algorithm (FPA). In addition, Multiwheel Attention Memory Network Encoder (MWAMNE) based classification technique is employed for identifying the appropriate class labels of the dermoscopic images. A comprehensive simulation analysis of the ASRGS-OEN technique takes place and the results are inspected under several dimensions. The simulation results highlighted the supremacy of the ASRGS-OEN technique on the applied dermoscopic images compared to the recently developed approaches.

This study investigates the application of the Xception architecture for accurate classification of skin lesions, focusing on the early detection of melanoma and other malignant skin conditions. Utilizing deep learning techniques, the research aims to enhance the precision and efficiency of skin lesions diagnosis. The study utilizes the TensorFlow framework and the HAM10000 dataset, comprising a vast collection of benign and malignant skin lesion images, for training and evaluating the Xception model. Preprocessing steps, including data splitting, augmentation, and image resizing, are applied to the dataset. The Xception architecture, a deep convolutional neural network, serves as the foundational model, supplemented with customized classification layers for specialized features and predictions. The model's performance is evaluated using diverse metrics. The experimental outcomes reveal the Xception architecture's potential in accurately classifying skin lesions. Moreover, the study underscores the significance of extensive and diverse datasets, as well as rigorous clinical validation, in the development of deep learning models for skin cancer detection. The findings contribute to the advancement of early melanoma detection, thereby improving patient outcomes and alleviating the burden of the disease.

Accurate and timely classification of skin lesions is critical for early cancer detection, yet current deep learning approaches suffer from high computational costs, limited interpretability, and poor transparency for clinical deployment. This study presents HCHS-Net, a lightweight and interpretable multimodal framework for six-class skin lesion classification on the PAD-UFES-20 dataset. The proposed framework extracts a 116-dimensional visual feature vector through three complementary handcrafted modules: a Color Module employing multi-channel histogram analysis to capture chromatic diagnostic patterns, a Haralick Module deriving texture descriptors from the gray-level co-occurrence matrix (GLCM) that quantify surface characteristics correlated with malignancy, and a Shape Module encoding morphological properties via Hu moment invariants aligned with the clinical ABCD rule. The architectural design of HCHS-Net adopts a biomimetic approach by emulating the hierarchical information processing of the human visual system and the cognitive diagnostic workflows of expert dermatologists. Unlike conventional black-box deep learning models, this framework employs parallel processing branches that simulate the selective attention mechanisms of the human eye by focusing on biologically significant visual cues such as chromatic variance, textural entropy, and morphological asymmetry. These visual features are concatenated with a 12-dimensional clinical metadata vector encompassing patient demographics and lesion characteristics, yielding a compact 128-dimensional multimodal representation. Classification is performed through an ensemble of three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) with majority voting. HCHS-Net achieves 97.76% classification accuracy with only 0.25 M parameters, outperforming deep learning baselines, including VGG-16 (94.60%), ResNet-50 (94.80%), and EfficientNet-B2 (95.16%), which require 60-97× more parameters. The framework delivers an inference time of 0.11 ms per image, enabling real-time classification on standard CPUs without GPU acceleration. Ablation analysis confirms the complementary contribution of each feature module, with metadata integration providing a 2.53% accuracy gain. The model achieves perfect melanoma and nevus recall (100%) with 99.55% specificity, maintaining reliable discrimination at safety-critical diagnostic boundaries. Comprehensive benchmarking against 13 published methods demonstrates that domain-informed handcrafted features combined with clinical metadata can match or exceed deep learning fusion approaches while offering superior interpretability and computational efficiency for point-of-care deployment.

Not knowing the type of skin lesion or too much-delayed diagnosis can lead to chronic disease or skin cancer. In SkinAid, we propose an application that can not only assist the dermatologist in obtaining a preliminary analysis of detecting, classifying and monitoring the skin lesion but also creates awareness for the user to care for the skin. SkinAid classifies and provides information on several skin lesions. In this regard, the highly unbalanced and limited data leads the existing Deep Learning models to overfit or poorly generalize, resulting in re-duced performance. We explore Generative Adversarial Networks (GANs) to augment and enhance the dataset. Also, we trained a Deep Convolutional Neural Network (CNN) model for edge computing platforms that can automatically detect and classify skin lesions from the captured image of the user's skin. A single-board computer and a smartphone employed as edge platforms have been implemented in SkinAid. The SkinAid model detects and classifies 7 different skin lesions with an overall accuracy of 92.2%. A health worker or patient can capture the real-time skin lesion images using a smartphone app camera to obtain a preliminary analysis to diagnose the skin lesion in Internet-of-Medical-Things (IoMT) platform for remote monitoring by dermatologists.

In recent years, intelligent automation in the healthcare sector becomes more familiar due to the integration of artificial intelligence (AI) techniques. Intelligent healthcare systems assist in making better decisions, which further enable the patient to provide improved medical services. At the same time, skin lesion is a deadly disease that affects people of all age groups. Skin lesion segmentation and classification play a vital part in the earlier and precise skin cancer diagnosis by intelligent systems. However, the automated diagnosis of skin lesions in dermoscopic images is challenging because of the problems such as artifacts (hair, gel bubble, ruler marker), blurry boundary, poor contrast, and variable sizes and shapes of the lesion images. This study develops intelligent multilevel thresholding with deep learning (IMLT-DL) based skin lesion segmentation and classification model using dermoscopic images to address these problems. Primarily, the presented IMLT-DL model incorporates the Top hat filtering and inpainting technique for the pre-processing of the dermoscopic images. In addition, the Mayfly Optimization (MFO) with multilevel Kapur’s thresholding-based segmentation process is involved in determining the infected regions. Besides, an Inception v3 based feature extractor is applied to derive a valuable set of feature vectors. Finally, the classification process is carried out using a gradient boosting tree (GBT) model. The presented model’s performance takes place against the International Skin Imaging Collaboration (ISIC) dataset, and the experimental outcomes are inspected in different evaluation measures. The resultant experimental values ensure that the proposed IMLT-DL model outperforms the existing methods by achieving higher accuracy of 0.992.