Search

Herein, a new paradigm based on deep learning was proposed that allows the extraction of fine-grained differences between skin lesions in pixel units for high accuracy classification of skin lesions. As basic feature information for a dermoscopic image of a skin region, 50 different features were extracted based on the edge, color, and texture features of the skin lesion image. For the edge features, a line-segment-type analysis algorithm was used, wherein the visual information of a dermoscopic image was precisely analyzed in terms of the units of pixels and was transformed into a structured pattern. Regarding the color features of skin lesions, the dermoscopic image was transformed into multiple color models, and the features were acquired by analyzing histograms showing information regarding the distribution of pixel intensities. Subsequently, texture features were extracted by applying the well-known Law’s texture energy measure algorithm. Feature data (50 × 256) generated via the feature extraction process above were used to classify skin lesions via a one-dimensional (1D) convolution layer-based classification model. Because the architecture of the designed model comprises parallel 1D convolution layers, fine-grained features of the dermoscopic image can be identified using different parameters. To evaluate the performance of the proposed method, datasets from the 2017 and 2018 International Skin Imaging Collaboration were used. A comparison of results yielded by well-known classification models and other models reported in the literature show the superiority of the proposed model. Additionally, the proposed method achieves an accuracy exceeding 88%.

Melanoma is considered one of the most lethal skin cancers. However, skin lesion classification based on deep learning diagnostic techniques is a challenging task owing to the insufficiency of labeled skin lesion images and intraclass-imbalanced datasets. It is thus necessary to utilize data augmentation methods based on generative adversarial networks (GANs) to assist skin lesion classification and help dermatologists reach more accurate diagnostic decisions. Moreover, insufficient samples can cause a low classification accuracy in a model by using deep learning in medical diagnosis and reduce the accuracy of skin lesion classification. To solve the above problems, this paper proposes a new skin lesion image classification framework based on a skin lesion augmentation style-based GAN (SLA-StyleGAN) according to the basic architecture of style-based GANs and DenseNet201. The proposed framework redesigns the structure of style control and noise input in the original generator and reconstructs the discriminator to adjust the generator to efficiently synthesize high-quality skin lesion images. We introduce a new loss function that reduces the intraclass sample distance and expands the sample distance between different classes, which can improve the balanced multiclass accuracy (BMA). The experimental results show that our classification framework performs well on the ISIC2019 dataset, and the BMA reaches 93.64%. The proposed method improves the accuracy of skin lesion image classification, assists dermatologists in determining and diagnosing different types of skin lesions, and analyzes skin lesions at different stages as well as those that are difficult to distinguish.

Examining and predicting skin cancer from skin lesion images is challenging due to the complexity of the images. Early detection and treatment of skin lesion disease can prevent mortality as it can be curable. Computer-aided diagnosis (CAD) provides a second opinion for dermatologists as they can classify the type of skin lesion with high accuracy due to their ability to show various clinical identification features locally and globally. Convolutional neural networks (CNNs) have significantly improved the performance of CAD systems for medical image segmentation and classifications. However, tuning CNNs are challenging since the search space of all possible hyperparameter configurations is substantially vast. In this paper, we adopt a genetic algorithm to automatically configure a CNN model for an accurate, reliable, and robust automated skin lesion classification for early skin lesion diagnosis. The optimized CNN model uses four public datasets to train and be able to detect abnormalities based on skin lesion features in different orientations. The model achieves the best scores for each of the DICE coefficients, precision measure, and F-score. These scores compare better than other existing methods. Considering the success of this optimized model, it could be a valuable method to implement in clinical settings.

Skin cancer (SC) is one of the most prevalent cancers worldwide. Clinical evaluation of skin lesions is necessary to assess the characteristics of the disease; however, it is limited by long timelines and variety in interpretation. As early and accurate diagnosis of SC is crucial to increase patient survival rates, machine-learning (ML) and deep-learning (DL) approaches have been developed to overcome these issues and support dermatologists. We present a systematic literature review of recent research on the use of machine learning to classify skin lesions with the aim of providing a solid starting point for researchers beginning to work in this area. A search was conducted in several electronic databases by applying inclusion/exclusion filters and for this review, only those documents that clearly and completely described the procedures performed and reported the results obtained were selected. Sixty-eight articles were selected, of which the majority use DL approaches, in particular convolutional neural networks (CNN), while a smaller portion rely on ML techniques or hybrid ML/DL approaches for skin cancer detection and classification. Many ML and DL methods show high performance as classifiers of skin lesions. The promising results obtained to date bode well for the not-too-distant inclusion of these techniques in clinical practice.

This study mainly focuses on pre-processing the HAM10000 and BCN20000 skin lesion datasets to select important features that will drive for proper skin cancer classification. In this work, three feature fusion strategies have been proposed by utilizing three pre-trained Convolutional Neural Network (CNN) models, namely VGG16, EfficientNet B0, and ResNet50 to select the important features based on the weights of the features and are coined as Adaptive Weighted Feature Set (AWFS). Then, two other strategies, Model-based Optimized Weighted Feature Set (MOWFS) and Feature-based Optimized Weighted Feature Set (FOWFS), are proposed by optimally and adaptively choosing the weights using a meta-heuristic artificial jellyfish (AJS) algorithm. The MOWFS-AJS is a model-specific approach whereas the FOWFS-AJS is a feature-specific approach for optimizing the weights chosen for obtaining optimal feature sets. The performances of those three proposed feature selection strategies are evaluated using Decision Tree (DT), Naïve Bayesian (NB), Multi-Layer Perceptron (MLP), and Support Vector Machine (SVM) classifiers and the performance are measured through accuracy, precision, sensitivity, and F1-score. Additionally, the area under the receiver operating characteristics curves (AUC-ROC) is plotted and it is observed that FOWFS-AJS shows the best accuracy performance based on the SVM with 94.05% and 94.90%, respectively, for HAM 10000 and BCN 20000 datasets. Finally, the experimental results are also analyzed using a non-parametric Friedman statistical test and the computational times are recorded; the results show that, out of those three proposed feature selection strategies, the FOWFS-AJS performs very well because its quick converging nature is inculcated with the help of AJS.

International audience; We present a study on the fusion of pixel data and patient metadata (age, gender, and body location) for improving the classification of skin lesion images. The experiments have been conducted with the ISIC 2019 skin lesion classification challenge data set. Taking two plain convolutional neural networks (CNNs) as a baseline, metadata are merged using either non-neural machine learning methods (tree-based and support vector machines) or shallow neural networks. Results show that shallow neural networks outperform other approaches in all overall evaluation measures. However, despite the increase in the classification accuracy (up to +19.1%), interestingly, the average per-class sensitivity decreases in three out of four cases for CNNs, thus suggesting that using metadata penalizes the prediction accuracy for lower represented classes. A study on the patient metadata shows that age is the most useful metadatum as a decision criterion, followed by body location and gender.

The growing incidence of skin cancer makes computer-aided diagnosis tools for this group of diseases increasingly important. The use of ultrasound has the potential to complement information from optical dermoscopy. The current work presents a fully automatic classification framework utilizing fully-automated (FA) segmentation and compares it with classification using two semi-automated (SA) segmentation methods. Ultrasound recordings were taken from a total of 310 lesions (70 melanoma, 130 basal cell carcinoma and 110 benign nevi). A support vector machine (SVM) model was trained on 62 features, with ten-fold cross-validation. Six classification tasks were considered, namely all the possible permutations of one class versus one or two remaining classes. The receiver operating characteristic (ROC) area under the curve (AUC) as well as the accuracy (ACC) were measured. The best classification was obtained for the classification of nevi from cancerous lesions (melanoma, basal cell carcinoma), with AUCs of over 90% and ACCs of over 85% obtained with all segmentation methods. Previous works have either not implemented FA ultrasound-based skin cancer classification (making diagnosis more lengthy and operator-dependent), or are unclear in their classification results. Furthermore, the current work is the first to assess the effect of implementing FA instead of SA classification, with FA classification never degrading performance (in terms of AUC or ACC) by more than 5%.