Search

Skin cancer is a common malignant tumor causing tens of thousands of deaths each year, making early detection essential for better treatment outcomes. However, the similar visual characteristics of skin lesions make it challenging to accurately differentiate between lesion types. With advancements in deep learning, researchers have increasingly turned to convolutional neural networks for skin cancer detection and classification. In this article, an improved skin cancer classification model M‐Net is proposed, and the enhanced gray wolf optimization algorithm is combined to improve the classification performance. The gray wolf optimization algorithm guides the wolf pack to prey through a multileader structure and gradually converges through the encirclement and pursuit mechanism, so as to perform a more detailed search in the later stage. To further improve the performance of the gray wolf optimization, this study introduces the simulated annealing algorithm to avoid falling into the local optimal state and expands the search range by improving the search mechanism, thus enhancing the global optimization ability of the algorithm. The M‐Net model significantly improves the accuracy of classification by extracting features of skin lesions and optimizing parameters with the enhanced gray wolf optimization algorithm. The experimental results based on the ISIC 2018 dataset show that compared with the baseline model, the feature extraction network of the model has achieved a significant improvement in accuracy. The classification performance of M‐Net is excellent in multiple indicators, with accuracy, precision, recall, and F1 score reaching 0.891, 0.857, 0.895, and 0.872, respectively. In addition, the modular design of M‐Net enables it to flexibly adjust feature extraction and classification modules to adapt to different classification tasks, showing great scalability and applicability. In general, the model proposed in this article performs well in the classification of skin lesions, has broad clinical application prospects, and provides strong support for promoting the diagnosis of skin diseases. [ABSTRACT FROM AUTHOR]

Background: Cutaneous melanoma is the most aggressive form of skin cancer, responsible for most skin cancer-related deaths. Recent advances in artificial intelligence, jointly with the availability of public dermoscopy image datasets, have allowed to assist dermatologists in melanoma identification. While image feature extraction holds potential for melanoma detection, it often leads to high-dimensional data. Furthermore, most image datasets present the class imbalance problem, where a few classes have numerous samples, whereas others are under-represented. Methods: In this paper, we propose to combine ensemble feature selection (FS) methods and data augmentation with the conditional tabular generative adversarial networks (CTGAN) to enhance melanoma identification in imbalanced datasets. We employed dermoscopy images from two public datasets, PH2 and Derm7pt, which contain melanoma and not-melanoma lesions. To capture intrinsic information from skin lesions, we conduct two feature extraction (FE) approaches, including handcrafted and embedding features. For the former, color, geometric and first-, second-, and higher-order texture features were extracted, whereas for the latter, embeddings were obtained using ResNet-based models. To alleviate the high-dimensionality in the FE, ensemble FS with filter methods were used and evaluated. For data augmentation, we conducted a progressive analysis of the imbalance ratio (IR), related to the amount of synthetic samples created, and evaluated the impact on the predictive results. To gain interpretability on predictive models, we used SHAP, bootstrap resampling statistical tests and UMAP visualizations. Results: The combination of ensemble FS, CTGAN, and linear models achieved the best predictive results, achieving AUCROC values of 87% (with support vector machine and IR=0.9) and 76% (with LASSO and IR=1.0) for the PH2 and Derm7pt, respectively. We also identified that melanoma lesions were mainly characterized by features related to color, while not-melanoma lesions were characterized by texture features. Conclusions: Our results demonstrate the effectiveness of ensemble FS and synthetic data in the development of models that accurately identify melanoma. This research advances skin lesion analysis, contributing to both melanoma detection and the interpretation of main features for its identification. [ABSTRACT FROM AUTHOR]

Knowledge Distillation has shown promising results for classifying skin lesions in dermatology images. Traditional knowledge distillation typically involves the student model passively mimicking the teacher model's knowledge. We propose utilizing AdaBoost to enable the student to actively mine the teacher's learning representation for skin lesion classification. This paradigm allows the student to determine the "granularity" in mining the teacher's knowledge. As the student's learning process progresses, it can become challenging to pinpoint specific learning difficulties, especially with potential interference from the teacher. To address this issue, we introduce a variational difficulty mining strategy to reduce the impact of such interference. This strategy involves the distillation module capturing more nuanced classification difficulties by extracting information from the node's l th hops. By maximizing the mutual information between the teacher and student, we effectively filter out noise interference from these nuanced difficulties. Our proposed framework, Variational AdaBoost Knowledge Distillation (VAdaKD), allows the student to actively mine and leverage the teacher's knowledge for improved skin lesion classification. Our proposed method performs satisfactorily on three benchmark datasets: the Dermnet dataset, ISIC 2019 dataset, and HAM10000 dataset, respectively. Specifically, our method shows an improvement of 2–3% over the baseline on the Dermnet dataset and outperforms the best results of the other compared methods by 1%. Experimental results and visualization performance indicate that our proposed method effectively captures the learning difficulties and achieves better visualized t-distributed stochastic neighbor embedding classification results. Our code is available at https://github.com/25brilliant/VAdaKD. [ABSTRACT FROM AUTHOR]

Abstract Background Cutaneous melanoma is the most aggressive form of skin cancer, responsible for most skin cancer-related deaths. Recent advances in artificial intelligence, jointly with the availability of public dermoscopy image datasets, have allowed to assist dermatologists in melanoma identification. While image feature extraction holds potential for melanoma detection, it often leads to high-dimensional data. Furthermore, most image datasets present the class imbalance problem, where a few classes have numerous samples, whereas others are under-represented. Methods In this paper, we propose to combine ensemble feature selection (FS) methods and data augmentation with the conditional tabular generative adversarial networks (CTGAN) to enhance melanoma identification in imbalanced datasets. We employed dermoscopy images from two public datasets, PH2 and Derm7pt, which contain melanoma and not-melanoma lesions. To capture intrinsic information from skin lesions, we conduct two feature extraction (FE) approaches, including handcrafted and embedding features. For the former, color, geometric and first-, second-, and higher-order texture features were extracted, whereas for the latter, embeddings were obtained using ResNet-based models. To alleviate the high-dimensionality in the FE, ensemble FS with filter methods were used and evaluated. For data augmentation, we conducted a progressive analysis of the imbalance ratio (IR), related to the amount of synthetic samples created, and evaluated the impact on the predictive results. To gain interpretability on predictive models, we used SHAP, bootstrap resampling statistical tests and UMAP visualizations. Results The combination of ensemble FS, CTGAN, and linear models achieved the best predictive results, achieving AUCROC values of 87% (with support vector machine and IR=0.9) and 76% (with LASSO and IR=1.0) for the PH2 and Derm7pt, respectively. We also identified that melanoma lesions were mainly characterized by features related to color, while not-melanoma lesions were characterized by texture features. Conclusions Our results demonstrate the effectiveness of ensemble FS and synthetic data in the development of models that accurately identify melanoma. This research advances skin lesion analysis, contributing to both melanoma detection and the interpretation of main features for its identification.

Abstract Skin cancer stands as one of the foremost challenges in oncology, with its early detection being crucial for successful treatment outcomes. Traditional diagnostic methods depend on dermatologist expertise, creating a need for more reliable, automated tools. This study explores deep learning, particularly Convolutional Neural Networks (CNNs), to enhance the accuracy and efficiency of skin cancer diagnosis. Leveraging the HAM10000 dataset, a comprehensive collection of dermatoscopic images encompassing a diverse range of skin lesions, this study introduces a sophisticated CNN model tailored for the nuanced task of skin lesion classification. The model’s architecture is intricately designed with multiple convolutional, pooling, and dense layers, aimed at capturing the complex visual features of skin lesions. To address the challenge of class imbalance within the dataset, an innovative data augmentation strategy is employed, ensuring a balanced representation of each lesion category during training. Furthermore, this study introduces a CNN model with optimized layer configuration and data augmentation, significantly boosting diagnostic precision in skin cancer detection. The model’s learning process is optimized using the Adam optimizer, with parameters fine-tuned over 50 epochs and a batch size of 128 to enhance the model’s ability to discern subtle patterns in the image data. A Model Checkpoint callback ensures the preservation of the best model iteration for future use. The proposed model demonstrates an accuracy of 97.78% with a notable precision of 97.9%, recall of 97.9%, and an F2 score of 97.8%, underscoring its potential as a robust tool in the early detection and classification of skin cancer, thereby supporting clinical decision-making and contributing to improved patient outcomes in dermatology.

Abstract Skin cancer is a lethal disease, and its early detection plays a pivotal role in preventing its spread to other body organs and tissues. Artificial Intelligence (AI)-based automated methods can play a significant role in its early detection. This study presents an AI-based novel approach, termed 'DualAutoELM' for the effective identification of various types of skin cancers. The proposed method leverages a network of autoencoders, comprising two distinct autoencoders: the spatial autoencoder and the FFT (Fast Fourier Transform)-autoencoder. The spatial-autoencoder specializes in learning spatial features within input lesion images whereas the FFT-autoencoder learns to capture textural and distinguishing frequency patterns within transformed input skin lesion images through the reconstruction process. The use of attention modules at various levels within the encoder part of these autoencoders significantly improves their discriminative feature learning capabilities. An Extreme Learning Machine (ELM) with a single layer of feedforward is trained to classify skin malignancies using the characteristics that were recovered from the bottleneck layers of these autoencoders. The 'HAM10000' and 'ISIC-2017' are two publicly available datasets used to thoroughly assess the suggested approach. The experimental findings demonstrate the accuracy and robustness of the proposed technique, with AUC, precision, and accuracy values for the 'HAM10000' dataset being 0.98, 97.68% and 97.66%, and for the 'ISIC-2017' dataset being 0.95, 86.75% and 86.68%, respectively. This study highlights the possibility of the suggested approach for accurate detection of skin cancer.

Abstract Identification of pigmented skin lesions is necessary for the detection of severe diseases associated with the skin organ, notably malignancy. Accurate skin cancer diagnosis can be improved with the use of image detection approaches and computer classification skills. Therefore, this research work plans to perform skin lesion prediction and classification using a novel deep learning methodology. Initially, the data related to the skin lesion are gathered from the ISIC dataset. After collecting the images, the pre-processing is performed using hair removal and filtering hair removed images via median filtering. These pre-processed images undergo segmentation process accomplished using the U-Net method. Next, the features are extracted from these segmented images with the help of color features, and texture features by GLCM and RGB histogram features. These extracted features undergo the prediction phase that is accomplished using the MLSTM model, in which the parameter optimization is done by the nature inspired novel hybrid metaheuristic algorithm referred as SC-STBO algorithm with the consideration of accuracy maximization and RMSE minimization as the major fitness for the objective function. If the predicted output is returned as the presence of skin lesion, the same novel MLSTM model classifies the final skin lesion output into seven types, such as Vascular Lesions, Melanocytic Nevi, Melanoma, Dermatofibroma, Benign Keratosis-like Lesions, BCC, and Actinic Keratoses, respectively. Seven groups of skin diseases can be identified early thanks to the suggested effort, which can then be tested and properly handled by medical professionals. With an accuracy of 0.9931, the recommended methodology clearly outperforms traditional techniques. Similarly, the suggested methodology clearly beats the conventional methods, with a recall of 0.9825.

Skin cancer is a pressing global health issue, with high incidence and mortality rates. Convolutional neural network (CNN) models have been proven to be effective in improving performance in skin lesion image classification and reducing the medical burden. However, the inherent class imbalance in training data caused by the difficulty of collecting dermoscopy images leads to categorical overfitting, which still limits the effectiveness of these data‐driven models in recognizing few‐shot categories. To address this challenge, we propose a dynamic multi‐output convolutional neural network (DMO‐CNN) model that incorporates exit nodes into the standard CNN structure and includes feature refinement layers (FRLs) and an adaptive output scheduling (AOS) module. This model improves feature representation ability through multi‐scale sub‐feature maps and reduces the inter‐layer dependencies during backpropagation. The FRLs ensure efficient and low‐loss down‐sampling, while the AOS module utilizes a trainable layer selection mechanism to refocus the model's attention on few‐shot lesion categories. Additionally, a novel correction factor loss is introduced to supervise and promote AOS convergence. Our evaluation of the DMO‐CNN model on the HAM10000 dataset demonstrates its effectiveness in multi‐class skin lesion classification and its superior performance in recognizing few‐shot categories. Despite utilizing a very simple VGG structure as the sole backbone structure, DMO‐CNN achieved impressive performance of 0.885 in BACC and 0.983 in weighted AUC. These results are comparable to those of the ensemble model that won the ISIC 2018 challenge, highlighting the strong potential of DMO‐CNN in dealing with few‐shot skin lesion data. [ABSTRACT FROM AUTHOR]

Even though past research suggests that visual learning may benefit from conceptual knowledge, current interventions for medical image evaluation often focus on procedural knowledge, mainly by teaching classification algorithms. We compared the efficacy of pure procedural knowledge (three-point checklist for evaluating skin lesions) versus combined procedural plus conceptual knowledge (histological explanations for each of the three points). All students then trained their classification skills with a visual learning resource that included images of two types of pigmented skin lesions: benign nevi and malignant melanomas. Both treatments produced significant and long-lasting effects on diagnostic accuracy in transfer tasks. However, only students in the combined procedural plus conceptual knowledge condition significantly improved their diagnostic performance in classifying lesions they had seen before in the pre- and post-tests. Findings suggest that the provision of additional conceptual knowledge supported error correction mechanisms. [ABSTRACT FROM AUTHOR]

Automatic classification of dermoscopy images plays a crucial role in the early diagnosis and treatment of serious diseases like skin cancer. However, it poses several challenges, including similar appearance lesions, different types of skin structures, variations in lesion stages, insufficient or inaccurate data, and artifacts present in dermoscopy images. In skin lesion classification tasks, deep learning-based methods have recently demonstrated superior performance compared to traditional machine learning-based methods. In this study, a novel ensemble-based approach is designed for skin lesion classification by leveraging the diverse information captured by different architectures of ConvNeXt models which have been demonstrated to achieve comparable performance to most vision transformers by utilizing a CNN backbone. More specifically, firstly, different versions of pre-trained and fine-tuned ConvNeXt models, namely Tiny, Small, Base, and Large, were used for the classification of skin lesion images to analyze and compare classification performances on the publicly available ISIC 2019 dataset. Among the individual models, ConvNeXt-Large achieved the highest accuracy rate of 97.2%, making it the top-performing model. Then, all four ConvNeXt models were fused using confidence scores to improve classification accuracy. The ensemble approach achieved an overall classification accuracy of 97.7%, surpassing both the performance of individual models and state-of-the-art methods. Additionally, a sensitivity value of 84.2% and a specificity value of 97.9% were obtained. The findings of this study provide evidence that the proposed approach effectively and accurately classifies skin lesions from dermoscopy images. [ABSTRACT FROM AUTHOR]

Early diagnosis of malignant melanoma can cure up to 90% of patients. Thus, our goal is to improve a specialized, multi-strategic diagnostic system supporting dermatologists and, in the long run, general practitioners, ensuring objective, reliable, and user-independent results. This research was concerned with extending the idea of Micro-AI models, deep learning detectors selected for each feature instead of a single AI model used for the entire image. Two types of relationships were defined for the melanocytic strategies used: impact on diagnosis (direct, indirect, selective), as well as interaction between features. Only strong causal relationships, with a probability above 0.9, between the features of the lesion were identified. The indicated features with significant dependencies, such as the border of the change and the diversity of its structure, will be included in the deep learning detector to achieve better classification/detection. [ABSTRACT FROM AUTHOR]

Skin cancer stands as one of the foremost challenges in oncology, with its early detection being crucial for successful treatment outcomes. Traditional diagnostic methods depend on dermatologist expertise, creating a need for more reliable, automated tools. This study explores deep learning, particularly Convolutional Neural Networks (CNNs), to enhance the accuracy and efficiency of skin cancer diagnosis. Leveraging the HAM10000 dataset, a comprehensive collection of dermatoscopic images encompassing a diverse range of skin lesions, this study introduces a sophisticated CNN model tailored for the nuanced task of skin lesion classification. The model's architecture is intricately designed with multiple convolutional, pooling, and dense layers, aimed at capturing the complex visual features of skin lesions. To address the challenge of class imbalance within the dataset, an innovative data augmentation strategy is employed, ensuring a balanced representation of each lesion category during training. Furthermore, this study introduces a CNN model with optimized layer configuration and data augmentation, significantly boosting diagnostic precision in skin cancer detection. The model's learning process is optimized using the Adam optimizer, with parameters fine-tuned over 50 epochs and a batch size of 128 to enhance the model's ability to discern subtle patterns in the image data. A Model Checkpoint callback ensures the preservation of the best model iteration for future use. The proposed model demonstrates an accuracy of 97.78% with a notable precision of 97.9%, recall of 97.9%, and an F2 score of 97.8%, underscoring its potential as a robust tool in the early detection and classification of skin cancer, thereby supporting clinical decision-making and contributing to improved patient outcomes in dermatology. [ABSTRACT FROM AUTHOR]

This paper introduces a novel approach to enhance content-based image retrieval, validated on two benchmark datasets: ISIC-2017 and ISIC-2018. These datasets comprise skin lesion images that are crucial for innovations in skin cancer diagnosis and treatment. We advocate the use of pre-trained Vision Transformer (ViT), a relatively uncharted concept in the realm of image retrieval, particularly in medical scenarios. In contrast to the traditionally employed Convolutional Neural Networks (CNNs), our findings suggest that ViT offers a more comprehensive understanding of the image context, essential in medical imaging. We further incorporate a weighted multi-loss function, delving into various losses such as triplet loss, distillation loss, contrastive loss, and cross-entropy loss. Our exploration investigates the most resilient combination of these losses to create a robust multi-loss function, thus enhancing the robustness of the learned feature space and ameliorating the precision and recall in the retrieval process. Instead of using all the loss functions, the proposed multi-loss function utilizes the combination of only cross-entropy loss, triplet loss, and distillation loss and gains improvement of 6.52% and 3.45% for mean average precision over ISIC-2017 and ISIC-2018. Another innovation in our methodology is a two-branch network strategy, which concurrently boosts image retrieval and classification. Through our experiments, we underscore the effectiveness and the pitfalls of diverse loss configurations in image retrieval. Furthermore, our approach underlines the advantages of retrieval-based classification through majority voting rather than relying solely on the classification head, leading to enhanced prediction for melanoma - the most lethal type of skin cancer. Our results surpass existing state-of-the-art techniques on the ISIC-2017 and ISIC-2018 datasets by improving mean average precision by 1.01% and 4.36% respectively, emphasizing the efficacy and promise of Vision Transformers paired with our tailor-made weighted loss function, especially in medical contexts. The proposed approach's effectiveness is substantiated through thorough ablation studies and an array of quantitative and qualitative outcomes. To promote reproducibility and support forthcoming research, our source code will be accessible on GitHub. [ABSTRACT FROM AUTHOR]

When analyzing skin lesion image data using deep learning, the lack of a sufficient amount of effective training data poses a challenge. Although transfer learning can alleviate the problem of a small amount of data, the difference between the source data and the target data makes the tranfer learning missing some key knowledge. It is important to find the key knowledge neglected by transfer learning. This paper argues that this key knowledge is contained in challenging samples. We propose a novel method named as Limited Samples Network (LSNet) to search challenging samples and strengthen the learning of them. Specifically, LSNet utilizes patch-based structured input and employs pseudoinverse learning autoencoder to quickly obtain position-sensitive loss. Challenging samples can be obtained by searching for position-sensitive loss. Subsequently, challenging samples-augmented transfer learning is employed to enhance the classification performance of deep learning models on skin lesion datasets with limited samples. We carry comparison experiment with the existing state-of-the-art method. Experiments are carried out on the ISIC 2017, ISIC 2018 and ISIC 2019 skin lesion datasets. The results demonstrate that our training strategy significantly improves the vanilla transfer learning procedure for different types of pre-trained DCNNs. In particular, our method achieves state-of-the-art performance on different skin lesion datasets without using any extra training data. [ABSTRACT FROM AUTHOR]

We present a unified framework for solving the nonlinear Support Vector Machines (SVM) training problems. The framework is based on an objective function approximation so that the Problem becomes separable, with low computational cost root-finding methods to solve the resulting subproblems. Because of the diagonalization of the objective function in the first stage of the framework, we named the new SVM solver DiagSVM. To test the performance of the DiagSVM, we reported preliminary numerical experiments with benchmark datasets. From the results, we chose the best combination used in the framework to solve the Skin Lesion Classification (SLC) problem. Since melanoma (skin cancer) is the most dangerous and deadliest disease that affects the skin, the application of the DiagSVM can be integrated into several Computer-Aided Diagnosis (CAD) systems to help them detect skin cancer and significantly reduce both morbidity and mortality associated with this disease. Machine learning (ML) and deep learning (DL) based approaches have been widely used to develop robust skin lesion classification systems. For the SLC problem, three pre-trained convolutional neural networks (CNN), Xception, InceptionResNetV2 and DenseNet201, were employed as feature extractors and their dimension was reduced using Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA) and Independent Component Analysis (ICA). Finally, the samples were fed into two SVM solvers: DiagSVM and Libsvm. The experiment shows that using PCA, KPCA, or ICA, the SVM can perform better than without feature reduction. The classification performance of the proposed methodology is analyzed on the ISIC2017 and PH2 datasets. The benchmark and SLC results indicate a promising proposal for accuracy, specificity and sensitivity metrics. [ABSTRACT FROM AUTHOR]

Accurate detection of skin lesions through computer-aided diagnosis has emerged as a critical advancement in dermatology, addressing the inefficiencies and errors inherent in manual visual analysis. Despite the promise of automated diagnostic approaches, challenges such as image size variability, hair artifacts, color inconsistencies, ruler markers, low contrast, lesion dimension differences, and gel bubbles must be overcome. Researchers have made significant strides in binary classification problems, particularly in distinguishing melanocytic lesions from normal skin conditions. Leveraging the “MNIST HAM10000” dataset from the International Skin Image Collaboration, this study integrates Scale-Invariant Feature Transform (SIFT) features with a custom convolutional neural network model called LesionNet. The experimental results reveal the model's robustness, achieving an impressive accuracy of 99.28%. This high accuracy underscores the effectiveness of combining feature extraction techniques with advanced neural network models in enhancing the precision of skin lesion detection.

Abstract Knowledge Distillation has shown promising results for classifying skin lesions in dermatology images. Traditional knowledge distillation typically involves the student model passively mimicking the teacher model's knowledge. We propose utilizing AdaBoost to enable the student to actively mine the teacher's learning representation for skin lesion classification. This paradigm allows the student to determine the “granularity” in mining the teacher's knowledge. As the student's learning process progresses, it can become challenging to pinpoint specific learning difficulties, especially with potential interference from the teacher. To address this issue, we introduce a variational difficulty mining strategy to reduce the impact of such interference. This strategy involves the distillation module capturing more nuanced classification difficulties by extracting information from the node's $$l$$ l th hops. By maximizing the mutual information between the teacher and student, we effectively filter out noise interference from these nuanced difficulties. Our proposed framework, Variational AdaBoost Knowledge Distillation (VAdaKD), allows the student to actively mine and leverage the teacher's knowledge for improved skin lesion classification. Our proposed method performs satisfactorily on three benchmark datasets: the Dermnet dataset, ISIC 2019 dataset, and HAM10000 dataset, respectively. Specifically, our method shows an improvement of 2–3% over the baseline on the Dermnet dataset and outperforms the best results of the other compared methods by 1%. Experimental results and visualization performance indicate that our proposed method effectively captures the learning difficulties and achieves better visualized t-distributed stochastic neighbor embedding classification results. Our code is available at https://github.com/25brilliant/VAdaKD .

Skin lesion diagnosis in medical image analysis is still a difficult task. A frequent kind of cancer known as skin cancer affects people worldwide and can be fatal. As a result, early and accurate diagnosis is crucial for finding skin cancer patients. One of the most recent technologies for detecting skin cancer is dermatoscopy. For proper treatment of skin cancer, an early diagnosis is required. The early stages of skin lesions are identical, making manual diagnosis difficult. Therefore, creating computer-aided methods for classifying skin lesions will assist dermatologists in detecting skin lesions earlier and treating them more successfully. Current research indicates a significant potential for the classification of skin lesions using deep learning networks. However, issues including unbalanced datasets, poor contrast lesions, and the extraction of pointless or duplicate features still need to be resolved. This study aims to propose a transfer learning-based ensemble model for more accurate classification results. InceptionV3 and Xception are employed to build an ensemble model for classifying skin lesion images known as IncepX-Ensemble. A traditional data augmentation method was employed for the HAM10000 dataset to address the imbalanced data. This technique mitigates the class imbalance by incorporating data augmentation, enhancing model accuracy. At the experiment’s outset, we utilized the original imbalanced data, and subsequently, balanced data were employed for the proposed model. Training and testing accuracy was achieved at 86% on the imbalanced dataset. A balanced data augmentation dataset yielded 98% training and 98% test accuracy rates. We evaluated the output of the proposed model against outputs from various transfer learning models using both the original and balanced datasets.

Skin lesion classification is a pivotal process in dermatology, enabling the early detection and precise diagnosis of skin diseases, leading to improved patient outcomes. Deep learning has shown great potential for this task by leveraging its ability to learn complex patterns from images. However, diagnostic accuracy is compromised by exclusive reliance on single-modality images. This research work proposes an innovative framework that unifies a Vision Transformer model with transfer learning, channel attention mechanism, and ROI for the accurate detection of skin conditions, including skin cancer. The proposed approach blends computer vision and machine-learning techniques, leveraging a comprehensive dataset comprised of macroscopic dermoscopic images, appended with patient metadata. Compared with conventional techniques, the proposed methodology exhibits significant improvements in various parameters, including sensitivity, specificity, and precision. Moreover, it demonstrates outstanding performance in real-world datasets, reinforcing its potential for clinical implementation. With a remarkable accuracy of 99%, the method outperforms existing approaches. Overall, this investigation underscores the transformative impact of deep learning and multimodal data analysis in the dermoscopic domain, projecting substantial headway into the field of skin lesion analytic diagnosis.

Skin cancer is one of the most common types of cancer globally. Despite the remarkable advancements of deep learning methods in computer vision, automatic diagnosis of skin diseases still faces challenges such as limited data and class imbalance. Generative Adversarial Networks (GANs), which can synthesize realistic data, appear as an alternative to mitigate these issues. However, for imbalanced data, unconditional GANs either generate uneven data distribution or neglect universal knowledge of the whole dataset, while state-of-the-art (SOTA) conditional GANs suffer from performance degradation due to the mode collapse of minority classes. This paper proposes a two-stage GAN-based method to synthesize fine-grained and diverse $256 \times 256$ pixels skin lesion images for the imbalanced dataset, named Self-Transfer GAN (STGAN). STGAN first learns universal knowledge from all classes then transfers this shared knowledge to each class and fuses it with class-specific knowledge to synthesize high-quality images. Furthermore, based on STGAN, a framework to enhance the classification performance is established. Both data generation and classification tasks are evaluated on HAM10000 dataset. In terms of Fréchet Inception Distance (FID), Inception Score, Precision, and Recall, STGAN improved by 16%, 16%, 4%, 33% compared with SOTA conditional StyleGAN2. For classification, the STGAN-based framework achieves remarkable results, with an Accuracy of 98.23%, Sensitivity of 88.85%, Precision of 90.23%, F1-score of 89.48%, and Specificity of 98.34%.

The combination of observation of skin lesion and digital image technology contributes to the diagnosis and treatment of skin diseases. To solve the problems of large variation of target size and shape in skin disease images, small difference between disease images and normal images, and difficulty of label acquisition, we propose a classification algorithm for skin lesion based on hybrid self‐supervised pretext tasks. We combine the discriminative self‐supervised relational reasoning task with the generative self‐supervised mutual information maximization task and design the loss function. Experiments show that the generative‐discriminative self‐supervised co‐training algorithm can identify images with small differences and learn discriminative features and achieve a classification accuracy of 82.6% on the DermaMNIST dataset. [ABSTRACT FROM AUTHOR]

Skin cancer is a common type of malignant tumor that poses a serious threat to patients' lives and health, especially melanoma. It may spread to other body parts, resulting in serious complications and death. In the medical field, accurate identification of skin lesion images is crucial for diagnosing different diseases. However, due to the similarity between different skin lesions, it brings some challenges to medical diagnosis. In this paper, a novel Ensemble Learning Model (EL‐DLOA) based on deep learning and optimization algorithms is proposed, which uses four different deep neural network architectures to generate confidence levels for classes, and optimization algorithms are used to integrate these confidence levels to make the final predictions. To ensure the model's accuracy and reliability, it is first trained using three different learning rates to find the best classification performance of the model. Then, a new search method based on the grey wolf optimization algorithm is proposed to enhance the grey wolf search efficiency. The method improves the search mechanism by changing the grey wolf's individual position through random perturbation or adaptive mutation, which solves the problem that the grey wolf algorithm is easy to fall into local optimum. Finally, four different ensemble strategies are used to reduce individual model bias in the classification process. The proposed model is trained and evaluated using the publicly available dataset HAM10000. The experimental results show that the improved grey wolf optimization algorithm effectively avoids the premature convergence problem and improves the search combination efficiency. Furthermore, in the ensemble methods, the adaptive weight average ensemble strategy effectively improves the classification performance, yielding accuracy, precision, recall, and F1 scores of 0.888, 0.837, 0.897, and 0.862, respectively. These metrics show varying degrees of improvement over the best performing single model. In general, the results indicate that the proposed method achieves high accuracy and practicality in skin lesion classification. Our model shows excellent performance in comparison with other existing models, which makes it significant for research and application in dermatology diagnosis. [ABSTRACT FROM AUTHOR]

Melanoma skin cancer is a widely occurring disease over the globe and it is needed to identify the disease at the initial stages. Recent technologies like Internet of Things (IoT) have aimed to design efficient healthcare system. Besides, deep learning and transfer learning are progressively important in the healthcare diagnoses of various diseases. This study focuses on the design of Intelligent Internet of Things with Deep learning Enabled Skin Lesion Diagnosis (IIoT-DLSLD) model for healthcare environment. The proposed IIoT-DLSLD technique enables the IoT devices to capture the dermoscopic images and classify the skin lesions into distinct class labels. In addition, the IIoT-DLSLD technique employs Gaussian filtering (GF) based preprocessing technique to eradicate the presence of noise. Besides, Otsu thresholding with swallow swarm optimization (OT-SSO) algorithm is employed for skin lesion segmentation. For skin lesion classification, MobileNet v2 based feature extraction and emperor penguin optimizer (EPO) based deep wavelet neural network (DWNN) is utilized. The experimental validation of the IIoT-DLSLD technique take place against ISIC dataset and the results portrayed the betterment of the IIoT-DLSLD algorithm over the other state of art skin lesion classifiers.

Prototypical networks (PN) have emerged as one of multiple effective approaches for few-shot learning (FSL), even in medical image classification. This study focuses on implementing a PN for skin lesion classification to assess its performance, generalizability, and robustness when applied across 11 dermoscopic image domains. Unlike conventional FSL scenarios, where the performance is evaluated for unseen classes in the test set, our analysis extends this to evaluate PNs on a complete hold-out dataset with the same classes from a different domain. Differences in a patient’s age, lesion localization, or image acquisition systems variations mimic real-world cross-domain conditions in a clinic. Given the scarcity of medical datasets, this assessment is crucial for potentially translating such systems into real-world clinical settings to support physicians with the diagnosis. Our primary focus is two-fold: investigating whether a PN performs on par with a baseline classifier, even using only a limited number of reference samples from the hold-out test set (in-domain) and whether a PN can generalize to the same classes of unseen domains (cross-domain). Our analysis uncovers that a PN can perform on par with the baseline classifier in an in-domain setting, even with only a few support samples. However, in cross-domain scenarios, a PN exhibits improved performance only on specific domains, while others demonstrate similar or even decreased performance when confronted with a smaller number of images. Our findings contribute to comprehending potential opportunities and limitations of FSL in dermatological practice.