Big transfer learning for automated skin cancer classification

In the last few years, Deep Learning (DL) has been showing superior performance in different modalities of bio-medical image analysis. Several DL architectures have been proposed for classification, segmentation, and detection tasks in medical imaging and computational pathology. In this paper, we propose a new DL architecture, the NABLA-N network (∇N-Net), with better feature fusion techniques in decoding units for dermoscopic image segmentation tasks. The ∇N-Net has several advances for segmentation tasks. First, this model ensures better feature representation for semantic segmentation with a combination of low to high-level feature maps. Second, this network shows better quantitative and qualitative results with the same or fewer network parameters compared to other methods. In addition, the Inception Recurrent Residual Convolutional Neural Network (IRRCNN) model is used for skin cancer classification. The proposed ∇N-Net network and IRRCNN models are evaluated for skin cancer segmentation and classification on the benchmark datasets from the International Skin Imaging Collaboration 2018 (ISIC-2018). The experimental results show superior performance on segmentation tasks compared to the Recurrent Residual U-Net (R2U-Net). The classification model shows around 87% testing accuracy for dermoscopic skin cancer classification on ISIC2018 dataset.

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.

Solid organ transplant recipients (SOTRs) have a high risk of developing aggressive skin cancers. However, there are no standardized triage guidelines to assist dermatology clinics with scheduling new patients pre- or post-transplant. Dermatologic care of SOTRs requires multidisciplinary coordination, extensive assessment, tailored counseling, and longitudinal care. Specialized high-risk transplant clinics are designed to address this clinical need but are a limited resource. This triage algorithm aims to provide a practical framework for tertiary care centers or community practice clinics receiving pre- or post-transplant referrals for active concerning growths or routine skin cancer screening exams. In summary, our expert panel recommends SOTRs are seen within 1–2 weeks for evaluation of an active growth and triaged according to their risk factors for the initial post-transplant screening visit (6 months–2+ years post-transplant). Transplant candidates should be seen for pre-transplant evaluation within 1 month of the referral for a skin cancer screening exam, depending on the transplant team’s timeline and dermatologist availability. Overall, dermatologists face numerous challenges in caring for transplant patients, and scheduling these patients in a timely manner according to the acuity of their needs will facilitate prevention and early diagnosis of skin cancer, thus improving transplant patient outcomes.

Skin Cancer is an extensive and possibly dangerous disorder that requires early detection for effective treatment. Add specific global statistics on skin cancer prevalence and mortality to emphasize the importance of early detection. Example: “Skin cancer accounts for 1 in 5 diagnosed cancers globally, with melanoma causing over 60,000 deaths annually. Manual skin cancer screening is both time-intensive and expensive. Deep learning (DL) techniques have shown exceptional performance in various applications and have been applied to systematize skin cancer diagnosis. However, training DL models for skin cancer diagnosis is challenging due to limited available data and the risk of overfitting. Traditionally approaches have High computational costs, a lack of interpretability, deal with numerous hyperparameters and spatial variation have always been problems with machine learning (ML) and DL. An innovative method called adaptive learning has been developed to overcome these problems. In this research, we advise an intelligent computer-aided system for automatic skin cancer diagnosis using a two-stage transfer learning approach and Pre-trained Convolutional Neural Networks (CNNs). CNNs are well-suited for learning hierarchical features from images. Annotated skin cancer photographs are utilized to detect ROIs and reset the initial layer of the pre-trained CNN. The lower-level layers learn about the characteristics and patterns of lesions and unaffected areas by fine-tuning the model. To capture high-level, global features specific to skin cancer, we replace the fully connected (FC) layers, responsible for encoding such features, with a new FC layer based on principal component analysis (PCA). This unsupervised technique enables the mining of discriminative features from the skin cancer images, effectively mitigating overfitting concerns and letting the model adjust structural features of skin cancer images, facilitating effective detection of skin cancer features. The system shows great potential in facilitating the initial screening of skin cancer patients, empowering healthcare professionals to make timely decisions regarding patient referrals to dermatologists or specialists for further diagnosis and appropriate treatment. Our advanced adaptive fine-tuned CNN approach for automatic skin cancer diagnosis offers a valuable tool for efficient and accurate early detection. By leveraging DL and transfer learning techniques, the system has the possible to transform skin cancer diagnosis and improve patient outcomes.

The skin cell which grows abnormally is known as skin cancer and it is caused due to sun rays in the
 uncovered skin. It spreads within a week, so the early diagnosis of skin cancer is required. Skin Cancer
 Classification (SCC) based on ranklet transform, co-occurrence features and random forest classifier is
 presented in this paper. Dermoscopic image in the PH2 database is used in this study for performance
 evaluation. Initially, the dermoscopic images of three categories normal benign and malignant images are
 preprocessed to smooth the images. Then the images are given to ranklet transform for decomposition. It
 produces subband coefficients. The Ranklet Features based Co-occurrence Matrix (RFCM) is used to extract
 the features and stored in database. The classification is made by Random Forest Classifier (RFC). The result
 shows better classification accuracy of 93.5% sensitivity is 92% and specificity is 95% is obtained by RFCM
 and RFC.

In recent years, deep learning has achieved remarkable advancements in medical image analysis, particularly through Convolutional Neural Networks (CNNs) and Transformer-based architectures. This study aims to evaluate and compare the performance of five transfer learning models (DenseNet169, InceptionV3, MobileNetV2, VGG16 and Xception) and a Vision Transformer (ViT) model for the classification of skin cancer using the “Skin Cancer: Malignant vs. Benign” dataset .In the first phase, the ViT model achieved the highest overall performance with 93.79% recall, 92.22% precision, 93.00% F1-score and 92.42% accuracy. Although InceptionV3 and MobileNetV2 demonstrated strong recall values, they did not match the overall accuracy of ViT. In the second phase, image enhancement techniques—grayscale conversion, thresholding, Canny edge detection, dilation, and erosion were applied to emphasize lesion boundaries and improve contrast. Using these enhanced images, the ViT model again achieved the best performance, with 95.49% recall, 94.17% precision, 94.83% F1-score, and 94.39% accuracy. These results indicate that the ViT architecture provides superior accuracy and reliability in complex and enhanced medical images. Furthermore, the study demonstrates that incorporating image preprocessing techniques can significantly enhance the performance of deep learning models in medical imaging applications.

Increase in usage of cosmetics, pollution, and radiations will always result in skin-related diseases. Moreover, skin cancer has also become a common disease. There are many features available to help in the process of identification of skin cancer. Deep learning algorithms are successfully applied to identify the skin cancer. Various transfer learning strategies can also be applied. This paper attempts to compare various transfer learning approaches and the degree of accuracy by using these models. The analysis can be made by training the system with the details obtained from images available in the database and the current image is then tested to find whether it is malignant or not. The dataset images obtained from Kaggle dataset have been used for this study. Pre-trained models like InceptionV3, ResNet50, and MobileNet are used along with the extracted pre-trained weights in this research work.KeywordsSkin cancerDeep learningMobileNetResNet50Prediction

Skin cancer diagnosis challenges dermatologists due to its complex visual variations across diagnostic categories. Convolutional neural networks (CNNs), specifically the Efficient Net B0-B7 series, have shown superiority in multiclass skin cancer classification. This study addresses the limitations of visual examination by presenting a tailored preprocessing pipeline designed for Efficient Net models. Leveraging transfer learning with pre-trained ImageNet weights, the research aims to enhance diagnostic accuracy in an imbalanced multiclass classification context. The study develops a specialized image preprocessing pipeline involving image scaling, dataset augmentation, and artifact removal tailored to the nuances of Efficient Net models. Using the Efficient Net B0-B7 dataset, transfer learning fine-tunes CNNs with pre-trained ImageNet weights. Rigorous evaluation employs key metrics like Precision, Recall, Accuracy, F1 Score, and Confusion Matrices to assess the impact of transfer learning and fine-tuning on each Efficient Net variant's performance in classifying diverse skin cancer categories. The research showcases the effectiveness of the tailored preprocessing pipeline for Efficient Net models. Transfer learning and fine-tuning significantly enhance the models' ability to discern diverse skin cancer categories. The evaluation of eight Efficient Net models (B0-B7) for skin cancer classification reveals distinct performance patterns across various cancer classes. While the majority class, Benign Kertosis, achieves high accuracy (>87%), challenges arise in accurately classifying Eczema classes. Melanoma, despite its minority representation (2.42% of images), attains an average accuracy of 80.51% across all models. However, suboptimal performance is observed in predicting warts molluscum (90.7%) and psoriasis (84.2%) instances, highlighting the need for targeted improvements in accurately identifying specific skin cancer types. The study on skin cancer classification utilizes EfficientNets B0-B7 with transfer learning from ImageNet weights. The pinnacle performance is observed with EfficientNet-B7, achieving a groundbreaking top-1 accuracy of 84.4% and top-5 accuracy of 97.1%. Remarkably efficient, it is 8.4 times smaller than the leading CNN. Detailed per-class classification exactitudes through Confusion Matrices affirm its proficiency, signaling the potential of EfficientNets for precise dermatological image analysis.

Recently, there has been an increase in the number of cancer cases due to causes such as physical inactivity, sun exposure, environmental changes, harmful drinks and viruses. One of the most common types of cancer in the general population is skin cancer. There is an increase in exposure to the sun's harmful rays due to reasons such as environmental changes, especially ozone depletion. As exposure increases, skin changes occur in various parts of the body, especially the head and neck, in both young and old. In general, changes such as swelling in skin lesions are diagnosed as skin cancer. Skin cancers that are frequently seen in the society are known as actinic keratosis (akiec), basal cell carcinoma (bcc), bening keratosis (bkl), dermatofibroma (df), melanoma (mel), melanocytic nevi (nv), and vascular (vasc) types. It is not possible to consider all possible skin changes as skin cancer. In such a case, the development of a decision support system that can automatically classify the specified skin cancer images will help specialized healthcare professionals. For these purposes, a basic model based on MobileNet V3 was developed using the swish activation function instead of the ReLU activation function of the MobileNet architecture. In addition, a new CNN model with a different convolutional layer is proposed for skin cancer classification, which is different from the studies in the literature. The proposed CNN model (SkinCNN) achieved a 97% success rate by performing the training process 30 times faster than the pre-trained MobileNet V3 model. In both models, training, validation and test data were modelled by partitioning according to the value of cross-validation 3. MobileNet V3 model achieved F1 score, recall, precision, and accuracy metrics of 0.87, 0.88, 0.84, 0.83, 0.84, and 0.83, respectively, in skin cancer classification. The SkinCNN obtained F1 score, recall, precision, and accuracy metrics of 0.98, 0.97, 0.96, and 0.97, respectively. With the obtained performance metrics, the SkinCNN is competitive with the studies in the literature. In future studies, since the SkinCNN is fast and lightweight, it can be targeted to run on real-time systems.

Skin cancer continues to be a global health issue, with early detection being critical for improving treatment outcomes. While deep learning models like convolutional neural networks (CNNs) have proven highly efficient in skin cancer classification from dermatological images, they often disregard the valuable patient metadata that can contribute to better diagnostic accuracy. In the present study, we introduce a multimodal late fusion framework that integrates both skin cancer images and patient metadata. The approach leverages the Inception-ResNet-v2 (IRv2) model to extract image features, and a stacking ensemble model consisting of Extra Trees and Random Forest classifiers for patient metadata preprocessing. Then, a final voting classifier applying a soft voting strategy, which aggregates class probabilities from Logistic Regression and Random Forest as base voters, is employed for the final fusion methodology. This leads to an accuracy of 95.9% on the HAM10000 dataset. Our results highlight the potential of multimodal approaches in healthcare applications.

One of the most common causes of death worldwide is skin cancer and its incidence is increasing. To achieve optimal treatment and improve clinical outcomes for patients, precision skin cancer detection and classification approaches are required, which can be achieved through the application of feature extraction and machine learning algorithms. The development of such algorithms to identify important patterns from skin cancer image datasets enables early detection and more accurate classification and more effective treatment. Although previous studies have tried to detect skin cancer using feature extraction techniques such as HFF, HOG, and GLCM, some weaknesses still need to be improved. This research aims to combine various feature extraction methods such as Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns and machine learning algorithms such as Support Vector Machine, Random Forest, and Gaussian Naïve Bayes in the classification process between Melanoma and Nevus skin cancers. In this research, the number of datasets used is 17,397 derived from the ISIC Dataset. The results showed that the Histogram Oriented Gradients method with Support Vector Machine algorithm achieved the highest accuracy of 92%. The combination of Gray Level Co-occurrence Matrix and Local Binary Patterns with Random Forest algorithm also achieved an accuracy of 92%, the combination of Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns with Random Forest algorithm also resulted in an accuracy of 92%. These findings suggest that the combination of various feature extraction methods and machine learning algorithms can improve accuracy in skin cancer classification, which in turn can contribute to early detection and more effective treatment.

People around the world suffer from a wide range of illnesses. The most dangerous of them all is cancer. Of all the cancers, skin cancer is the one that is spreading the fastest. The reason for this is because skin cells grow abnormally. Skin cancer is spreading around the world in part due to an increase in UV light on Earth's surface. The two most prevalent kinds of skin cancer are benign and malignant. Despite undergoing costly and time-consuming therapies, skin cancer mortality rates do not decrease. Early identification of skin cancer in its early stages is useful in lowering the death rate. Deep learning is being utilized in the modern world to identify illnesses. Convolutional neural networks (CNNs) improve the accuracy of image classification in the detection of skin cancer. This study compares the operational procedures of several CNN models in order to identify which produces the best outcomes. CNN models are analyzed using pre-trained models such as VGG16, Res-Net50, and Inception Resnet V2. Due to differences in their layer numbers, these models operate in distinct ways. Certain models function better than others, depending on their layers and how they operate. A Kaggle picture dataset containing both benign and cancerous data has been extracted. There are 3287 photos of benign and malignant skin cancer in this dataset. We have obtained accurate results for VGG16 (85%), ResNet50 (69%), and Inception Resnet V2 (83%), using various techniques. This study compares these results according to the model's operation. We compare precision, working process, and model layer numbers.

Enhancement in Skin Cancer Detection using Image Super Resolution and Convolutional Neural Network

Skin cancer is one of the most dangerous types of cancer due to its immediate appearance and the possibility of rapid spread. It arises from uncontrollably growing cells, rapidly dividing cells in one area of the body, invading other bodily tissues, and spreading throughout the body. Early detection helps prevent cancer progress from reaching critical levels, reducing the risk of complications and the need for more aggressive treatment options. Convolutional neural networks (CNNs) revolutionize skin cancer diagnosis by extracting intricate features from images, enabling an accurate classification of lesions. Their role extends to early detection, providing a powerful tool for dermatologists to identify abnormalities in their nascent stages, ultimately improving patient outcomes. This study proposes a novel deep convolutional neural network (DCNN) approach to classifying skin cancer lesions. The proposed DCNN model is evaluated using two unbalanced datasets, namely HAM10000 and ISIC-2019. The DCNN model is compared with other transfer learning models, including VGG16, VGG19, DenseNet121, DenseNet201, and MobileNetV2. Its performance is assessed using four widely used evaluation metrics: accuracy, recall, precision, F1-score, specificity, and AUC. The experimental results demonstrate that the proposed DCNN model outperforms other deep learning (DL) models that utilized these datasets. The proposed DCNN model achieved the highest accuracy with the HAM10000 and ISIC-2019 datasets, reaching 98.5%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$98.5\\%$$\\end{document} and 97.1%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$97.1\\%$$\\end{document}, respectively. These experimental results show how competitive and successful the DCNN model is in overcoming the problems caused by class imbalance and raising skin cancer classification accuracy. Furthermore, the proposed model demonstrates superior performance, particularly excelling in terms of accuracy, compared to other recent studies that utilize the same datasets, which highlights the robustness and effectiveness of the proposed DCNN.

Skin cancers are one of the most common cancers in the world. Early detections and treatments of skin cancers can greatly improve the survival rates of patients. In this paper, a skin lesions classification system is developed with deep convolutional neural networks of ResNet50, which may help dermatologists to recognize skin cancers earlier. We utilize the ResNet50 as a pre-trained model. Then, by transfer learning, it is trained on our skin lesions dataset. Image preprocessing and dataset balancing methods are used to increase the accuracy of the classification model. In classification of skin diseases, our model achieves an overall accuracy of 83.74% on nine-class skin lesions. The experimental results show an impressive effect of the ResNet50 model in finegrained skin lesions classification and skin cancers recognition.