Feature Fusion for Improved Skin Cancer Diagnosis Using Support Vector Machines

Abstract: Early detection of skin cancer, including types such as basal cell carcinoma and melanoma, is crucial for effective treatment and reducing mortality rates. Skin cancer diagnoses often surpass those of all other cancers combined, with rising global mortality rates underscoring the need for improved detection methods. Early identification significantly enhances treatment outcomes, as confirmed by the World Health Organization. Advances in image processing and machine vision, particularly through convolutional neural networks (CNNs), have shown that deep learning models can outperform experienced dermatologists in skin cancer detection. In this project, we developed a deep learning model using Python libraries to categorize dermoscopic images from the MNIST HAM-10000 dataset into malignant or benign categories. The model's performance was further evaluated against three datasets from the International Skin Imaging Collaboration (ISIC) challenge archives, with the goal of enhancing early detection and treatment of skin cancer to lower mortality rates

The medical sciences are facing a major problem with the auto-detection of disease due to the fast growth in population density. Intelligent systems assist medical professionals in early disease detection and also help to provide consistent treatment that reduces the mortality rate. Skin cancer is considered to be the deadliest and most severe kind of cancer. Medical professionals utilize dermoscopy images to make a manual diagnosis of skin cancer. This method is labor-intensive and time-consuming and demands a considerable level of expertise. Automated detection methods are necessary for the early detection of skin cancer. The occurrence of hair and air bubbles in dermoscopic images affects the diagnosis of skin cancer. This research aims to classify eight different types of skin cancer, namely actinic keratosis (AKs), dermatofibroma (DFa), melanoma (MELa), basal cell carcinoma (BCCa), squamous cell carcinoma (SCCa), melanocytic nevus (MNi), vascular lesion (VASn), and benign keratosis (BKs). In this study, we propose SNC_Net, which integrates features derived from dermoscopic images through deep learning (DL) models and handcrafted (HC) feature extraction methods with the aim of improving the performance of the classifier. A convolutional neural network (CNN) is employed for classification. Dermoscopy images from the publicly accessible ISIC 2019 dataset for skin cancer detection is utilized to train and validate the model. The performance of the proposed model is compared with four baseline models, namely EfficientNetB0 (B1), MobileNetV2 (B2), DenseNet-121 (B3), and ResNet-101 (B4), and six state-of-the-art (SOTA) classifiers. With an accuracy of 97.81%, a precision of 98.31%, a recall of 97.89%, and an F1 score of 98.10%, the proposed model outperformed the SOTA classifiers as well as the four baseline models. Moreover, an Ablation study is also performed on the proposed method to validate its performance. The proposed method therefore assists dermatologists and other medical professionals in early skin cancer detection.

Background/Objectives: Skin cancer is a very serious disease. There is a risk that the cancer will spread to other parts of the body as the cancerous tissue deepens. For this reason, early diagnosis is important because it allows for early initiation of treatment. This study proposes a hybrid model for the early diagnosis of skin cancer. Methods: The proposed model was developed using Convolutional Neural Networks (CNNs), Vision Transformer (ViT) architectures, and the k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Neural Network Classifiers, Decision Tree (DT), and Logistic Regression (LR) classifiers. Furthermore, the proposed model was fine-tuned to improve its disease diagnosis. Two attention mechanisms, channel and spatial, were used together in the proposed model. The HAM10000 dataset was used during the experiments. Class weighting was performed to ensure class-based balance in the dataset. Results: The proposed model was also compared with the CNN and ViT architectures frequently used in the literature. Among these models, the highest accuracy value of 95.1% was obtained with the proposed model. Conclusions: It is considered that the proposed model can be used as a decision support system for dermatologists in the diagnosis of skin cancer.

Early detection of skin cancer allows timely treatment and improves clinical outcome. The armamentarium for diagnosing skin cancer has been growing notably over the last decades. New tools have led to earlier recognition and a more specific and sensitive diagnosis. In this editorial, we discuss several recent studies published in the BJD on the diagnosis of pigmented skin lesions. The majority of studies published on the detection of skin cancer have investigated methods that are already widely accepted and increasingly used in dermatology, such as dermatoscopy, reflectance confocal microscopy (RCM) and teledermatology. Other investigators have walked off the beaten paths and reported unconventional findings, for example Willis et al. investigated a dog's olfactory ability to discriminate melanoma from control skin lesions.1 In this study, a Labrador, named Ronnie, performed 20 double‐blind tests, each requiring the selection of one melanoma from nine controls, consisting of three each of basal cell carcinomas, naevi and healthy skin. Ronnie correctly identified the melanoma on nine occasions (45%), vs. two expected by chance alone. This creative work demonstrates that invasive melanoma emits volatile organic compounds that differ from those of control lesions. The volatile compounds might be utilized as new biomarkers for a noninvasive diagnosis of melanoma using standardized biochemical assays.

Background: Malignant melanoma is rising quickly in incidence and mortality rates. Family physicians (FPs) have been reported to lack confidence in diagnosing skin cancers. Objective: The aim of this study was to determine whether an educational intervention can improve FPs' abilities to diagnose skin cancers. Methods: The design was a prospective, randomized trial which included a skin cancer questionnaire, a video intervention, and a skin biopsy review. Results: Pre-intervention, FPs answered 57% of the questions correctly on the skin cancer questionnaire. Post-intervention, the video intervention group scored higher than did the control group. The video intervention group removed 10% fewer benign lesions and almost 3 times more malignant lesions compared with their pre-intervention biopsy rate. No findings were statistically significant. Conclusion: An educational intervention may improve FPs' knowledge and diagnosis of skin cancer. Our results may guide future studies with larger sample sizes in developing a skin cancer continuing medical education (CME) course for FPs.

Skin cancer is the most predominat cancer in the world. Detection of skin cancer in earrly stages helps to decrease the fatality rate. Image processing and AI plays vital role in early detection of skin cancer. Dermoscopy images are used by doctors to detect skin cancer.In this paper, shape based features such as eccentricity, perimeter, convex area, orientation,area, ratio of major axis to minor acis length, eqvidiameter have been extracted from segmented skin lesion lesions. Subsequntly these features are give different classifiers such as SVM,KNN,ensemble learning. The efficacy of the proposed method was evaluated on 200 segmented skin lesions of common nevus, atypical nevus and melanoma with different class combinations. The proposed method achieved accuracy of 90% accuracy (acc) and 93% sensitivity (sen) for classifying segmented skin lesions into commatypical nevi and malignant melanoma. This approach helps dermatologists in screening skin lesions very fast and accurate.

Skin cancer prevention is a public health priority due to its high incidence and potential to cause significant morbidity and mortality. This study evaluated the effectiveness of an early skin cancer detection program in a community pharmacy, utilizing advanced technologies and interdisciplinary collaboration. 1. Early detection of melanoma and non-melanoma skin cancer in patients visiting the community pharmacy. 2. Facilitate patient referral to a dermatologist through the pharmacy. A cross-sectional observational study was conducted in a community pharmacy between June 2018 and September 2023. Adult patients concerned about skin lesions were included. After obtaining written informed consent, an interview was conducted, and photographs of the lesions were taken and electronically sent to a dermatology service for a preliminary diagnosis within 24-48 hours. A total of 41 patients were evaluated (51% men; 54% over 50 years old). Benign lesions were identified in 54% of cases, avoiding unnecessary consultations and optimizing health resources. 46% presented suspicious cancer lesions requiring detailed evaluation, with 63% of this group being over 60 years old. More than 85% of the preliminary diagnoses were accurate with the images sent. The results underscore the effectiveness of early detection programs in community pharmacies for identifying benign and suspicious lesions, optimizing resources, and facilitating early interventions. The collaboration between pharmacists and dermatologists, along with the use of advanced technologies, were key to the program's success. However, the study's limitations include the sample size and its focus on a single pharmacy. Community pharmacies can play a crucial role in the secondary prevention of skin cancer, improving healthcare system efficiency and benefiting patients through early detection and timely intervention. Future studies with larger samples are recommended to validate these findings and quantify resource optimization.

Skin cancers are the most common form of cancers in humans. It is a deadly type of cancer affecting skin. Most of the skin cancers are curable at initial stages. So an early detection of skin cancer can save the patients. Conventional diagnosis method for skin cancer detection is Biopsy method. It is done by removing or scraping off skin and that sample undergoes a series of laboratory testing. It is painful and time consuming one. Computer based skin cancer detection is more advantageous to patients, by which patients can identify the skin cancer without going to hospital or without the help of a doctor. Computer based detection uses imaging techniques and Artificial Intelligence. The different stages of detection involves- collection of dermoscopic images, filtering the images for removing hairs and noises, segmenting the images using Maximum Entropy Threshold, feature extraction using Gray Level Co-occurrence Matrix(GLCM), and classification using Artificial Neural Network(ANN). Back-Propagation Neural (BPN) Network is used for classification purpose. It classifies the given data set into cancerous or non-cancerous.

Skin cancer is one of the most dangerous types of cancer among the cancers. The early detection of skin cancer helps resolve it. Hence, it is necessary to diagnose the disease as early as possible. This paper presents Convolutional Neural Networks and the Vgg16 algorithm to recognize skin cancer types. The HAM10000 dataset, which comprises seven distinct forms of skin cancer, melanocytic nevi (nv), Melanoma (mel), basal cell carcinoma (bcc), actinic keratoses (akiec), vascular lesions (vasc), and dermatofibroma (df). This system aims to improve classification accuracy; the methodology necessitates extensive dataset preparation, including scaling, normalization, and augmentation. The Vgg16 algorithm, when combined with the CNN architecture, offers a robust basis for the classification of skin cancer. Comprehensive details on regularization techniques, optimization strategies, and training parameters are included to ensure openness and reproducibility. The system's performance is evaluated using accuracy, precision, recall, and F1-score for every type of skin cancer. This paper highlights the usefulness of the proposed method in skin cancer diagnosis and looks at challenges, constraints, and prospects for further research. New methods for identifying skin cancer are being developed with the help of this research, which can improve patient outcomes and clinical decision-making.

The early detection of Non-Melanoma Skin Cancer (NMSC) is crucial to achieve the best treatment outcomes. Shape is considered one of the main parameters taken for the detection of some types of skin cancer such as melanoma. For NMSC, the importance of shape as a visual detection parameter is not well-studied. A dataset of 993 standard camera images containing different types of NMSC and benign skin lesions was analysed. For each image, the lesion boundaries were extracted. After an alignment and scaling, Elliptic Fourier Analysis (EFA) coefficients were calculated for the boundary of each lesion. The asymmetry of lesions was also calculated. Then, multivariate statistics were employed for dimensionality reduction and finally computational learning classification was employed to evaluate the separability of the classes. The separation between malignant and benign samples was successful in most cases. The best-performing approach was the combination of EFA coefficients and asymmetry. The combination of EFA and asymmetry resulted in a balanced accuracy of 0.786 and an Area Under Curve of 0.735. The combination of EFA and asymmetry for lesion classification resulted in notable success rates when distinguishing between benign and malignant lesions. In light of these results, skin lesions’ shape should be integrated as a fundamental part of future detection techniques in clinical screening.

Convolutional neural networks (CNNs) are a branch of deep learning which have been turned into one of the popular methods in different applications, especially medical imaging. One of the significant applications in this category is to help specialists make an early detection of skin cancer in dermoscopy and can reduce mortality rate. However, there are a lot of reasons that affect system diagnosis accuracy. In recent years, the utilization of computer-aided technology for this purpose has been turned into an interesting category for scientists. In this research, a meta-heuristic optimized CNN classifier is applied for pre-trained network models for visual datasets with the purpose of classifying skin cancer images. However there are different methods about optimizing the learning step of neural networks, and there are few studies about the deep learning based neural networks and their applications. In the present work, a new approach based on whale optimization algorithm is utilized for optimizing the weight and biases in the CNN models. The new method is then compared with 10 popular classifiers on two skin cancer datasets including DermIS Digital Database Dermquest Database. Experimental results show that the use of this optimized method performs with better accuracy than other classification methods.

Advances in medical diagnostics have increasingly harnessed the power of artificial intelligence, offering substantial improvements in early and accurate disease identifi- cation. This paper elaborates on a novel integration of Multi-Agent Reinforcement Learning (MARL) with Deep Learning for the early detection of skin cancer, one of the most prevalent and lethal forms of cancer when left unchecked. Our project capitalizes on the sophisticated VGG16 Network for the extraction of detailed features from the widely-utilized HAM10000 dermatoscopic dataset, enhancing these features with additional color, texture, and shape analysis. Utilizing a custom-designed MARL environment, we facilitate a collaboration among multiple intelligent agents, each harnessing Deep Q-Networks (DQN) for the optimization of decision-making processes. The results showcase our model’s proficiency, boasting an impressive accuracy rate of 94% in the classification of skin lesions. This indicates a significant leap towards a new era of computational assistance in dermatology, providing non-invasive, rapid, and reliable diagnostics for skin cancer.

Climate and other environmental humans are being more exposed to the Sun's ultraviolet(UV) rays. This exposure has increased the chances of humans developing skin cancer. The early detection of skin cancer is vital for curing this disease. The recent development in Neural Networks and state of the art deep learning techniques have an essential role in detecting skin cancer. In this paper, we extensively go through the deep neural network architectures and compare their results. We have tried to propose an analysis report using the state-of-the-art transfer and comparing their prediction capabilities to detect Skin Cancer by testing it on the HAM1000 dataset. We propose a solution by using transfer learning which have very heavily trained dense trainable layers with weights from imagenet. Finally, we show that among all the models, Resnet50, U-net, Densenet121, MOBILENETV1, InceptionV3 and U Net achieved the highest accuracy with 91% test accuracy becoming the top approach. To draw comparison, we have also used CNN architecture models which was previously structured using Keras Sequential API. We see the newer dense transfer learning models provide better testing accuracy. Hence, this paper aims to detect skin in its early stage to start treatment and hopefully save valuable lives in the process.

ObjectiveIn computer-aided medical diagnosis, precise skin lesion segmentation is crucial for the early detection and treatment of skin cancer. However, challenges such as unclear lesion boundaries, low contrast, and varying lesion shapes make accurate segmentation a difficult task. To address these challenges, we propose DMFF-Net, a multi-scale, multi-attention feature fusion network based on DeepLabV3, designed to improve the accuracy of skin lesion segmentation.MethodsDMFF-Net integrates several advanced modules to enhance segmentation performance. The network incorporates a Global Grid Coordinate Attention Module (GGCAM), which effectively fuses spatial and channel features to capture the complex relationships between local and global information. Additionally, a Multi-Scale Depthwise Separable Dilated Convolution (MDSDC) module is employed to strengthen multi-scale feature extraction, thereby preventing resolution degradation during convolution. A Mid-High Level Feature Fusion (MHLFF) module is also introduced to refine critical feature representations and suppress irrelevant information, thereby improving segmentation accuracy.ResultsThe proposed network was evaluated on four publicly available datasets: ISIC 2016, ISIC 2017, ISIC 2018, and PH2. The results show that DMFF-Net significantly outperforms existing advanced methods. Specifically, it achieves MIoU values of 89.31%, 91.47%, and 86.93% on the ISIC 2016, ISIC 2017, and ISIC 2018 datasets, respectively. Furthermore, the network achieves accuracy values of 95.62%, 97.33%, and 94.78%, and F1 scores of 96.93%, 94.91%, and 93.61%, respectively, demonstrating its robustness and effectiveness in skin lesion segmentation.ConclusionThe DMFF-Net model, with its multi-scale feature fusion and attention mechanisms, substantially improves skin lesion segmentation by preserving crucial spatial details and improving feature representation. Its superior performance on multiple datasets highlights its potential as a powerful tool for skin lesion diagnosis and provides an important reference for future advancements in medical image segmentation.

Early detection of skin cancer is crucial for improving patient outcomes, as the disease progresses rapidly when left untreated. Recent advancements in artificial intelligence have revolutionized the field of early detection, giving clinicians more accurate and efficient diagnostic tools. In this paper, two convolutional neural network-based classifiers using transfer learning are proposed to improve early skin cancer detection. These models were trained and tested on the novel ISIC-2024 dataset. To mitigate the class imbalance in this Dataset, a Generative Adversarial Network (DCGAN) is adopted to synthesize malignant samples. Additionally, the pre-trained VGG-16 and MobileNetV2 models were fine-tuned to improve feature learning and classification performance. Our MobileNetV2-based model outperformed the VGG16-based model, achieving an accuracy of 96.87%, a precision of 98.97%, and a recall of 94.7%. These results highlight the impact of deep learning in early skin cancer detection, and most importantly, they lead to better patient outcomes.