Diagnosis Of Skin Cancer Research Articles

Clinical Utility of a Digital Dermoscopy Image-Based Artificial Intelligence Device in the Diagnosis and Management of Skin Cancer by Dermatologists

Background: Patients with skin lesions suspicious for skin cancer or atypical melanocytic nevi of uncertain malignant potential often present to dermatologists, who may have variable dermoscopy triage clinical experience. Objective: To evaluate the clinical utility of a digital dermoscopy image-based artificial intelligence algorithm (DDI-AI device) on the diagnosis and management of skin cancers by dermatologists. Methods: Thirty-six United States board-certified dermatologists evaluated 50 clinical images and 50 digital dermoscopy images of the same skin lesions (25 malignant and 25 benign), first without and then with knowledge of the DDI-AI device output. Participants indicated whether they thought the lesion was likely benign (unremarkable) or malignant (suspicious). Results: The management sensitivity of dermatologists using the DDI-AI device was 91.1%, compared to 84.3% with DDI, and 70.0% with clinical images. The management specificity was 71.0%, compared to 68.4% and 64.9%, respectively. The diagnostic sensitivity of dermatologists using the DDI-AI device was 86.1%, compared to 78.8% with DDI, and 63.4% with clinical images. Diagnostic specificity using the DDI-AI device increased to 80.7%, compared to 75.9% and 73.6%, respectively. Conclusion: The use of the DDI-AI device may quickly, safely, and effectively improve dermoscopy performance, skin cancer diagnosis, and management when used by dermatologists, independent of training and experience.

Recent Progress and Current Status of Artificial Intelligence in Skin Cancer Diagnosis: A Systematic Review—Where do we Stand?

Introduction: Skin cancer is one of the most prevalent forms worldwide, with a significant increase in recent decades. Real-time and accurate detection can reduce the burdens of invasive treatments. The advent of Artificial Intelligence (AI) and Machine learning (ML) has introduced multiple tools to aid accurate and early detection, categorizing dermatological images and proving especially valuable in regions with a shortage of specialists. However, the adoption of these AI-based tools requires consideration of efficacy, safety, and ethical implications. Objective: The systematic review aims to evaluate existing research on the detection, categorization, and assessment of skin cancer images. Methods: The systematic literature review is conducted based on studies published from 2018 to 2023 in PubMed, Scopus, Embase, Web of Science, IEEE Xplore, ACM DL, and Ovid MEDLINE. Study selection, data extraction, and inclusion are carried out after a proper evaluation of the studies. Results are presented in tables and figures using a narrative synthesis. Results: The search identified 687 studies from the database. However, after three phases of identification, screening, and evaluation, only 16 studies were chosen, focusing on developing and validating AI tools to detect, diagnose, and categorize skin cancer. This systematic review covers the selected studies in multiple dimensions. Conclusion: The use of AI and ML in dermatology has revolutionized the early detection of cancer, but it is necessary to validate and collaborate with healthcare professionals to ensure efficacy, safety, and effectiveness.

Skin Cancer Image Classification Using Artificial Intelligence Strategies: A Systematic Review

The increasing incidence of and resulting deaths associated with malignant skin tumors are a public health problem that can be minimized if detection strategies are improved. Currently, diagnosis is heavily based on physicians’ judgment and experience, which can occasionally lead to the worsening of the lesion or needless biopsies. Several non-invasive imaging modalities, e.g., confocal scanning laser microscopy or multiphoton laser scanning microscopy, have been explored for skin cancer assessment, which have been aligned with different artificial intelligence (AI) strategies to assist in the diagnostic task, based on several image features, thus making the process more reliable and faster. This systematic review concerns the implementation of AI methods for skin tumor classification with different imaging modalities, following the PRISMA guidelines. In total, 206 records were retrieved and qualitatively analyzed. Diagnostic potential was found for several techniques, particularly for dermoscopy images, with strategies yielding classification results close to perfection. Learning approaches based on support vector machines and artificial neural networks seem to be preferred, with a recent focus on convolutional neural networks. Still, detailed descriptions of training/testing conditions are lacking in some reports, hampering reproduction. The use of AI methods in skin cancer diagnosis is an expanding field, with future work aiming to construct optimal learning approaches and strategies. Ultimately, early detection could be optimized, improving patient outcomes, even in areas where healthcare is scarce.

Addressing Challenges in Skin Cancer Diagnosis: A Convolutional Swin Transformer Approach.

Skin cancer is one of the top three hazardous cancer types, and it is caused by the abnormal proliferation of tumor cells. Diagnosing skin cancer accurately and early is crucial for saving patients' lives. However, it is a challenging task due to various significant issues, including lesion variations in texture, shape, color, and size; artifacts (hairs); uneven lesion boundaries; and poor contrast. To solve these issues, this research proposes a novel Convolutional Swin Transformer (CSwinformer) method for segmenting and classifying skin lesions accurately. The framework involves phases such as data preprocessing, segmentation, and classification. In the first phase, Gaussian filtering, Z-score normalization, and augmentation processes are executed to remove unnecessary noise, re-organize the data, and increase data diversity. In the phase of segmentation, we design a new model "Swinformer-Net" integrating Swin Transformer and U-Net frameworks, to accurately define a region of interest. At the final phase of classification, the segmented outcome is input into the newly proposed module "Multi-Scale Dilated Convolutional Neural Network meets Transformer (MD-CNNFormer)," where the data samples are classified into respective classes. We use four benchmark datasets-HAM10000, ISBI 2016, PH2, and Skin Cancer ISIC for evaluation. The results demonstrated the designed framework's better efficiency against the traditional approaches. The proposed method provided classification accuracy of 98.72%, pixel accuracy of 98.06%, and dice coefficient of 97.67%, respectively. The proposed method offered a promising solution in skin lesion segmentation and classification, supporting clinicians to accurately diagnose skin cancer.

Advances in Deep Learning for Skin Cancer Diagnosis

The most prevalent type of cancer worldwide is known as skin cancer. Early detection is critical because if left undiagnosed in the primary stage, it might be fatal. Although there are differences within the class and high inter-class similarities, it is too difficult to distinguish with the naked eye. Owing to the disease's global prevalence, a number of deep learning based automated systems were created thus far to help doctors identify skin lesions early on. Using pre-trained ImageNet weights and fine-tuning the Convolutional Neural Networks (CNNs), we trained VGG19 on the HAM10000 dataset. The optimal performance was observed with FT. The model that was created, which yielded an accuracy that was greater overall than the one used in transfer learning, was 82.4±1.9 %. By offering a second opinion and supporting the clinician's diagnosis, this performance could lower morbidity and treatment costs.

Hybrid Deep Learning Framework for Melanoma Diagnosis Using Dermoscopic Medical Images

Background: Melanoma, or skin cancer, is a dangerous form of cancer that is the major cause of the demise of thousands of people around the world. Methods: In recent years, deep learning has become more popular for analyzing and detecting these medical issues. In this paper, a hybrid deep learning approach has been proposed based on U-Net for image segmentation, Inception-ResNet-v2 for feature extraction, and the Vision Transformer model with a self-attention mechanism for refining the features for early and accurate diagnosis and classification of skin cancer. Furthermore, in the proposed approach, hyperparameter tuning helps to obtain more accurate and optimized results for image classification. Results: Dermoscopic shots gathered by the worldwide skin imaging collaboration (ISIC2020) challenge dataset are used in the proposed research work and achieved 98.65% accuracy, 99.20% sensitivity, and 98.03% specificity, which outperforms the other existing approaches for skin cancer classification. Furthermore, the HAM10000 dataset is used for ablation studies to compare and validate the performance of the proposed approach. Conclusions: The achieved outcome suggests that the proposed approach would be able to serve as a valuable tool for assisting dermatologists in the early detection of melanoma.

Skin cancer in Europe today and challenges for tomorrow.

One in every three cancers diagnosed is a skin cancer. Europe has the global lead in the number of UV-attributable cancer cases with the highest number of melanoma cases worldwide and the second highest number of keratinocyte cancers (KC). Further increases are expected in Europe for the coming decades. Projected increases are highest for KC with increases in incidence around 40% and increases in mortality around 50%, with KC mortality in males approximating melanoma mortality in females. The two main drivers for this skin cancer epidemic are ageing of the population but especially UV exposure. In conclusion, skin cancer represents a major challenge in the cancer field in Europe today and will continue to do so in the coming decades. This calls for a European skin cancer action plan intended to reduce avoidable UV exposure and to prepare the healthcare system to safeguard early diagnosis and treatment of skin cancer.

Diagnosing skin cancer using social spider optimization (SSO) and error correcting output codes (ECOC) with weighted hamming distance

Skin cancer is a common disease resulting from genetic defects, and early detection is critical to improve treatment outcomes. Diagnostic programs that use computer aid especially those that use supervised learning are very useful in early diagnosis of skin cancer. This research therefore presents a new approach that integrates optimization methods with supervised learning to improve skin cancer diagnosis using machine vision approach. The presented method is initiated by data pre-processing that involves the removal of unnecessary data. Then, to segment the images, a combination of K-means clustering and social spider optimization technique is employed. The region of interest is then extracted from the segmented image and from this region a convolutional neural network extracts the significant features. To enhance the classification performance as compared with the standard classifiers, this research introduces a new concept of error correcting output codes coupled with a weighted Hamming distance in the group of gamma classifiers. The ability of the proposed approach in segmentation of skin lesions and classifying them was tested using samples from the ISIC-2017 and ISIC-2016 databases. The introduced method obtained state-of-the-art accuracy on both datasets (ISIC-2016: 97.10%, ISIC-2017: 95.17%). In particularly, the accuracy of the introduced approach for both these databases is at least 1.17% higher than the compared methods. This proves the high performance of the suggested method based on the usage of the convolutional neural networks for feature extraction and gamma classifiers with error correcting output codes for classification in skin cancer detection.

Integrating generative AI with ABCDE rule analysis for enhanced skin cancer diagnosis, dermatologist training and patient education.

The early detection and accurate monitoring of suspicious skin lesions are critical for effective dermatological diagnosis and treatment, particularly for reliable identification of the progression of nevi to melanoma. The traditional diagnostic framework, the ABCDE rule, provides a foundation for evaluating lesion characteristics by visual examination using dermoscopes. Simulations of skin lesion progression could improve the understanding of melanoma growth patterns. This study aims to enhance lesion analysis and understanding of lesion progression by providing a simulated potential progression of nevi into melanomas. The study generates a dataset of simulated lesion progressions, from nevi to simulated melanoma, based on a Cycle-Consistent Adversarial Network (Cycle-GAN) and frame interpolation. We apply an optical flow analysis to the generated dermoscopic image sequences, enabling the quantification of lesion transformation. In parallel, we evaluate changes in ABCDE rule metrics as example to assess the simulated evolution. We present the first simulation of nevi progressing into simulated melanoma counterparts, consisting of 152 detailed steps. The ABCDE rule metrics correlate with the simulation in a natural manner. For the seven samples studied, the asymmetry metric increased by an average of 19%, the border gradient metric increased by an average of 63%, the convexity metric decreased by an average of 3%, the diameter increased by an average of 2%, and the color dispersion metric increased by an average of 45%. The diagnostic value of the ABCDE rule is enhanced through the addition of insights based on optical flow. The outward expansion of lesions, as captured by optical flow vectors, correlates strongly with the expected increase in diameter, confirming the simulation's fidelity to known lesion growth patterns. The heatmap visualizations further illustrate the degree of change within lesions, offering an intuitive visual proxy for lesion evolution. The achieved simulations of potential lesion progressions could facilitate improved early detection and understanding of how lesions evolve. By combining the optical flow analysis with the established criteria of the ABCDE rule, this study presents a significant advancement in dermatoscopic diagnostics and patient education. Future research will focus on applying this integrated approach to real patient data, with the aim of enhancing the understanding of lesion progression and the personalization of dermatological care.

Time from Diagnostic Suspicion to In-Person Evaluation in Skin Cancer Using Teledermatology.

Introduction: Early diagnosis of skin cancer is crucial for improving prognosis. Teledermatology (TD) usage can optimize referrals and reduce waiting times. This study aims to evaluate waiting times at the critical referral nodes in teleinterconsultations that raised suspicion of skin malignancy in the Chilean TD platform of the public health care system. Materials and Methods: A cross-sectional observational study that analyzed asynchronous teleinterconsultations and raised suspicion for skin malignancy following the teledermatologist evaluation was uploaded on the Chilean Ministry of Health's TD platform from January 1 to June 30, 2022. Results: Out of 20,522 teleinterconsultations, 1,853 raised suspicion of skin cancer. Among them, 1,119 patients were assessed by in-person examination, while 669 were still on the waiting list. Response times averaged 3.98 days for TD diagnostic suggestions. Overall referral times averaged 75.98 days from initial teleinterconsultation to the final specialist in-person evaluation. Waiting times showed significant differences among health care services and geographic regions. Discussion: In resource-limited settings, TD serves as a valuable tool to optimize referrals and manage the demand for oncologic dermatological consultation. The long waiting times emphasize the need for targeted interventions, especially in regions with longer delays. Conclusion: While TD has shown to be an effective tool in optimizing referrals, waiting times still exceed international recommendations, even in urban centers. The considerable heterogeneity in referral times within health care services and geographic regions highlights the necessity of establishing standardized referral protocols and explicit deadlines to fulfill teleinterconsultations that raise suspicion of skin malignancy in the Chilean public system.

ACGAN: adaptive conditional generative adversarial network architecture predicting skin lesion using collaboration of transfer learning models

Skin cancer has become a serious disease which has the potential to scale up if it is not identified earlier. It is imperative to detect and give treatment to skin cancer promptly. Diagnosing skin cancer manually takes a lot of time and it is costly, and the probability of false diagnosis has increased due to the outstanding resemblances among various skin lesions. Enhancing the classification of multi-class lesions of skin needs the development of investigative systems which should be automated. Data augmentation with GANs and Adaptive Conditional Generative Adversarial Network strategies improves performance. The performance is tested using balanced and unbalanced datasets. Using a proper process of augmentation of data, the suggested system attains a 94% accuracy for the VGG16, 93% for the ResNet50 and 94.25% for ResNet101. The process of collaboration of all such methods improves accuracy further to 95%. In summary, the novelty of the work lies in its holistic approach to automated skin lesion classification, incorporating advanced deep learning models, novel data augmentation techniques and comprehensive performance evaluation on real-world datasets. These contributions collectively advance the field of computer-aided diagnosis for the detection of skin cancer and treatment.

Skin Lesion Segmentation through Generative Adversarial Networks with Global and Local Semantic Feature Awareness

The accurate segmentation of skin lesions plays an important role in the diagnosis and treatment of skin cancers. However, skin lesion areas are rich in details and local features, including the appearance, size, shape, texture, etc., which pose challenges for the accurate localization and segmentation of the target area. Unfortunately, the consecutive pooling and stride convolutional operations in existing convolutional neural network (CNN)-based solutions lead to the loss of some spatial information and thus constrain the accuracy of lesion region segmentation. In addition, using only the traditional loss function in CNN cannot ensure that the model is adequately trained. In this study, a generative adversarial network is proposed, with global and local semantic feature awareness (GLSFA-GAN) for skin lesion segmentation based on adversarial training. Specifically, in the generator, a multi-scale localized feature fusion module and an effective channel-attention module are designed to acquire the multi-scale local detailed information of the skin lesion area. In addition, a global context extraction module in the bottleneck between the encoder and decoder of the generator is used to capture more global semantic features and spatial information about the lesion. After that, we use an adversarial training strategy to make the discriminator discern the generated labels and the segmentation prediction maps, which assists the generator in yielding more accurate segmentation maps. Our proposed model was trained and validated on three public skin lesion challenge datasets involving the ISIC2017, ISIC2018, and HAM10000, and the experimental results confirm that our proposed method provides a superior segmentation performance and outperforms several comparative methods.

Abstract A023: Immune-related diseases and skin cancer in a racially and ethnically diverse US-based population

Abstract Though the immune system plays a crucial role in skin cancer development, associations between immune-related diseases and skin cancer have not been well studied in racial and ethnic minorities. The goal of this cross-sectional study was to assess the relationship between various immune-related diseases and basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and cutaneous malignant melanoma (MM) diagnoses within the diverse “All of Us” Research Program cohort. It included 307,451 adult participants with electronic health record (EHR) data enrolled from 2017-2023. Participant EHRs were used to determine immune-related diseases and skin cancer diagnoses. Multivariate logistic regression analyses were adjusted for demographic characteristics, lifestyle factors such as smoking history, in addition to health insurance status, educational attainment, history of photosensitivity, history of organ transplant, as well as UV exposure at residence. R v4.0.5 was utilized to conduct the analysis. 8,107 participants with BCC, 4,102 with SCC and 2,461 with MM were identified. Personal history of any immune-related disease was significantly associated with all skin cancer types (odds ratio and 95% confidence intervals -- BCC: 1.27 [1.20-1.33]; SCC:1.38 [1.29-1.49]; MM: 1.55 [1.42-1.69]). Rheumatoid arthritis, hypothyroidism, type I diabetes, Crohn’s disease, and ulcerative colitis were each associated with the three skin cancer types. Multiple sclerosis, Sjogren’s syndrome, hyperthyroidism, dermatomyositis/polymyositis, vitiligo, and psoriasis were associated with at least one skin cancer. Systemic lupus, scleroderma, alopecia areata, and atopic dermatitis were not associated with any skin cancer. In non-White participants alone (n=133,144; 43.3%), history of any immune-related disease was similarly significantly associated with all three skin cancer types. These findings suggest that the history of several immune-related diseases is associated with skin cancer, including among racial/ethnic minorities, and thus increased skin cancer surveillance in these patient populations may be indicated. Citation Format: Erica M. Lin, Sara Ragi, Rachel Lim, Shirley Lin, Isabelle Moseley, Abrar Qureshi, Eunyoung Cho. Immune-related diseases and skin cancer in a racially and ethnically diverse US-based population [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A023.

A miniaturized dual band terahertz metamaterial based absorber as a biosensor for non-melanoma skin cancer diognostic

Early diagnosis of Non-melanoma skin cancers (NMSCs) is most important for successful treatment of the disease.The detection of NMSCs involves visual inspection or invasive method of detection by skin biopsy. Recently, terahertz spectroscopy has come into limelight for detection of biomarkers in low terahertz (THz) region in between 0.1 – 10 THz which will be in resonance with the biomolecules. This work entails in designing a microscale THz metamaterial absorber for discriminating the attributes between Non-melanoma skin cancerous skin and normal skin. The proposed absorber is composed of space filling curved aluminum layer over a polymide substrate. The absorber culminates its absorbance peak of 99.8 % at 0.503 THz and 99.5 % at 1.076 THz, revealing its dual band trait. Moreover, variation of refractive index of the medium from 1.3 to 1.4 shows shift in absorption peak with a sensitivity of 95.76 GHz/RIU and 100 GHz/RIU for first and second band respectively.

Empowering patients: leveraging the untapped potential of smartphone recordings in dermatology consultations.

During consultations, patients can be overwhelmed with new diagnoses, complex treatment plans, particularly when bad news is broken (such as a new skin cancer diagnosis). Patients may be unable to recall nuanced medical information, particularly if elderly, attending on their own, with lower literacy, with impaired sensory abilities and where English may not be their native language. Given the ubiquity of smartphones, recording conversations during consultations—with the doctor’s consent—has become an accessible tool for patients. Allowing patients to record their consultations can empower them, enhance recall, and reduce decisional regret, particularly in emotionally charged settings such as skin cancer clinics where cognitive processing may be impaired.

The use of game-based learning strategies for dermatology and dermoscopy education: a cross-sectional study by the International Dermoscopy Society (IDS) survey

Abstract Introduction Dermoscopy is a valuable tool in the diagnosis of various skin conditions. Dermoscopy increases the sensitivity and specificity for skin cancer diagnosis, as well as infectious, inflammatory, and hair diseases. However, mastering dermoscopy intricacies poses challenges. In this context, innovative educational methods are sought, including game-based learning (GBL) strategies. Objective To describe current perceptions, knowledge and usage of GBL strategies in dermoscopy education; and identify strengths and challenges to enhance their utilization. Methods This was a cross-sectional study conducted by the International Dermoscopy Society (IDS). A web-based survey with 25-questions was distributed among the IDS members between October 2022 and April 2023. Responses were collected and analyzed using SPSS Statistics 26. Results A total of 801 responses were received. Of these, 46.6% responders were unfamiliar with gamification and serious games. Among those acquainted, 56.3% reported using GBL strategies for education. Younger participants were more likely to use GBL strategies (p = 0.015). Participants familiar with GBL believed it enhances medical education (78.5%) but not as a sole replacement for traditional methods (96%). For dermoscopy education, 22.2% had used GBL strategies, with Kahoot (35.5%) and You Dermoscopy (24.1%) being the most commonly used. Respondents found gaming strategies to be fun (95%), motivating (91%), and valuable for e-learning (94%). Conclusion Results from this survey demonstrate favorable perception towards GBL strategies in dermatology education, including dermoscopy. While there are ongoing challenges in validation, GBL strategies are promising and valuable tools that can aid the learning and teaching experience. Addressing implementation barriers and validating existing games could optimize GBL's impact on dermatology education.

Skin cancer diagnosis associated with asthma and hay fever: a nationwide cross-sectional study.

Asthma is a respiratory disorder caused by airway inflammation which may worsen after allergen exposure. Recent cohort studies demonstrate a positive association between skin cancer and asthma or hay fever (allergy to outdoor allergens such as pollen). Nationally-representative data for adults in the United States remains limited. We aimed to characterize skin cancer prevalence among individuals in the United States who have asthma or hay fever. To achieve this aim, we extracted nationwide cross-sectional data from 16,277 adult participants (total survey-weighted sample = 174,765,931) of the Third National Health and Nutrition Examination Survey from 1988 to 1994. This study uses survey-weighted regression to compare the nationwide prevalence of skin cancer among participants with or without a history of asthma or hay fever. Sensitivity analysis examined the influence of sex, 25-hydroxyvitamin D, chronic bronchitis or emphysema, geographical region, urban proximity, and oral glucocorticoid use. Of the included participants, the age-adjusted prevalence of skin cancer was 7.2%, similar to national estimates. Skin cancer prevalence was higher among participants who had asthma with hay fever (adjusted prevalence ratio, 1.79; 95% confidence interval, 1.16, 2.76), but not among participants with asthma only or hay fever only. Similarly, skin cancer prevalence was higher for those with asthma and positive pollen allergen skin prick testing (SPT), but not for those with hay fever and positive pollen SPT. No association was noted between skin cancer and wheezing triggered by pollen. Hay fever or immunoglobulin-E sensitization to pollen may increase skin cancer prevalence among individuals with a history of asthma.

Skin cancer identification utilizing deep learning: A survey

AbstractMelanoma, a highly prevalent and lethal form of skin cancer, has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the early identification of melanoma. Despite their high performance, relying solely on an image classifier undermines the credibility of the application and makes it difficult to understand the rationale behind the model's predictions highlighting the need for Explainable AI (XAI). This study provides a survey on skin cancer identification using DL techniques utilized in studies from 2017 to 2024. Compared to existing survey studies, the authors address the latest related studies covering several public skin cancer image datasets and focusing on segmentation, classification based on convolutional neural networks and vision transformers, and explainability. The analysis and the comparisons of the existing studies will be beneficial for the researchers and developers in this area, to identify the suitable techniques to be used for automated skin cancer image classification. Thereby, the survey findings can be used to implement support applications advancing the skin cancer diagnosis process.

A Hybrid Convolutional Neural Network Model for the Classification of Multi‐Class Skin Cancer

ABSTRACTSkin cancer is a significant public health issue, making accurate and early diagnosis crucial. This study proposes a novel and efficient hybrid deep‐learning model for accurate skin cancer diagnosis. The model first employs DeepLabV3+ for precise segmentation of skin lesions in dermoscopic images. Feature extraction is then carried out using three pretrained models: MobileNetV2, EfficientNetB0, and DenseNet201 to ensure balanced performance and robust feature learning. These extracted features are then concatenated, and the ReliefF algorithm is employed to select the most relevant features. Finally, obtained features are classified into eight categories: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, melanocytic nevus, squamous cell carcinoma, and vascular lesion using the kNN algorithm. The proposed model achieves an F1 score of 93.49% and an accuracy of 94.42% on the ISIC‐2019 dataset, surpassing the best individual model, EfficientNetB0, by 1.20%. Furthermore, the evaluation of the PH2 dataset yielded an F1 score of 94.43% and an accuracy of 94.44%, confirming its generalizability. These findings signify the potential of the proposed model as an expedient, accurate, and valuable tool for early skin cancer detection. They also indicate combining different CNN models achieves superior results over the results obtained from individual models.

Skin Cancer Classification Using Fine-Tuned Transfer Learning of DENSENET-121

Skin cancer diagnosis greatly benefits from advanced machine learning techniques, particularly fine-tuned deep learning models. In our research, we explored the impact of traditional machine learning and fine-tuned deep learning approaches on prediction accuracy. Our findings reveal significant improvements in predictability and accuracy with fine-tuning, particularly evident in deep learning models. The CNN, SVM, and Random Forest Classifier achieved high accuracy. However, fine-tuned deep learning models such as EfficientNetB0, ResNet34, VGG16, Inception _v3, and DenseNet121 demonstrated superior performance. To ensure comparability, we fine-tuned these models by incorporating additional layers, including one flatten layer and three densely interconnected layers. These layers play a crucial role in enhancing model efficiency and performance. The flatten layer preprocesses multidimensional feature maps, facilitating efficient information flow, while subsequent dense layers refine feature representations, capturing intricate patterns and relationships within the data. Leveraging LeakyReLU activation functions in the dense layers mitigates the vanishing gradient problem and promotes stable training. Finally, the output dense layer with a sigmoid activation function simplifies decision making for healthcare professionals by providing binary classification output. Our study underscores the significance of incorporating additional layers in fine-tuned neural network models for skin cancer classification, offering improved accuracy and reliability in diagnosis.