Improving outcomes in patients with melanoma: strategies to ensure an early diagnosis

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.

Solutions for Addressing the Dermatologist Shortage in Rural Canada: A Review of the Literature

In Canada, there is a maldistribution of dermatologists, with as many as 5.6 dermatologists per 100,000 population in urban areas and as low as 0.6 per 100,000 in rural areas. Considering trends of dermatologists to work in group practices in urban areas, and the low number of rural dermatologists, one solution may be to incentivize dermatologists to practice rurally. Several solutions using the following themes are discussed: dermatology program-specific incentives, dermatology practice-specific incentives, and other indirect incentives. The low number of dermatologists in rural areas in Canada is concerning and has negative consequences for access to care for patients in rural areas, ultimately resulting in worse patient outcomes. Future research is needed to evaluate the impact of these initiatives and assess future access to dermatological care.

MRI Detection of Lymph Node Metastasis through Molecular Targeting of C-C Chemokine Receptor Type 2 and Monocyte Hitchhiking

Biopsy is the clinical standard for diagnosing lymph node (LN) metastasis, but it is invasive and poses significant risk to patient health. Magnetic resonance imaging (MRI) has been utilized as a noninvasive alternative but is limited by low sensitivity, with only ∼35% of LN metastases detected, as clinical contrast agents cannot discriminate between healthy and metastatic LNs due to nonspecific accumulation. Nanoparticles targeted to the C-C chemokine receptor 2 (CCR2), a biomarker highly expressed in metastatic LNs, have the potential to guide the delivery of contrast agents, improving the sensitivity of MRI. Additionally, cancer cells in metastatic LNs produce monocyte chemotactic protein 1 (MCP1), which binds to CCR2+ inflammatory monocytes and stimulates their migration. Thus, the molecular targeting of CCR2 may enable nanoparticle hitchhiking onto monocytes, providing an additional mechanism for metastatic LN targeting and early detection. Hence, we developed micelles incorporating gadolinium (Gd) and peptides derived from the CCR2-binding motif of MCP1 (MCP1-Gd) and evaluated the potential of MCP1-Gd to detect LN metastasis. When incubated with migrating monocytes in vitro, MCP1-Gd transport across lymphatic endothelium increased 2-fold relative to nontargeting controls. After administration into mouse models with initial LN metastasis and recurrent LN metastasis, MCP1-Gd detected metastatic LNs by increasing MRI signal by 30-50% relative to healthy LNs. Furthermore, LN targeting was dependent on monocyte hitchhiking, as monocyte depletion decreased accumulation by >70%. Herein, we present a nanoparticle contrast agent for MRI detection of LN metastasis mediated by CCR2-targeting and demonstrate the potential of monocyte hitchhiking for enhanced nanoparticle delivery.

SkinLesNet: Classification of Skin Lesions and Detection of Melanoma Cancer Using a Novel Multi-Layer Deep Convolutional Neural Network

Skin cancer is a widespread disease that typically develops on the skin due to frequent exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer accounts for a significant proportion of all new cancer diagnoses worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of morphological variety and indistinguishable characteristics across skin malignancies. Recently, deep learning models have been used in the field of image-based skin-lesion diagnosis and have demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep convolutional neural network termed SkinLesNet was built in this study. The dataset used in this study was extracted from the PAD-UFES-20 dataset and was augmented. The PAD-UFES-20-Modified dataset includes three common forms of skin lesions: seborrheic keratosis, nevus, and melanoma. To comprehensively assess SkinLesNet's performance, its evaluation was expanded beyond the PAD-UFES-20-Modified dataset. Two additional datasets, HAM10000 and ISIC2017, were included, and SkinLesNet was compared to the widely used ResNet50 and VGG16 models. This broader evaluation confirmed SkinLesNet's effectiveness, as it consistently outperformed both benchmarks across all datasets.

Prognostic gene biomarkers for c-Src inhibitor Si162 sensitivity in melanoma cells

Background/aim

Early detection and treatment are crucial in combating malignant melanoma. Src is an important therapeutic target in melanoma due to its association with cancer progression. However, developing effective Src-targeting drugs remains challenging and personalized medicine relies on biomarkers and targeted therapies for precise and effective treatment. This study focuses on Si162, a newly synthesized c-Src inhibitor, to identify reliable biomarkers for predicting Si162 sensitivity and explore associated biological characteristics and pathways in melanoma cells.

Materials and methods

Primary melanoma cells (M1, M21, M24, M84, M133, M307, and M2025) were obtained from patients diagnosed with melanoma. Si162 cytotoxicity tests were performed using luminescent adenosine triphosphate detection and the half-maximal inhibitory concentration (IC50) values were calculated. Gene expression profiles were analyzed using microarray-based gene expression data. Differentially expressed genes between the resistant and sensitive groups were identified using Pearson correlation analysis. Gene coexpression, interactions, and pathways were investigated through clustering, network, and pathway analyses. Biological functions were examined using the Database for Annotation, Visualization, and Integrated Discovery. Molecular pathways associated with different responses to Si162 were identified using gene set enrichment analysis. The gene expressions were validated using reverse transcription-quantitative polymerase chain reaction.

Results

The cells revealed significant differences in response to Si162 based on the IC50 values (p < 0.05). A total of 36 differentially expressed genes associated with Si162 susceptibility were identified. Distinct expression patterns between the sensitive and resistant groups were observed in 9 genes (LRBA, MGMT, CAND1, ADD1, SETD2, CNTN6, FGF18, C18orf25, and RPL13). Coexpression among the differentially expressed genes was highlighted, and 9 genes associated with molecular pathways, including EMT, transforming growth factor-beta (TGF-β) signaling, and ribosomal protein synthesis, between groups. Genes involved in dysregulated immune response were observed in the resistant group. The involvement of 5 genes (ADD1, CNTN6, FGF18, C18orf25, and RPL13) in Si162 resistance was confirmed through qRT-PCR validation.

Conclusion

These findings contribute to our understanding of the underlying biological differences among melanoma cells and suggest potential biomarkers and pathways associated with Si162 response and resistance.

Role of galectin-3 in the elastic response of radial growth phase melanoma cancer cells

Melanoma is originated from the malignant transformation of the melanocytes and is characterized by a high rate of invasion, the more serious stage compromising deeper layers of the skin and eventually leading to the metastasis. A high mortality due to melanoma lesion persists because most of melanoma lesions are detected in advanced stages, which decreases the chances of survival. The identification of the principal mechanics implicated in the development and progression of melanoma is essential to devise new early diagnosis strategies. Cell mechanics is related with a lot of cellular functions and processes, for instance motility, differentiation, migration and invasion. In particular, the elastic modulus (Young's modulus) is a very explored parameter to describe the cell mechanical properties; most cancer cells reported in the literature smaller elasticity modulus. In this work, we show that the elastic modulus of melanoma cells lacking galectin-3 is significantly lower than those of melanoma cells expressing galectin-3. More interestingly, the gradient of elastic modulus in cells from the nuclear region towards the cell periphery is more pronounced in shGal3 cells. RESEARCH HIGHLIGHTS: AFM imaging and force spectroscopy were used to investigate the morphology and elasticity properties of healthy HaCaT cells and melanoma cells WM1366, with (shSCR) and without (shGal3) expression of galectin-3. It is shown the effect of galectin-3 protein on the elastic properties of cells: the cells without expression of galectin-3 presents lower elastic modulus. By the results, we suggest here that galectin-3 could be used as an effective biomarker of malignancy in both melanoma diagnostic and prognosis.

Melanoma Management: From Epidemiology to Treatment and Latest Advances

Melanoma is the deadliest skin cancer, whose morbidity and mortality indicators show an increasing trend worldwide. In addition to its great heterogeneity, melanoma has a high metastatic potential, resulting in very limited response to therapies currently available, which were restricted to surgery, radiotherapy and chemotherapy for many years. Advances in knowledge about the pathophysiological mechanisms of the disease have allowed the development of new therapeutic classes, such as immune checkpoint and small molecule kinase inhibitors. However, despite the incontestable progress in the quality of life and survival rates of the patients, effectiveness is still far from desired. Some adverse side effects and resistance mechanisms are the main barriers. Thus, the search for better options has resulted in many clinical trials that are now investigating new drugs and/or combinations. The low water solubility of drugs, low stability and rapid metabolism limit the clinical potential and therapeutic use of some compounds. Thus, the research of nanotechnology-based strategies is being explored as the basis for the broad application of different types of nanosystems in the treatment of melanoma. Future development focus on challenges understanding the mechanisms that make these nanosystems more effective.

How to Treat Melanoma? The Current Status of Innovative Nanotechnological Strategies and the Role of Minimally Invasive Approaches like PTT and PDT

Melanoma is the most aggressive type of skin cancer, the incidence and mortality of which are increasing worldwide. Its extensive degree of heterogeneity has limited its response to existing therapies. For many years the therapeutic strategies were limited to surgery, radiotherapy, and chemotherapy. Fortunately, advances in knowledge have allowed the development of new therapeutic strategies. Despite the undoubted progress, alternative therapies are still under research. In this context, nanotechnology is also positioned as a strong and promising tool to develop nanosystems that act as drug carriers and/or light absorbents to potentially improve photothermal and photodynamic therapies outcomes. This review describes the latest advances in nanotechnology field in the treatment of melanoma from 2011 to 2022. The challenges in the translation of nanotechnology-based therapies to clinical applications are also discussed. To sum up, great progress has been made in the field of nanotechnology-based therapies, and our understanding in this field has greatly improved. Although few therapies based on nanoparticulate systems have advanced to clinical trials, it is expected that a large number will come into clinical use in the near future. With its high sensitivity, specificity, and multiplexed measurement capacity, it provides great opportunities to improve melanoma treatment, which will ultimately lead to enhanced patient survival rates.

Untangling Classification Methods for Melanoma Skin Cancer

Skin cancer is the most common cancer in the USA, and it is a leading cause of death worldwide. Every year, more than five million patients are newly diagnosed in the USA. The deadliest and most serious form of skin cancer is called melanoma. Skin cancer can affect anyone, regardless of skin color, race, gender, and age. The diagnosis of melanoma has been done by visual examination and manual techniques by skilled doctors. It is a time-consuming process and highly prone to error. The skin images captured by dermoscopy eliminate the surface reflection of skin and give a better visualization of deeper levels of the skin. However, the existence of many artifacts and noise such as hair, veins, and water residue make the lesion images very complex. Due to the complexity of images, the border detection, feature extraction, and classification process are challenging. Without a proper mechanism, it is hard to identify and predict melanoma at an early stage. Therefore, there is a need to provide precise details, identify early skin cancer, and classify skin cancer with appropriate sensitivity and precision. This article aims to review and analyze two deep neural network-based classification algorithms (convolutional neural network, CNN; recurrent neural network, RNN) and a decision tree-based algorithm (XG-Boost) on skin lesion images (ISIC dataset) and find which of these provides the best classification performance metric. Also, the performance of algorithms is compared using six different metrics—loss, accuracy, precision, recall, F1 score, and ROC.

Analysis of the ISIC image datasets: Usage, benchmarks and recommendations

The International Skin Imaging Collaboration (ISIC) datasets have become a leading repository for researchers in machine learning for medical image analysis, especially in the field of skin cancer detection and malignancy assessment. They contain tens of thousands of dermoscopic photographs together with gold-standard lesion diagnosis metadata. The associated yearly challenges have resulted in major contributions to the field, with papers reporting measures well in excess of human experts. Skin cancers can be divided into two major groups - melanoma and non-melanoma. Although less prevalent, melanoma is considered to be more serious as it can quickly spread to other organs if not treated at an early stage. In this paper, we summarise the usage of the ISIC dataset images and present an analysis of yearly releases over a period of 2016 - 2020. Our analysis found a significant number of duplicate images, both within and between the datasets. Additionally, we also noted duplicates spread across testing and training sets. Due to these irregularities, we propose a duplicate removal strategy and recommend a curated dataset for researchers to use when working on ISIC datasets. Given that ISIC 2020 focused on melanoma classification, we conduct experiments to provide benchmark results on the ISIC 2020 test set, with additional analysis on the smaller ISIC 2017 test set. Testing was completed following the application of our duplicate removal strategy and an additional data balancing step. As a result of removing 14,310 duplicate images from the training set, our benchmark results show good levels of melanoma prediction with an AUC of 0.80 for the best performing model. As our aim was not to maximise network performance, we did not include additional steps in our experiments. Finally, we provide recommendations for future research by highlighting irregularities that may present research challenges. A list of image files with reference to the original ISIC dataset sources for the recommended curated training set will be shared on our GitHub repository (available at www.github.com/mmu-dermatology-research/isic_duplicate_removal_strategy).

Optimal surveillance strategies for patients with stage 1 cutaneous melanoma post primary tumour excision: three systematic reviews and an economic model

BACKGROUND

Malignant melanoma is the fifth most common cancer in the UK, with rates continuing to rise, resulting in considerable burden to patients and the NHS.

OBJECTIVES

The objectives were to evaluate the effectiveness and cost-effectiveness of current and alternative follow-up strategies for stage IA and IB melanoma.

REVIEW METHODS

Three systematic reviews were conducted. (1) The effectiveness of surveillance strategies. Outcomes were detection of new primaries, recurrences, metastases and survival. Risk of bias was assessed using the Cochrane Collaboration's Risk-of-Bias 2.0 tool. (2) Prediction models to stratify by risk of recurrence, metastases and survival. Model performance was assessed by study-reported measures of discrimination (e.g. D-statistic, Harrel's c-statistic), calibration (e.g. the Hosmer-Lemeshow 'goodness-of-fit' test) or overall performance (e.g. Brier score, R ²). Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). (3) Diagnostic test accuracy of fine-needle biopsy and ultrasonography. Outcomes were detection of new primaries, recurrences, metastases and overall survival. Risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Review data and data from elsewhere were used to model the cost-effectiveness of alternative surveillance strategies and the value of further research.

RESULTS

(1) The surveillance review included one randomised controlled trial. There was no evidence of a difference in new primary or recurrence detected (risk ratio 0.75, 95% confidence interval 0.43 to 1.31). Risk of bias was considered to be of some concern. Certainty of the evidence was low. (2) Eleven risk prediction models were identified. Discrimination measures were reported for six models, with the area under the operating curve ranging from 0.59 to 0.88. Three models reported calibration measures, with coefficients of ≥ 0.88. Overall performance was reported by two models. In one, the Brier score was slightly better than the American Joint Committee on Cancer scheme score. The other reported an R ² of 0.47 (95% confidence interval 0.45 to 0.49). All studies were judged to have a high risk of bias. (3) The diagnostic test accuracy review identified two studies. One study considered fine-needle biopsy and the other considered ultrasonography. The sensitivity and specificity for fine-needle biopsy were 0.94 (95% confidence interval 0.90 to 0.97) and 0.95 (95% confidence interval 0.90 to 0.97), respectively. For ultrasonography, sensitivity and specificity were 1.00 (95% confidence interval 0.03 to 1.00) and 0.99 (95% confidence interval 0.96 to 0.99), respectively. For the reference standards and flow and timing domains, the risk of bias was rated as being high for both studies. The cost-effectiveness results suggest that, over a lifetime, less intensive surveillance than recommended by the National Institute for Health and Care Excellence might be worthwhile. There was considerable uncertainty. Improving the diagnostic performance of cancer nurse specialists and introducing a risk prediction tool could be promising. Further research on transition probabilities between different stages of melanoma and on improving diagnostic accuracy would be of most value.

LIMITATIONS

Overall, few data of limited quality were available, and these related to earlier versions of the American Joint Committee on Cancer staging. Consequently, there was considerable uncertainty in the economic evaluation.

CONCLUSIONS

Despite adoption of rigorous methods, too few data are available to justify changes to the National Institute for Health and Care Excellence recommendations on surveillance. However, alternative strategies warrant further research, specifically on improving estimates of incidence, progression of recurrent disease; diagnostic accuracy and health-related quality of life; developing and evaluating risk stratification tools; and understanding patient preferences.

STUDY REGISTRATION

This study is registered as PROSPERO CRD42018086784.

FUNDING

This project was funded by the National Institute for Health Research Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol 25, No. 64. See the NIHR Journals Library website for further project information.

"Let's Talk about Skin Cancer": Examining Association between Family Communication about Skin Cancer, Perceived Risk, and Sun Protection Behaviors

Family communication about skin cancer risk may motivate protective behaviors. However, it is unclear how widespread such communication might be. In this study, we describe prevalence and patterns (across environmental, personal, and behavioral factors) of family communication about skin cancer across N = 600 diverse (79% female, 48% Hispanic, 44% non-Hispanic White) primary care patients from Albuquerque, New Mexico, a geographical location with year-round sun exposure. Over half reported discussing general cancer (77%) and skin cancer risks (66%) with their families. The most frequent target of skin cancer risk communication included doctors (54%), followed by friends/coworkers (49%), spouse/partner (43%), other family members (38%), sisters (36%), mothers (36%), daughters (33%), sons (32%), father (24%), and brothers (22%). On average, participants reported having talked to three family members about skin cancer risks. The most frequently discussed content of skin cancer risk communication was the use of sun protection (89%), followed by the personal risk of skin cancer (68%), who had skin cancer in the family (60%), family risk of skin cancer (59%), time of sun exposure (57%), and skin cancer screening (57%). A family or personal history of cancer, higher perceived risk, higher health literacy, being non-Hispanic, having higher education or income, and proactive sun protective behavior were associated with greater family communication about general cancer and skin cancer risks. These study findings have implications for interventions that encourage discussions about skin cancer risk, sun protection, and skin cancer screening that lead to adoption of sun-safe behaviors.

Accessing Mole-Scanning through Community Pharmacy: A Pilot Service in Collaboration with Dermatology Specialists

Early identification and treatment of malignant melanoma is crucial to prevent mortality. The aim of this work was to describe the uptake, profile of users and service outcomes of a mole scanning service in the community pharmacy setting in the UK. In addition, health care costs saved from the perspective of general practice were estimated. The service allowed patients to have concerning skin lesions scanned with a dermatoscopy device which were analyzed remotely by clinical dermatology specialists in order to provide recommendations for the patient. Patients were followed up to ascertain the clinical outcome. Data were analyzed for 6355 patients and 9881 scans across 50 community pharmacies. The majority of the scans required no further follow-up (n = 8763, 88.7%). Diagnosis was confirmed for 70.4% (n = 757/1118) of scans where patients were recommended to seek further medical attention. Of these, 44.3% were ultimately defined as normal (n = 335) and 6.2% as malignant melanoma (n = 47/757). An estimated 0.7% of scans taken as part of the service led to a confirmed diagnosis of malignant melanoma. This service evaluation has shown that a mole scanning service available within community pharmacies is effective at triaging patients and ultimately playing a part in identifying diagnoses of malignant melanoma.

The Impact and Consequences of SARS-CoV-2 Pandemic on a Single University Dermatology Outpatient Clinic in Germany

The pandemic outbreak of coronavirus disease 2019 (COVID-19) affects health care systems globally and leads to other challenges besides infection and its direct medical consequences. The aim of this study was to investigate the impact of SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) pandemic on the university dermatology outpatient clinic (UDOC) of the Technical University of Munich, Germany. We analyzed datasets from 2015 until 2020 extracted from the hospital information system database and our documented outpatient files regarding patient numbers, gender, age, and diagnoses. In 2020, case numbers of outpatient care declined significantly (p = 0.021) compared to previous years and was related to the timing of political announcements answering SARS-CoV-2 pandemic. Additionally, during calendar week 10 to 15—the peak time of the spread of COVID-19 in Germany—the proportion of patients missing their consultation was significantly higher in 2020 than in 2019 (22.4% vs. 12.4%; p < 0.001). Gender-associated differences regarding absences were not detected, but patients aged 85 years or older were significantly more likely to miss their consultation compared to all other age groups (p = 0.002). Regarding different disease clusters, patients with chronic inflammatory skin diseases and infectious and malignant diseases were more likely to miss their consultation (p = 0.006). Noticeably, less patients with malignant diseases, and particularly malignant melanoma, were registered during this pandemic. Our data support the hypothesis that medically constructive prioritization might not be implemented properly by patients themselves. Identifying missed patients and catching up on their medical care apart from COVID-19 will pose an enormous challenge for health care systems globally.

Distinguishing melanocytic nevi from melanomas using static and dynamic infrared thermal imaging

BACKGROUND

The incidence rates of melanoma have risen to worrying levels over the last decade. Delayed diagnosis, due to faults on the detection stage, indicates the necessity of new aiding diagnosis techniques. Since metabolic activity is highly connected to neoplasia formation, a detection technique that focuses its results on vascular responses, as Infrared thermal (IRT), seems to be a viable option.

MATERIALS AND METHODS

Static and dynamic (cooling) thermal images of melanoma and melanocytic nevi lesions were collected and analysed to retrieve thermal parameters characteristic of this skin lesion types. The steady-state and dynamic variables were tested separately with different machine learning classifiers to verify whether the distinction of melanoma and nevi lesions was achievable.

RESULTS

The differentiation of both types of skin tumours was doable, achieving an accuracy of 84.2% and a sensitivity of 91.3% with the implementation of a learner based on support vector machines and an input vector composed by static variables.

CONCLUSION

The use of IRT for skin tumour classification is achievable, but some improvement is needed to raise the metrics of sensitivity and specificity. For future work, it is recommended the study of dynamic parameters for the classification of other types of skin neoplasia.

Melanoma Masquerading as a Zosteriform Rash

BACKGROUND Primary care physicians and internal medicine specialists frequently encounter a variety of rashes. Many of these cases look and feel typical of common entities, resulting in the potential for misdiagnosis. CASE REPORT This is a case of a zosteriform rash where the surprising true diagnosis of metastatic melanoma was confirmed with bedside skin punch biopsy. Possible mechanisms involve direct cutaneous injury, neuronal, and dorsal root ganglia involvement in metastases. CONCLUSIONS Skin biopsy is indispensable especially when there is a lack of clinical response or deterioration in the clinical condition. The pathophysiology of zosteriform metastasis is unclear.