A protocol for annotation of total body photography for machine learning to analyze skin phenotype and lesion classification.

Introduction: Artificial Intelligence (AI) has proven effective in classifying skin cancers using dermoscopy images. In experimental settings, algorithms have outperformed expert dermatologists in classifying melanoma and keratinocyte cancers. However, clinical application is limited when algorithms are presented with 'untrained' or out-of-distribution lesion categories, often misclassifying benign lesions as malignant, or misclassifying malignant lesions as benign. Another limitation often raised is the lack of clinical context (e.g., medical history) used as input for the AI decision process. The increasing use of Total Body Photography (TBP) in clinical examinations presents new opportunities for AI to perform holistic analysis of the whole patient, rather than a single lesion. Currently there is a lack of existing literature or standards for image annotation of TBP, or on preserving patient privacy during the machine learning process. Methods: This protocol describes the methods for the acquisition of patient data, including TBP, medical history, and genetic risk factors, to create a comprehensive dataset for machine learning. 500 patients of various risk profiles will be recruited from two clinical sites (Australia and Spain), to undergo temporal total body imaging, complete surveys on sun behaviors and medical history, and provide a DNA sample. This patient-level metadata is applied to image datasets using DICOM labels. Anonymization and masking methods are applied to preserve patient privacy. A two-step annotation process is followed to label skin images for lesion detection and classification using deep learning models. Skin phenotype characteristics are extracted from images, including innate and facultative skin color, nevi distribution, and UV damage. Several algorithms will be developed relating to skin lesion detection, segmentation and classification, 3D mapping, change detection, and risk profiling. Simultaneously, explainable AI (XAI) methods will be incorporated to foster clinician and patient trust. Additionally, a publicly released dataset of anonymized annotated TBP images will be released for an international challenge to advance the development of new algorithms using this type of data. Conclusion: The anticipated results from this protocol are validated AI-based tools to provide holistic risk assessment for individual lesions, and risk stratification of patients to assist clinicians in monitoring for skin cancer.

Prognostic Value of the Neutrophil-to-lymphocyte Ratio, Platelet-to- lymphocyte Ratio and Monocyte-to-lymphocyte Ratio in Melanoma Patients: A Cohort Study.

The prognostic value of the neutrophil-lymphocyte ratio, platelet-lymphocyte ratio and monocyte-lymphocyte ratio in patients with melanoma has yielded controversial results in the literature. A retrospective single-centre cohort study was conducted from 1998 to 2020, including patients diagnosed with invasive melanoma. A total of 2,721 patients were included in the study. The median follow-up was 8.23 years (IQR 4.41-13.25). The median baseline neutrophil- lymphocyte ratio, platelet-lymphocyte ratio and monocyte-lymphocyte ratio values increased significantly (p < 0.001) with the increasing American Joint Committee on Cancer stage. The optimal cut-off values for neutrophil-lymphocyte ratio, platelet-lymphocyte ratio and monocyte-lymphocyte ratio were determined as 2.1, 184 and 0.2, respectively. In the multivariate analysis, high levels of neutrophil-lymphocyte ratio (≥ 2.1), platelet-lymphocyte ratio (≥ 184) and monocyte-lymphocyte ratio (≥ 0.2) were independently associated with significantly shorter melanoma-specific survival (neutrophil-lymphocyte ratio: HR 1.30, 95% CI 1.06-1.60, p = 0.013; platelet-lymphocyte ratio: HR 1.37, 95% CI 1.06-1.76, p = 0.014; monocyte- lymphocyte ratio: HR 1.29, 95% CI 1.05-1.58, p = 0.015) and overall survival (neutrophil-lymphocyte ratio: HR 1.39, 95% CI 1.19-1.64, p < 0.001; platelet- lymphocyte ratio: HR 1.44, 95% CI 1.19-1.74, p < 0.001; monocyte-lymphocyte ratio: HR 1.42, 95% CI 1.21-1.66, p < 0.001). High levels of neutrophil- lymphocyte ratio and monocyte-lymphocyte ratio were also associated with poor relapse-free survival, while platelet-lymphocyte ratio was not. In conclusion, baseline neutrophil-lymphocyte ratio, platelet-lymphocyte ratio and monocyte-lymphocyte ratio were identified as independent predictors for the prognosis of melanoma.

Sentinel lymph node risk prognostication in primary cutaneous melanoma through tissue-based profiling, potentially redefining the need for sentinel lymph node biopsy.

PURPOSE OF REVIEW: The role of Sentinel Lymph Node Biopsy (SLNB) is pivotal in the contemporary staging of cutaneous melanoma. In this review, we examine advanced molecular testing platforms like gene expression profiling (GEP) and immunohistochemistry (IHC) as tools for predicting the prognosis of sentinel lymph nodes. We compare these innovative approaches with traditional staging assessments. Additionally, we delve into the shared genetic and protein markers between GEP and IHC tests and their relevance to melanoma biology, exploring their prognostic and predictive characteristics. Finally, we assess alternative methods to potentially obviate the need for SLNB altogether. RECENT FINDINGS: Progress in adjuvant melanoma therapy has diminished the necessity of Sentinel Lymph Node Biopsy (SLNB) while underscoring the importance of accurately identifying high-risk stage I and II melanoma patients who may benefit from additional anti-tumor interventions. The clinical application of testing through gene expression profiling (GEP) or immunohistochemistry (IHC) is gaining traction, with platforms such as DecisionDx, Merlin Assay (CP-GEP), MelaGenix GEP, and Immunoprint coming into play. Currently, extensive validation studies are in progress to incorporate routine molecular testing into clinical practice. However, due to significant methodological limitations, widespread clinical adoption of tissue-based molecular testing remains elusive at present. SUMMARY: While various tissue-based molecular testing platforms have the potential to stratify the risk of sentinel lymph node positivity (SLNP), most suffer from significant methodological deficiencies, including limited sample size, lack of prospective validation, and limited correlation with established clinicopathological variables. Furthermore, the genes and proteins identified by individual gene expression profiling (GEP) or immunohistochemistry (IHC) tests exhibit minimal overlap, even when considering the most well-established melanoma mutations. However, there is hope that the ongoing prospective trial for the Merlin Assay may safely reduce the necessity for SLNB procedures if successful. Additionally, the MelaGenix GEP and Immunoprint tests could prove valuable in identifying high-risk stage I-II melanoma patients and potentially guiding their selection for adjuvant therapy, thus potentially reducing the need for SLNB. Due to the diverse study designs employed, effective comparisons between GEP or IHC tests are challenging, and to date, there is no study directly comparing the clinical utility of these respective GEP or IHC tests.

Dermatoscopic patterns of cutaneous metastases: A multicentre cross-sectional study of the International Dermoscopy Society.

BACKGROUND: The detection of cutaneous metastases (CMs) from various primary tumours represents a diagnostic challenge. OBJECTIVES: Our aim was to evaluate the general characteristics and dermatoscopic features of CMs from different primary tumours. METHODS: Retrospective, multicentre, descriptive, cross-sectional study of biopsy-proven CMs. RESULTS: We included 583 patients (247 females, median age: 64 years, 25%-75% percentiles: 54-74 years) with 632 CMs, of which 52.2% (n = 330) were local, and 26.7% (n = 169) were distant. The most common primary tumours were melanomas (n = 474) and breast cancer (n = 59). Most non-melanoma CMs were non-pigmented (n = 151, 95.6%). Of 169 distant metastases, 54 (32.0%) appeared on the head and neck region. On dermatoscopy, pigmented melanoma metastases were frequently structureless blue (63.6%, n = 201), while amelanotic metastases were typified by linear serpentine vessels and a white structureless pattern. No significant difference was found between amelanotic melanoma metastases and CMs of other primary tumours. CONCLUSIONS: The head and neck area is a common site for distant CMs. Our study confirms that most pigmented melanoma metastasis are structureless blue on dermatoscopy and may mimic blue nevi. Amelanotic metastases are typified by linear serpentine vessels and a white structureless pattern, regardless of the primary tumour.

European consensus-based interdisciplinary guideline for diagnosis, treatment and prevention of actinic keratoses, epithelial UV-induced dysplasia and field cancerization on behalf of European Association of Dermato-Oncology, European Dermatology Forum, European Academy of Dermatology and Venereology and Union of Medical Specialists (Union Européenne des Médecins Spécialistes).

A collaboration of multidisciplinary experts from the European Association of Dermato-Oncology, the European Dermatology Forum, the European Academy of Dermatology and Venereology, and the European Union of Medical Specialists was formed to develop European recommendations on AK diagnosis and treatment, based on current literature and expert consensus. This guideline addresses the epidemiology, diagnostics, risk stratification and treatments in immunocompetent as well as immunosuppressed patients. Actinic keratoses (AK) are potential precursors of cutaneous squamous cell carcinoma (cSCC) and display typical histopathologic and immunohistochemical features of this malignancy in an early stage. They can develop into cSSC in situ and become invasive in a low percentage of cases. AK is the most frequent neoplasia in white populations, frequently occurring within a cancerous field induced by ultraviolet radiation. Since it cannot be predicted, which lesion will progress to cSCC and when treatment is usually recommended. The diagnosis of AK and field cancerization is made by clinical examination. Dermatoscopy, confocal microscopy, optical coherence tomography or line-field confocal-OCT can help in the differential diagnosis of AK and other skin neoplasms. A biopsy is indicated in clinically and/or dermatoscopically suspicious and/or treatment-refractory lesions. The choice of treatment depends on patients' and lesion characteristics. For single non-hyperkeratotic lesions, the treatment can be started upon patient's request with destructive treatments or topical treatments. For multiple lesions, field cancerization treatment is advised with topical treatments and photodynamic therapy. Preventive measures such as sun protection, self-examination and repeated field cancerization treatments of previously affected skin areas in high-risk patients are advised.

Restrospective reappraisal of the prognostic classification of spitzoid melanocytic neoplasms after BRAF and NRAS mutation characterisation: a single institution experience.

AIMS: The current WHO classification of melanocytic tumours excludes neoplasms showing BRAF or NRAS mutations from the Spitz category. This study aimed to review and reclassify atypical melanocytic tumours with spitzoid morphological features diagnosed between 2009 and 2021 in our hospital after expanding the molecular profile, including BRAF and NRAS mutations in all cases. METHODS AND RESULTS: A total of 71 neoplasms showing spitzoid features (Spitz-like) and atypia were included. The risk of progression of tumours was first studied by integrating the morphology, immunohistochemistry (p16, Ki67, HMB45 and PRAME) and fluorescence in-situ hybridisation (FISH) results (melanoma multiprobe and 9p21). In a second step, after expanding the molecular study, including BRAF and NRAS mutational status, the neoplasms were finally classified into four subgroups: atypical Spitz tumour (AST, n = 45); BRAF-mutated naevus/low-grade melanocytoma with spitzoid morphology (BAMS, n = 2); Spitz melanoma (SM, n = 14); and BRAF or NRAS mutated melanoma with spitzoid features (MSF, n = 10). Follow-up of patients revealed uneventful results for AST and BAMS. Only one SM presented lymph node metastasis after 134 months. Conversely, patients with MSF showed an unfavourable outcome: three developed lymph node metastases after a mean time of 22 months, with one patient presenting distant metastasis and dying of the disease 64 months from diagnosis. The progression-free survival showed significant differences between the four groups of spitzoid tumours (P < 0.001) and between both melanoma subtypes (P = 0.012). CONCLUSIONS: The classification and prognostication of atypical neoplasms with spitzoid features requires the integration of histomorphology with the molecular investigation of tumours, which should include BRAF and NRAS mutational status.

Longitudinal gut microbiome changes in immune checkpoint blockade-treated advanced melanoma.

Multiple clinical trials targeting the gut microbiome are being conducted to optimize treatment outcomes for immune checkpoint blockade (ICB). To improve the success of these interventions, understanding gut microbiome changes during ICB is urgently needed. Here through longitudinal microbiome profiling of 175 patients treated with ICB for advanced melanoma, we show that several microbial species-level genome bins (SGBs) and pathways exhibit distinct patterns from baseline in patients achieving progression-free survival (PFS) of 12 months or longer (PFS ≥12) versus patients with PFS shorter than 12 months (PFS <12). Out of 99 SGBs that could discriminate between these two groups, 20 were differentially abundant only at baseline, while 42 were differentially abundant only after treatment initiation. We identify five and four SGBs that had consistently higher abundances in patients with PFS ≥12 and <12 months, respectively. Constructing a log ratio of these SGBs, we find an association with overall survival. Finally, we find different microbial dynamics in different clinical contexts including the type of ICB regimen, development of immune-related adverse events and concomitant medication use. Insights into the longitudinal dynamics of the gut microbiome in association with host factors and treatment regimens will be critical for guiding rational microbiome-targeted therapies aimed at enhancing ICB efficacy.

Melanocortin-1 receptor (MC1R): a review for dermatologists.

Melanocortin-1 receptor (MC1R) and its variants have a pivotal role in melanin synthesis. However, MC1R has been associated to non-pigmentary pathways related to DNA-repair activities and inflammation. The aim of this review is to provide an up-to-date overview about the role of MC1R in the skin. Specifically, after summarizing the current knowledge about MC1R structure and polymorphisms, we report data concerning the correlation between MC1R, phenotypic traits, skin aging, other diseases and skin cancers and their risk assessment through genetic testing.

Prognostic and predictive value of non-steroidal anti-inflammatory drugs in the EORTC 1325/KEYNOTE-054 phase III trial of pembrolizumab versus placebo in resected high-risk stage III melanoma.

BACKGROUND: Pain is common in patients with cancer. The World Health Organisation recommends paracetamol or non-steroidal anti-inflammatory drugs (NSAIDs) for mild pain and combined with other agents for moderate/severe pain. This study estimated associations of NSAIDs with recurrence-free survival (RFS), distant metastasis-free survival (DMFS) and the incidence of immune-related adverse events (irAEs) in high-risk patients with resected melanoma in the EORTC 1325/KEYNOTE-054 phase III clinical trial. PATIENTS AND METHODS: Patients with AJCC7 stage IIIA, IIIB or IIIC resected melanoma were randomized to receive 200 mg of adjuvant pembrolizumab (N = 514) or placebo (N = 505) 3-weekly for one year or until recurrence. As previously reported, pembrolizumab prolonged RFS and DMFS. NSAID use was defined as administration between 7 days pre-randomization and starting treatment. Multivariable Cox and Fine and Gray models were used to estimate hazard ratios (HRs) for associations of NSAIDs with RFS, DMFS and irAEs. RESULTS: Of 1019 patients randomized, 59 and 44 patients in the pembrolizumab and placebo arms, respectively, used NSAIDs. NSAIDs were not associated with RFS (HR 0.91, 95% CI 0.58-1.43) or DMFS in the pembrolizumab (HR 1.03, 95% CI 0.65-1.66) or placebo arms (for RFS, HR 0.76, 95% CI 0.48-1.20; for DMFS, HR 0.80, 95% CI 0.49-1.31). NSAIDs were associated with the incidence of irAEs in the placebo arm (HR 3.06, 95% CI 1.45-6.45) but not in the pembrolizumab arm (HR 0.94, 95% CI 0.58-1.53). CONCLUSION: NSAIDs were not associated with efficacy outcomes nor the risk of irAEs in patients with resected high-risk stage III melanoma receiving adjuvant pembrolizumab.

A Narrative Review: Opportunities and Challenges in Artificial Intelligence Skin Image Analyses Using Total Body Photography.

Artificial intelligence (AI) algorithms for skin lesion classification have reported accuracy at par with and even outperformance of expert dermatologists in experimental settings. However, the majority of algorithms do not represent real-world clinical approach where skin phenotype and clinical background information are considered. We review the current state of AI for skin lesion classification and present opportunities and challenges when applied to total body photography (TBP). AI in TBP analysis presents opportunities for intrapatient assessment of skin phenotype and holistic risk assessment by incorporating patient-level metadata, although challenges exist for protecting patient privacy in algorithm development and improving explainable AI methods.

The 31-Gene Expression Profile Test Outperforms AJCC in Stratifying Risk of Recurrence in Patients with Stage I Cutaneous Melanoma.

BACKGROUND: Patients with stage I cutaneous melanoma (CM) are considered at low risk for metastasis or melanoma specific death; however, because the majority of patients are diagnosed with stage I disease, they represent the largest number of melanoma deaths annually. The 31-gene expression profile (31-GEP) test has been prospectively validated to provide prognostic information independent of staging, classifying patients as low (Class 1A), intermediate (Class 1B/2A), or high (Class 2B) risk of poor outcomes. METHODS: Patients enrolled in previous studies of the 31-GEP were combined and evaluated for recurrence-free (RFS) and melanoma-specific survival (MSS) (n = 1261, "combined"). A second large, unselected real-world cohort (n = 5651) comprising clinically tested patients diagnosed 2013-2018 who were linked to outcomes data from the NCI Surveillance, Epidemiology, and End Results (SEER) Program registries was evaluated for MSS. RESULTS: Combined cohort Class 1A patients had significantly higher RFS than Class 1B/2A or Class 2B patients (97.3%, 88.6%, 77.3%, p < 0.001)-better risk stratification than AJCC8 stage IA (97.5%) versus IB (89.3%). The SEER cohort showed better MSS stratification by the 31-GEP (Class 1A = 98.0%, Class 1B/2A = 97.5%, Class 2B = 92.3%; p < 0.001) than by AJCC8 staging (stage IA = 97.6%, stage IB = 97.9%; p < 0.001). CONCLUSIONS: The 31-GEP test significantly improved patient risk stratification, independent of AJCC8 staging in patients with stage I CM. The 31-GEP provided greater separation between high- (Class 2B) and low-risk (Class 1A) groups than seen between AJCC stage IA and IB. These data support integrating the 31-GEP into clinical decision making for more risk-aligned management plans.

Artificial Intelligence in Skin Cancer Diagnosis: A Reality Check.

The field of skin cancer detection offers a compelling use case for the application of artificial intelligence (AI) within the realm of image-based diagnostic medicine. Through the analysis of large datasets, AI algorithms have the capacity to classify clinical or dermoscopic images with remarkable accuracy. Although these AI-based applications can operate both autonomously and under human supervision, the best results are achieved through a collaborative approach that leverages the expertise of both AI and human experts. However, it is important to note that most studies focus on assessing the diagnostic accuracy of AI in artificial settings rather than in real-world scenarios. Consequently, the practical utility of AI-assisted diagnosis in a clinical environment is still largely unknown. Furthermore, there exists a knowledge gap concerning the optimal use cases and deployment settings for these AI systems as well as the practical challenges that may arise from widespread implementation. This review explores the advantages and limitations of AI in a variety of real-world contexts, with a specific focus on its value to consumers, general practitioners, and dermatologists.

Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy.

Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. In this study, we attempted to evaluate agreement among experts on exemplar images not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least 1 of 31 melanocytic-specific features were submitted by 25 world experts as exemplars. Using a web-based platform that allows for image markup of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with eight achieving excellent agreement (Gwet's AC >0.75) and seven of them being melanoma-specific features. These features were peppering/granularity (0.91), shiny white streaks (0.89), typical pigment network (0.83), blotch irregular (0.82), negative network (0.81), irregular globules (0.78), dotted vessels (0.77), and blue-whitish veil (0.76). By utilizing an exemplar dataset, a good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication, and machine learning experiments.

Sphingolipid paracrine signaling impairs keratinocyte adhesion to promote melanoma invasion.

Melanoma is the deadliest form of skin cancer due to its propensity to metastasize. It arises from melanocytes, which are attached to keratinocytes within the basal epidermis. Here, we hypothesize that, in addition to melanocyte-intrinsic modifications, dysregulation of keratinocyte functions could initiate early-stage melanoma cell invasion. We identified the lysolipid sphingosine 1-phosphate (S1P) as a tumor paracrine signal from melanoma cells that modifies the keratinocyte transcriptome and reduces their adhesive properties, leading to tumor invasion. Mechanistically, tumor cell-derived S1P reduced E-cadherin expression in keratinocytes via S1P receptor dependent Snail and Slug activation. All of these effects were blocked by S1P2/3 antagonists. Importantly, we showed that epidermal E-cadherin expression was inversely correlated with the expression of the S1P-producing enzyme in neighboring tumors and the Breslow thickness in patients with early-stage melanoma. These findings support the notion that E-cadherin loss in the epidermis initiates the metastatic cascade in melanoma.

Combined WNT-activated deep penetrating/plexiform melanocytoma: insights into clinicopathological and molecular characterization.

INTRODUCTION: A combined deep penetrating tumor redefined as WNT-activated deep penetrating/plexiform melanocytoma (DPM), may pose challenging clinical and histological diagnoses. OBJECTIVES: This study aims to review the clinicopathological characteristics of combined DPMs and characterize the molecular profile of atypical and malignant forms. METHODS: The study included 51 cases of combined DPMs diagnosed at the Hospital Clinic of Barcelona and the University of Florence between 2012 and 2020. Clinical data, dermoscopy images (when available), and histological characteristics were reviewed. Immunohistochemistry for ß-catenin, LEF1, HMB45, Ki67, p16, and PRAME was performed. Atypical forms underwent NGS panel analysis, including driver genes implicated in DPMs, TERT- promoter (p) mutation, and the investigation of the 9p21 locus via FISH. RESULTS: Among the 51 cases (32 females and 19 males, age range 4- 74), 68% with available clinical data were initially suspected of melanoma. Except for one case, complete excision resulted in no recurrences or metastases. One incompletely excised combined DPM developed a lymph node melanoma metastasis 10 years later. Ten cases (20%) showed atypical histological features; 7 cases (13%) exhibited a significant loss of p16 expression; and 2 cases (4%) showed a high-proliferative index (Ki67 over 5%). NGS analysis in these cases revealed a double mutation BRAFV600E and exon 3 CTNNB1; no TERT-p mutations were detected. CONCLUSIONS: Clinical suspicion of melanoma is common in combined DPMs, but the malignant progression is infrequent in tumors lacking high-grade atypia or proliferation. These findings are congruent with the consideration of these lesions as intermediate-grade tumors or melanocytomas.

Validation of Epidermal AMBRA1 and Loricrin (AMBLor) as a prognostic biomarker for non-ulcerated AJCC stage I/II cutaneous melanoma.

BACKGROUND: Combined loss of the autophagy-regulatory protein AMBRA1 and the terminal differentiation marker loricrin in the peritumoural epidermis of stage I melanomas can identify tumour subsets at low risk of metastasis. OBJECTIVES: The aim of the present study was to validate the combined loss of peritumoural AMBRA1 and loricrin (AMBLor) as a prognostic biomarker able to identify both stage I and II melanomas at low risk of tumour recurrence. METHODS: Automated Immunohistochemistry was used to analyse peritumoural AMBRA1 and loricrin expression in geographically distinct discovery (n = 540) and validation (n = 300) cohorts of non-ulcerated AJCC stage I and II melanomas. AMBLor status was correlated with clinical outcomes in the discovery and validation cohorts separately and combined. RESULTS: Analysis of AMBLor in the discovery cohort revealed a recurrence-free survival (RFS) rate of 95.5% in the AMBLor low risk group compared to 81.7% in the AMBLor at-risk group (multivariate log-rank, P < 0.001), and a negative predictive value (NPV) of 96%. In the validation cohort, AMBLor analysis revealed a RFS rate of 97.6% in the AMBLor low risk group compared to 78.3% in the at-risk group (multivariate log-rank, P < 0.001) and a NPV of 97.6%. In a multivariate model considering AMBLor, Breslow thickness, age and sex, analysis of the combined discovery and validation cohorts showed that the estimated effect of AMBLor was statistically significant with a hazard ratio of 3.469 (95% confidence interval 1.403-8.580, P = 0.007), with an overall NPV of 96.5%. CONCLUSIONS: These data provide further evidence validating AMBLor as a prognostic biomarker to identify non-ulcerated AJCC stage I and II melanoma tumours at low risk of disease recurrence.