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.

Inner gray halo, a novel dermoscopic feature for the diagnosis of pigmented actinic keratosis: clues for the differential diagnosis with lentigo maligna.

BACKGROUND: Pigmented actinic keratosis (PAK) is a frequent simulator of lentigo maligna (LM) on the face upon clinical and dermoscopic examination, leading to misdiagnosis and unnecessary excisions. LM and PAK share dermoscopic features, making it difficult to have a confident diagnosis of PAK only with current dermoscopic knowledge. OBJECTIVE: We sought to evaluate sensitivity, specificity, and interobserver reproducibility of a novel dermoscopic feature, inner gray halo (IGH), and establish its histopathological and confocal correlations. METHODS: Dermoscopists blinded to histopathological diagnosis evaluated 58 PAK and 21 LM for the presence of IGH and dermoscopy parameters. Areas exhibiting IGH were marked and imaged with reflectance confocal microscopy before sampling for histopathologic correlation. Reflectance confocal microscopy and transverse histologic sectioning were performed in 14 of 79 cases. RESULTS: IGH was present in 53 of 58 (94.1%) PAK and in 5 of 21 (23.8%) LM in our series (sensitivity 91.4%; specificity 71.4%; positive predictive value 89.8%). Interobserver agreement was excellent (Kappa 0.846). Through transverse and perpendicular histologic sections, a dermoscopic-histologic-confocal correlation of IGH was established. LIMITATIONS: A larger test set is needed to further validate the use of IGH in the differential diagnosis of PAK and facial pigmented lesions. CONCLUSION: IGH is a novel dermoscopic parameter useful for the differentiation of PAK from LM on the face.

Gene network analyses point to the importance of human tissue kallikreins in melanoma progression.

BACKGROUND: A wide variety of high-throughput microarray platforms have been used to identify molecular targets associated with biological and clinical tumor phenotypes by comparing samples representing distinct pathological states. METHODS: The gene expression profiles of human cutaneous melanomas were determined by cDNA microarray analysis. Next, a robust analysis to determine functional classifications and make predictions based on data-oriented hypotheses was performed. Relevant networks that may be implicated in melanoma progression were also considered. RESULTS: In this study we aimed to analyze coordinated gene expression changes to find molecular pathways involved in melanoma progression. To achieve this goal, ontologically-linked modules with coordinated expression changes in melanoma samples were identified. With this approach, we detected several gene networks related to different modules that were induced or repressed during melanoma progression. Among them we observed high coordinated expression levels of genes involved in a) cell communication (KRT4, VWF and COMP); b) epidermal development (KLK7, LAMA3 and EVPL); and c) functionally related to kallikreins (EVPL, KLK6, KLK7, KLK8, SERPINB13, SERPING1 and SLPI). Our data also indicated that hKLK7 protein expression was significantly associated with good prognosis and survival. CONCLUSIONS: Our findings, derived from a different type of analysis of microarray data, highlight the importance of analyzing coordinated gene expression to find molecular pathways involved in melanoma progression.

Time to diagnosis of melanoma: same trend in different continents.

BACKGROUND: Patients and physicians both play an important role in the diagnosis of malignant melanoma. OBJECTIVE: The purpose of this study was to assess important factors of delay in diagnosis at different centers and on three continents. METHODS: Between October 2001 and October 2002, patients with histologically confirmed invasive melanoma were included in the study and given an established questionnaire. Recorded patients and tumor characteristics included age, sex, anatomic location, Breslow thickness, patients' awareness of the lesion and time with suspicion, and physicians' time (delay) before the operation. RESULTS: The study included 985 patients (486 males, 499 females): 253 from Germany, 464 from Sweden, 58 from Brazil, and 210 from Australia. More females detected their lesions by themselves. The change to a darker color (21%) and enlargement of the area of the lesion (19%) were the major signs. The highest knowledge among patients that early detection may improve the outcome was found in Sweden and Australia. At each center, the media (newspaper, magazine, radio, and television) provided the best sources of information about melanoma. Twenty to 33% of all physicians initially consulted missed the melanoma diagnosis, independent of their specialty. CONCLUSIONS: There are still factors for the delay in melanoma diagnosis in different countries and continents, but the differences are rather small. The results should be included in planning prevention campaigns in this specific field and in the education of medical students, physicians of all specialties, and other health professionals.

Cutaneous melanoma in childhood and adolescence: retrospective study of 32 patients.

This study was performed to analyse the behaviour, risk factors, prognosis and evolution of cutaneous melanoma in childhood and adolescence treated in a single institution. A retrospective study was performed between 1980 and 2000 of patients aged 18 years or younger followed at the Hospital do Cancer de Sao Paulo, Brazil. Data included demographic status, risk factors, clinical and histopathological characteristics of the primary and metastatic lesions, stage and follow-up. Seventeen female (53.1%) and 15 male (46.9%) patients were studied. Twelve patients (37.5%) were aged 12 years or younger. The trunk was the most common location (14 patients; 43.8%). Five patients (15.6%) had giant congenital melanocytic naevus, three (9.4%) had xeroderma pigmentosum and one (3%) had dysplastic melanocytic naevus. Nodular melanoma was the most frequent histological type and 43.8% had a thickness of more than 4 mm. Five of the 32 patients (15.6%) were lost to follow-up and 15 (46.9%) were alive at the last year's follow-up, 11 (34.4%) without disease and four (12.5%) with active disease. The 5-year overall survival was 64.34%. An overall survival of 11.71% was found in patients with visceral metastasis with or without cutaneous and/or lymph node involvement, whereas the corresponding value was 90.48% (P value=0.0002) in patients with only cutaneous and/or lymph node metastasis. Cutaneous melanomas are uncommon in the young and are seldom diagnosed in the early stages, perhaps due to a reluctance to accept this diagnosis in this age group. Prevention and early stage diagnosis depend upon the recognition that this disease is present in the young.

Subcutaneous phaeohyphomycosis caused by Phoma cava: report of a case and review of the literature

O presente trabalho registra um caso de feo-hifomicose subcutanea em paciente do sexo masculino com o diagnostico de sarcoidose pulmonar, submetido a terapeutica por corticosteroides quando apresentou no dorso da mao direita lesoes cutaneas nodulares, eritemato-violaceas, de aspecto infiltrado, exigindo biopsia para o diagnostico. O exame histopatologico revelou processo granulomatoso, com a presenca de hifas e celulas arredondadas demacias...