3D Whole-body skin imaging for automated melanoma detection.

BACKGROUND: Existing artificial intelligence for melanoma detection has relied on analysing images of lesions of clinical interest, which may lead to missed melanomas. Tools analysing the entire skin surface are lacking. OBJECTIVES: To determine if melanoma can be distinguished from other skin lesions using data from automated analysis of 3D-images. METHODS: Single-centre, retrospective, observational convenience sample of patients diagnosed with melanoma at a tertiary care cancer hospital. Eligible participants were those with a whole-body 3D-image captured within 90 days prior to the diagnostic skin biopsy. 3D-images were obtained as standard of care using VECTRA WB360 Whole Body 3-dimensional Imaging System (Canfield Scientific). Automated data from image processing (i.e. lesion size, colour, border) for all eligible participants were exported from VECTRA DermaGraphix research software for analysis. The main outcome was the area under the receiver operating characteristic curve (AUC). RESULTS: A total of 35 patients contributed 23,538 automatically identified skin lesions >2 mm in largest diameter (102-3021 lesions per participant). All were White patients and 23 (66%) were males. The median (range) age was 64 years (26-89). There were 49 lesions of melanoma and 22,489 lesions that were not melanoma. The AUC for the prediction model was 0.94 (95% CI: 0.92-0.96). Considering all lesions in a patient-level analysis, 14 (28%) melanoma lesions had the highest predicted score or were in the 99th percentile among all lesions for an individual patient. CONCLUSIONS: In this proof-of-concept pilot study, we demonstrated that automated analysis of whole-body 3D-images using simple image processing techniques can discriminate melanoma from other skin lesions with high accuracy. Further studies with larger, higher quality, and more representative 3D-imaging datasets would be needed to improve and validate these results.

The long-term evolution of melanocytic nevi among high-risk adults.

BACKGROUND: There is little understanding regarding the long-term natural history of melanocytic nevi among adults. OBJECTIVE: The objective of the study was to describe the long-term natural history of individual nevi located on the torso of high-risk patients. METHODS: All patients attending Memorial Sloan Kettering Cancer Center (MSKCC) who underwent two total body photography (TBP) sessions 15+ years apart were included ('retrospective' group). To account for a potential selection bias, we also included consecutive patients who had TBP 15+ years ago and consented to undergo follow-up TBP ('prospective' group). We compared baseline and follow-up torso images on the TBPs and evaluated the number of total, new and disappearing nevi; number of seborrheic keratoses and actinic keratoses; each nevus' diameter at both time points; each nevus' colour change; the presence of clinical atypia; and when dermoscopy was available, the dermoscopic features at each time point. RESULTS: One hundred six patients were included in the study. Although the average age of the patients was 40 at baseline TBP, most patients developed new nevi between imaging sessions (median 16.4 years) with an average of 2.6 (SD = 4.8) nevi per participant. The average number of disappearing nevi was 0.3 (SD = 0.6). In addition, 62/106 (58%) patients had an absolute increase, and 9/106 (8%) patients had an absolute decrease in their total nevus count. Roughly half (49%: 1416/2890) of the nevi that could be evaluated at both time points increased in diameter by at least 25%. Only 6% (159/2890) of nevi shrunk in diameter by at least 25%. Patients with a history of melanoma had a higher rate of disappearing nevi, and their nevi were more likely to grow. Most nevi demonstrated no significant dermoscopic changes. CONCLUSIONS: High-risk patients acquire new nevi throughout life with very few nevi disappearing over time. Contrary to prior reports, most nevi in adults increase in diameter, while few nevi shrink.

Performance of a deep neural network in teledermatology: a single-centre prospective diagnostic study.

BACKGROUND: The use of artificial intelligence (AI) algorithms for the diagnosis of skin diseases has shown promise in experimental settings but has not been yet tested in real-life conditions. OBJECTIVE: To assess the diagnostic performance and potential clinical utility of a 174-multiclass AI algorithm in a real-life telemedicine setting. METHODS: Prospective, diagnostic accuracy study including consecutive patients who submitted images for teledermatology evaluation. The treating dermatologist chose a single image to upload to a web application during teleconsultation. A follow-up reader study including nine healthcare providers (3 dermatologists, 3 dermatology residents and 3 general practitioners) was performed. RESULTS: A total of 340 cases from 281 patients met study inclusion criteria. The mean (SD) age of patients was 33.7 (17.5) years; 63% (n = 177) were female. Exposure to the AI algorithm results was considered useful in 11.8% of visits (n = 40) and the teledermatologist correctly modified the real-time diagnosis in 0.6% (n = 2) of cases. The overall top-1 accuracy of the algorithm (41.2%) was lower than that of the dermatologists (60.1%), residents (57.8%) and general practitioners (49.3%) (all comparisons P < 0.05, in the reader study). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained, the balanced top-1 accuracy of the algorithm (47.6%) was comparable to the dermatologists (49.7%) and residents (47.7%) but superior to the general practitioners (39.7%; P = 0.049). Algorithm performance was associated with patient skin type and image quality. CONCLUSIONS: A 174-disease class AI algorithm appears to be a promising tool in the triage and evaluation of lesions with patient-taken photographs via telemedicine.

Association between the dermoscopic morphology of peripheral globules and melanocytic lesion diagnosis.

BACKGROUND: The presence of peripheral globules is associated with enlarging melanocytic lesions; however, there are numerous patterns of peripheral globules distribution and it remains unknown whether specific patterns can help differentiate enlarging naevi from melanoma. OBJECTIVE: To investigate whether morphological differences exist between the peripheral globules seen in different subsets of naevi and in melanoma. METHODS: A cross-sectional study of clinical notes that mentioned peripheral globules, in addition to all melanoma images with peripheral globules on the International Skin Imaging Collaboration archive. Dermoscopic images were reviewed and annotated. Associations between diagnosis and categorical features were measured with odds ratios. Non-parametric tests were used for continuous factors. RESULTS: 184 lesions with peripheral globules from our clinic were included in the analysis; only 6 of these proved to be melanoma. 109 melanomas with peripheral globules from the International Skin Imaging Collaboration archive were added to the analysis. Melanomas were more common on the extremities and among older individuals. Melanomas were more likely to display atypical, tiered and/or focal peripheral globules. Only 5% of melanomas lacked dermoscopic melanoma-specific structures compared to 48% of naevi. CONCLUSIONS: Melanocytic lesions with atypical or asymmetrically distributed peripheral globules, especially when located on the extremities, should raise suspicion for malignancy. Melanocytic lesions with typical and symmetrically distributed peripheral globules, and with no other concerning dermoscopic features, are unlikely to be malignant.

Human surface anatomy terminology for dermatology: a Delphi consensus from the International Skin Imaging Collaboration.

BACKGROUND: There is no internationally vetted set of anatomic terms to describe human surface anatomy. OBJECTIVE: To establish expert consensus on a standardized set of terms that describe clinically relevant human surface anatomy. METHODS: We conducted a Delphi consensus on surface anatomy terminology between July 2017 and July 2019. The initial survey included 385 anatomic terms, organized in seven levels of hierarchy. If agreement exceeded the 75% established threshold, the term was considered 'accepted' and included in the final list. Terms added by the participants were passed on to the next round of consensus. Terms with <75% agreement were included in subsequent surveys along with alternative terms proposed by participants until agreement was reached on all terms. RESULTS: The Delphi included 21 participants. We found consensus (≥75% agreement) on 361/385 (93.8%) terms and eliminated one term in the first round. Of 49 new terms suggested by participants, 45 were added via consensus. To adjust for a recently published International Classification of Diseases-Surface Topography list of terms, a third survey including 111 discrepant terms was sent to participants. Finally, a total of 513 terms reached agreement via the Delphi method. CONCLUSIONS: We have established a set of 513 clinically relevant terms for denoting human surface anatomy, towards the use of standardized terminology in dermatologic documentation.

Outpatient dermatology consultations for oncology patients with acute dermatologic adverse events impact anticancer therapy interruption: a retrospective study.

BACKGROUND: Dermatologic adverse events (dAEs) of anticancer therapies may negatively impact dosing and quality of life. While therapy interruption patterns due to dAEs have been studied in hospitalized cancer patients, similar outcomes in outpatient oncodermatology are lacking. OBJECTIVES: To analyse the therapy interruption patterns, clinico-histopathologic characteristics and management outcomes of outpatient dermatology consultations for acute dAEs attributed to the most frequently interrupted class of oncologic agents. METHODS: We performed a retrospective cohort study of all cancer patients who received a same-day outpatient dermatology consultation for acute dAEs at our institution from 1 January to 30 June 2015. Relevant data were abstracted from electronic medical records, including demographics, oncologic history and explicit recommendations by both the referring clinician and consulting dermatologist on anticancer therapy interruption. Consultations with the most frequently interrupted class of oncologic treatment were characterized according to clinico-histopathologic features, dermatologic management and clinical outcomes. RESULTS: There were 426 same-day outpatient dermatology consultations (median age 59, 60% female, 30% breast cancer), of which 295 (69%) had systemic anticancer therapy administered within 30 days prior. There was weak inter-rater agreement between referring clinicians and consulting dermatologists on interruption of anticancer treatment (n = 150, κ = 0.096; 95% CI -0.02 to 0.21). Seventy-three (25%) consultations involved interruption by the referring clinician, most commonly targeted therapy (24, 33%). Maculopapular rash was commonly observed in 23 consultations with 25 dAEs attributed to targeted agents (48%), and topical corticosteroids were most frequently utilized for management (22, 38%). The majority (83%) of consultations with targeted therapy-induced dAEs responded to dermatologic treatment and 84% resumed oncologic therapy, although three (19%) at a reduced dose. Rash recurred only in two instances (13%). CONCLUSIONS: A high frequency of positive outcomes in the management of targeted therapy-induced dAEs by outpatient consulting dermatologists and low recurrence of skin toxicity suggests impactful reductions in interruption of anticancer therapy.

Accuracy of tele-consultation on management decisions of lesions suspect for melanoma using reflectance confocal microscopy as a stand-alone diagnostic tool.

BACKGROUND: Diagnostic accuracy of reflectance confocal microscopy (RCM) as a stand-alone diagnostic tool for suspect skin lesions has not been extensively studied. OBJECTIVE: Primary aim was to measure experts' accuracy in RCM-based management decisions. Secondary aim was to identify melanoma-specific RCM features. METHODS: The study enrolled patients ≥18 years that underwent biopsy of skin lesions clinically suspected to be melanoma. One hundred lesions imaged by RCM were randomly selected from 439 lesions prospectively collected at four pigmented lesion clinics. The study data set included 23 melanomas, three basal cell and two squamous cell carcinomas, 11 indeterminate melanocytic lesions and 61 benign lesions including 50 nevi. Three expert RCM evaluators were blinded to clinical or dermoscopic images, and to the final histopathological diagnosis. Evaluators independently issued a binary RCM-based management decision, 'biopsy' vs. 'observation'; these decisions were scored against histopathological diagnosis, with 'biopsy' as the correct management decision for malignant and indeterminate lesions. A subset analysis of 23 melanomas and 50 nevi with unequivocal histopathological diagnosis was performed to identify melanoma-specific RCM features. RESULTS: Sensitivity, specificity and diagnostic accuracy were 74%, 67% and 70% for reader 1, 46%, 84% and 69% for reader 2, and 72%, 46% and 56% for reader 3, respectively. The overall kappa for management decisions was 0.34. Readers had unanimous agreement on management for 50 of the 100 lesions. Non-specific architecture, non-visible papillae, streaming of nuclei, coarse collagen fibres and abnormal vasculature showed a significant association with melanoma in the evaluation of at least two readers. CONCLUSIONS: Reflectance confocal microscopy tele-consultation of especially challenging lesions, based on image review without benefit of clinical or dermoscopy images, may be associated with limited diagnostic accuracy and interobserver agreement. Architectural and stromal criteria may emerge as potentially useful and reproducible criteria for melanoma diagnosis.

A case report of disappearing pigmented skin lesions associated with pembrolizumab treatment for metastatic melanoma.

Pembrolizumab is an immune checkpoint inhibitor that targets the programmed cell death (PD)-1 receptor. Common cutaneous adverse side-effects of PD-1 inhibitors include maculopapular rash, pruritus, vitiligo and lichenoid skin and mucosal reactions. Here we describe a man in his sixties with metastatic melanoma treated with pembrolizumab who subsequently developed fading or disappearance of pigmented skin lesions, lightening of the skin, and poliosis of the eyebrows, eyelashes and scalp and body hair. Compared with baseline high-resolution three-dimensional total-body photography, we observed fading or disappearance of solar lentigines, seborrhoeic keratoses and melanocytic naevi, suggesting that PD-1 inhibitors may affect the evolution of these benign skin lesions. With dermatoscopic follow-up, altered lesions showed either blue-grey peppering/granularity or fading in colour without other identifiable features. No halo lesions or lesions with surrounding inflammation were identified. One changed pigmented lesion that showed blue-grey peppering/granularity on dermoscopy was biopsied and interpreted as a macular seborrhoeic keratosis with melanophages. Further studies are required to elucidate the effects of PD-1 inhibition on benign skin lesions.

Dermoscopic features and patterns of poromas: a multicentre observational case-control study conducted by the International Dermoscopy Society.

BACKGROUND: Poromas are benign cutaneous sweat gland tumours that are challenging to identify. The dermoscopic features of poromas are not well characterized. OBJECTIVE: To determine the clinical-dermoscopic features of poromas. METHODS: Cross-sectional, observational study of 113 poromas and 106 matched control lesions from 16 contributors and eight countries. Blinded reviewers evaluated the clinical and dermoscopic features present in each clinical and dermoscopic image. RESULTS: Poromas were most commonly non-pigmented (85.8%), papules (35.4%) and located on non-acral sites (65.5%). In multivariate analysis, dermoscopic features associated with poroma included white interlacing areas around vessels (OR: 7.9, 95% CI: 1.9-32.5, P = 0.004), yellow structureless areas (OR: 2.5, 95% CI: 1.1-6.0, P = 0.04), milky-red globules (OR: 3.9, 95% CI: 1.4-11.1, P = 0.01) and poorly visualized vessels (OR: 33.3, 95% CI: 1.9-586.5, P = 0.02). The presence of branched vessels with rounded endings was positively associated with poromas but did not reach statistical significance (OR: 2.4, 95% CI: 0.8-6.5, P = 0.10). The presence of any of these five features was associated with a sensitivity and specificity of 62.8% and 82.0%, respectively. CONCLUSION: We identified dermoscopic features that are specific to the diagnosis of poroma. Overall, however, the prevalence of these features was low. Significant clinical and dermoscopic variability is a hallmark of these uncommon tumours, which are most prevalent on non-acral sites.

Cutaneous involvement of disseminated adenovirus infection in an allogeneic stem cell transplant recipient.

Infection by human adenoviruses can lead to significant morbidity and mortality in immunocompromised hosts, such as allogeneic stem cell transplant (SCT) recipients, with limited effective treatment options. Specific cutaneous manifestations of disseminated adenovirus infection are not well described. We report a woman in her twenties who received an allogeneic T-cell-depleted peripheral blood SCT for the treatment of severe aplastic anaemia and, 5 months post-transplant, was hospitalized for severe systemic adenovirus infection with progressive involvement of the colon, liver and lungs. Despite therapy with intravenous cidofovir, oral brincidofovir and intravenous immunoglobulin, she had progression of adenoviraemia and dissemination of adenoviral disease. The patient developed a progressive rash characterized by keratotic papules that began on the palms and soles and spread to the entire body. Histopathological examination of skin biopsies of individual skin lesions from the palm and abdomen showed focal acantholytic dyskeratosis and keratinocytes with hyperchromatic nuclei. Several keratinocyte nuclei were immunoreactive for adenovirus. The patient was further treated with ribavirin and adenovirus-specific cytotoxic T lymphocytes but experienced multisystem progression of adenovirus infection culminating in death.

A Clinical Aid for Detecting Skin Cancer: The Triage Amalgamated Dermoscopic Algorithm (TADA).

PURPOSE: Family physicians (FPs) frequently evaluate skin lesions but may not have the necessary training to accurately and confidently identify lesions that require skin biopsy or specialist referral. We evaluated the diagnostic performance of a new, simplified dermoscopy algorithm for skin cancer detection. METHODS: In this cross-sectional, observation study, attendees of a dermoscopy course evaluated 50 polarized dermoscopy images of skin lesions (27 malignant and 23 benign) using the Triage Amalgamated Dermoscopic Algorithm (TADA). The dermoscopic criteria of TADA include architectural disorder (ie, disorganized or asymmetric distribution of colors and/or structures), starburst pattern, blue-black or gray color, white structures, negative network, ulcer, and vessels. The study occurred after 1 day of basic dermoscopy training. Clinical information related to palpation (ie, firm, dimpling) was provided when relevant. RESULTS: Of 200 course attendees, 120 (60%) participated in the study. Participants included 64 (53.3%) dermatologists and 41 (34.2%) primary care physicians, 19 (46.3%) of whom were FPs. Fifty-two (43%) individuals had no previous dermoscopy training. Overall, the sensitivity and specificity of TADA for malignant skin lesions was 94.8% and 72.3%, respectively. Previous dermoscopy training and years of dermoscopy experience were not associated with diagnostic sensitivity (P = .13 and P = .05, respectively) or specificity (P = .36 and P = .21, respectively). Specialty type was not associated with sensitivity (P = .37) but dermatologists had a higher specificity than nondermatologists (79% v. 72%, P = .008). CONCLUSIONS: After basic instruction, TADA may be a useful dermoscopy algorithm for FPs who examine skin lesions as it has a high sensitivity for detecting skin cancer.

Cross-sectional analysis of the dermoscopic patterns and structures of melanocytic naevi on the back and legs of adolescents.

BACKGROUND: Junctional (flat) naevi predominate on the extremities, whereas dermal (raised) naevi are found primarily on the head, neck and trunk. Few studies have investigated the anatomical site prevalence of melanocytic naevi categorized using dermoscopy. OBJECTIVES: To identify the prevalence of dermoscopic patterns and structures of naevi from the back and legs of adolescents. METHODS: Dermoscopic images of acquired melanocytic naevi were obtained from the back and legs of students from a population-based cohort in Framingham, Massachusetts. Naevi were classified into reticular, globular, homogeneous or complex dermoscopic patterns. Multinomial logistic regression modelling assessed the associations between dermoscopic pattern and anatomical location. RESULTS: In total 509 participants (mean age 14 years) contributed 2320 back naevi and 637 leg naevi. Compared with homogeneous naevi, globular and complex naevi were more commonly observed on the back than the legs [odds ratio (OR) 29·39, 95% confidence interval (CI) 9·53-90·65, P < 0·001 and OR 6·8, 95% CI 2·7-17·14, P < 0·001, respectively], whereas reticular lesions were less likely to be observed on the back than on the legs (OR 0·67, 95% CI 0·54-0·84, P = 0·001). Naevi containing any globules were more prevalent on the back than on the legs (25% vs. 3·6%, P < 0·001). Naevi containing any network were more prevalent on the legs than on the back (56% vs. 40·6%, P < 0·001). CONCLUSIONS: These findings add to a robust body of literature suggesting that dermoscopically defined globular and reticular naevi represent biologically distinct naevus subsets that differ in histopathological growth pattern, age- and anatomical-site-related prevalence, molecular phenotype and aetiological pathways.

Genetic factors associated with naevus count and dermoscopic patterns: preliminary results from the Study of Nevi in Children (SONIC).

BACKGROUND: Melanocytic naevi are an important risk factor for melanoma. Naevi with distinct dermoscopic patterns can differ in size, distribution and host pigmentation characteristics. OBJECTIVES: We examined MC1R and 85 other candidate loci in a cohort of children to test the hypothesis that the development and dermoscopic type of naevi are modulated by genetic variants. METHODS: Buccal DNAs were obtained from a cohort of 353 fifth graders (mean age 10·4 years). Polymorphisms were chosen based on a known or anticipated role in naevi and melanoma. Associations between single-nucleotide polymorphisms (SNPs) and baseline naevus count were determined by multivariate regression adjusting for sex, race/ethnicity and sun sensitivity. Dermoscopic images were available for 853 naevi from 290 children. Associations between SNPs and dermoscopic patterns were determined by polytomous regression. RESULTS: Four SNPs were significantly associated with increasing (IRF4) or decreasing (PARP1, CDK6 and PLA2G6) naevus count in multivariate shrinkage analyses with all SNPs included in the model; IRF4 rs12203952 showed the strongest association with log naevus count (relative risk 1·56, P < 0·001). Using homogeneous naevi as the reference, IRF4 rs12203952 and four other SNPs in TERT, CDKN1B, MTAP and PARP1 were associated with either globular or reticular dermoscopic patterns (P < 0·05). CONCLUSIONS: Our results provide evidence that subsets of naevi defined by dermoscopic patterns differ in their associations with germline genotypes and support the hypothesis that dermoscopically defined subsets of naevi are biologically distinct. These results require confirmation in larger cohorts. If confirmed, these findings will improve the current knowledge of naevogenesis and assist in the identification of individuals with high-risk phenotypes.

Melanocytic naevi with globular and reticular dermoscopic patterns display distinct BRAF V600E expression profiles and histopathological patterns.

BACKGROUND: BRAF (v-raf murine sarcoma viral oncogene homologue B) V600E mutations have been detected with high frequency in melanocytic naevi. Few studies have stratified analyses by naevus dermoscopic pattern. OBJECTIVES: To determine the frequency of BRAF V600E expression and histopathological pattern in acquired melanocytic naevi distinguished by a globular vs. reticular dermoscopic pattern. METHODS: We retrospectively identified histologically proven melanocytic naevi with banal reticular or globular dermoscopic patterns and evaluated BRAF V600E expression using immunohistochemistry. RESULTS: BRAF V600E expression was detected in 11 of 12 globular naevi vs. four of 13 reticular naevi (91·7% vs. 30·1%, P = 0·004). A predominantly dermal growth pattern (P < 0·001) and the presence of large junctional nests (P = 0·017) were each associated with a globular dermoscopic pattern. The presence of either a predominantly dermal growth pattern or large junctional nests was found in 13 of 15 naevi positive for BRAF V600E and in two of 10 naevi negative for BRAF V600E (86·7% vs. 20%, P = 0·002). CONCLUSIONS: The frequency of BRAF V600E mutations differs in naevi distinguished by unique dermoscopic structures and microanatomical growth patterns. Globular naevi, which most often histologically correspond to a predominantly dermal growth pattern and/or the presence of large junctional nests, are significantly more likely to express BRAF V600E than reticular naevi. These preliminary results require validation, but may directly inform future studies of naevogenesis and melanoma genesis.