Clinical and dermatoscopic predictors of squamous cell carcinoma of the lips: a case-control, multicentric study.

BACKGROUND: Squamous cell carcinoma of the lip accounts for 20% of all oral carcinomas. Its diagnosis may be challenging because it clinically resembles actinic cheilitis and inflammatory lesions of the lips. OBJECTIVES: To determine clinical and dermatoscopic predictors of squamous cell carcinoma of the lip vs. other lip lesions. METHODS: Multicentre retrospective morphological study, including histologically confirmed cases of squamous cell carcinoma of the lip and controls consisting of actinic cheilitis and inflammatory lesions of the lips. Clinical and dermatoscopic images were evaluated for the presence of predefined criteria. Crude and adjusted odds ratios and corresponding 95% confidence intervals were calculated by univariate and multivariate logistic regression respectively. RESULTS: A total of 177 lip lesions were evaluated, 107 (60.5%) were squamous cell carcinomas and 70 (39.5%) were controls. The most frequent dermatoscopic criteria of lip squamous cell carcinoma were scales (100%), white halos (87.3%) and ulceration (79.4%). The majority of squamous cell carcinomas displayed polymorphic vessels (60.8%), with linear (68.6%) and hairpin (67.6%) being the most frequent types. Multivariate logistic regression analysis showed that clinical predictors of lip squamous cell carcinoma were exophytic appearance and clinical hyperkeratosis, with 43-fold and 6-fold higher probability respectively. White clods and ulceration in dermoscopy presented a 6-fold and 4-fold increased risk for squamous cell carcinoma respectively. CONCLUSIONS: A scaly lesion with exophytic growth, dermatoscopically displaying white clods, ulceration and linear and hairpin vessels is very likely a squamous cell carcinoma of the lip.

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.

'Inverse association between the total naevus count and melanoma thickness'.

BACKGROUND: Individuals with a high total naevus count (TNC) are at a higher risk to develop melanoma, and screening efforts have been largely focused on this group. However, some studies suggest that melanomas of patients with many nevi are thinner than those of patients with few nevi. Additionally, nodular melanoma has been associated with individuals with a low naevus count. OBJECTIVE: To investigate the association between TNC and melanoma Breslow thickness. METHODS: A two-centre retrospective study from 1 January 2016 to 1 January 2018. This included three hundred and twenty-six consecutive melanoma patients from two tertiary melanoma centres. The mean age at presentation was 58.3 years (SD = 15.9), and the majority (54.9%, N = 179) were men. Incidence of new in situ and invasive melanomas and correlation with TNC were measured. RESULTS: The mean total naevus count for patients presenting with in situ melanoma was 57.2 (range 4-178), while for patients presenting with invasive disease was 31.5 (P = 0.01). In situ disease was associated with a higher TNC across all ages. For invasive melanoma, a positive association between age and Breslow thickness was observed, while TNC was inversely associated with Breslow thickness. Each additional naevus accounted for a 4% decreased likelihood that the subject had invasive disease. CONCLUSION: Patients with a higher naevus count had thinner melanomas and more melanomas in situ, independent of age and sex.

Reflectance confocal microscopy and dermoscopy aid in evaluating repigmentation within or adjacent to lentigo maligna melanoma surgical scars.

BACKGROUND: Determining whether repigmentation within or adjacent to lentigo maligna or lentigo maligna melanoma (LM/LMM) scars represents recurrence of melanoma is challenging. The use of reflectance confocal microscopy (RCM) and dermoscopy may aid in differentiating true melanoma recurrence from other causes of repigmentation. OBJECTIVES: To describe the characteristics of repigmentation within or adjacent to LM/LMM scars observable on RCM and dermoscopy. METHODS: We retrospectively analysed patients who presented with new pigmentation within or adjacent to scars from surgically treated LM/LMM between January 2014 and December 2018. Clinical and demographic characteristics and time to recurrence were recorded. RCM was used to evaluate areas of pigmentation before biopsy. If available, dermoscopic images were also evaluated. RESULTS: In total, 30 confocal studies in 29 patients were included in the study cohort. Twenty-one patients had biopsy-confirmed recurrent LM/LMM; the remainder had pigmented actinic keratosis (n = 4) or hyperpigmentation/solar lentigo (n = 5). RCM had sensitivity of 95.24% (95% CI, 76.18-99.88%), specificity of 77.7% (95% CI, 39.99-97.19%), positive predictive value of 90.91% (95% CI, 74.58-97.15%) and negative predictive value of 87.5% (95% CI, 50.04-98.0%). The most common dermoscopic feature observed among patients with recurrent LM/LMM was focal homogeneous or structureless areas of light-brown pigmentation (92.8% vs. 37.5% in patients with other diagnoses; P = 0.009). LM-specific dermoscopic criteria were present in only 28.5% of patients with recurrent LM/LMM. CONCLUSIONS: Reflectance confocal microscopy and dermoscopy are valuable tools for the comprehensive evaluation of repigmentation within or adjacent to LM scars.

Incompletely excised lentigo maligna melanoma is associated with unpredictable residual disease: clinical features and the emerging role of reflectance confocal microscopy.

BACKGROUND: Lentigo maligna/lentigo maligna melanoma (LM/LMM) poses a treatment and surgical challenge given unpredictable subclinical extension resulting in incomplete excision. OBJECTIVES: To describe the demographic, clinical and pathologic characteristics of incompletely excised LM/LMM. To evaluate the potential role of reflectance confocal microscopy (RCM). PATIENTS AND METHODS: A retrospective review of a melanoma database at a tertiary cancer centre for patients referred with 'incompletely excised LM/LMM' or 'incompletely excised melanoma' between October 2006 and July 2017. We recorded clinical and pathological data and surgical margins needed to clear the residual LM/LMM. The second part consisted of a prospective cohort of patients in which RCM was performed when presenting with incompletely excised LM/LMM. RESULTS: We included a total of 67 patients (retrospective + prospective cohort); mean age was 64.9 (standard deviation: 11.3) years and 52.2% were males. For the retrospective cohort (n = 53), the mean scar size was 3.4 cm. The average initial margins excised prior to presentation were 4.8 mm (range 3-7 mm). The average additional margin needed to clear the residual, incompletely excised LM/LMM was 7.8 mm. For the prospective cohort (n = 14), there were no differences in age, gender or size when compared to the retrospective cohort. RCM had a diagnostic accuracy of 78.6%, a sensitivity of 90.9%, a specificity of 33.3% and a positive predictive value of 83.3% for the detection of incompletely excised LM/LMM. CONCLUSIONS: Incompletely excised LM/LMM is a poorly characterized clinical-pathological scenario that may require considerable extra margins for microscopic clearance. RCM may emerge as a valuable tool for the evaluation of patients with incompletely excised LM/LMM.

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.

Dermatoscopic features of thin (≤2 mm Breslow thickness) vs. thick (>2 mm Breslow thickness) nodular melanoma and predictors of nodular melanoma versus nodular non-melanoma tumours: a multicentric collaborative study by the International Dermoscopy Society.

BACKGROUND: Thin nodular melanoma (NM) often lacks conspicuous melanoma-specific dermatoscopic criteria and escapes clinical detection until it progresses to a thicker and more advanced tumour. OBJECTIVE: To investigate the dermatoscopic morphology of thin (≤2 mm Breslow thickness) vs. thick (>2 mm) NM and to identify dermatoscopic predictors of its differential diagnosis from other nodular tumours. METHODS: Retrospective, morphological case-control study, conducted on behalf of the International Dermoscopy Society. Dermatoscopic images of NM and other nodular tumours from 19 skin cancer centres worldwide were collected and analysed. RESULTS: Overall, 254 tumours were collected (69 NM of Breslow thickness ≤2 mm, 96 NM >2 mm and 89 non-melanoma nodular lesions). Light brown coloration (50.7%) and irregular brown dots/globules (42.0%) were most frequently observed in ≤2 mm NMs. Multivariate analysis revealed that dotted vessels (3.4-fold), white shiny streaks (2.9-fold) and irregular blue structureless area (2.4-fold) were predictors for thinner NM compared to non-melanoma nodular tumours. Overall, irregular blue structureless area (3.4-fold), dotted vessels (4.6-fold) and serpentine vessels (1.9-fold) were predictors of all NM compared to non-melanoma nodular lesions. LIMITATIONS: Absence of a centralized, consensus pathology review and cases selected form tertiary centres maybe not reflecting the broader community. CONCLUSIONS: Our study sheds light into the dermatoscopic morphology of thin NM in comparison to thicker NM and could provide useful clues for its differential diagnosis from other non-melanoma nodular tumours.