Search

Diagnosing atypical pigmented facial lesions (aPFLs) is a challenging topic for dermatologists. Accurate diagnosis of these lesions is crucial for effective patient management, especially in dermatology, where visual assessment plays a central role. Incorrect diagnoses can result in mismanagement, delays in appropriate interventions, and potential harm. AI, however, holds the potential to enhance diagnostic accuracy and provide reliable support to clinicians. This work aimed to evaluate and compare the effectiveness of machine learning (logistic regression of lesion features and patient metadata) and deep learning (CNN analysis of images) models in dermoscopy diagnosis and the management of aPFLs. This study involved the analysis of 1197 dermoscopic images of facial lesions excised due to suspicious and histologically confirmed malignancy, classified into seven classes (lentigo maligna—LM; lentigo maligna melanoma—LMM; atypical nevi—AN; pigmented actinic keratosis—PAK; solar lentigo—SL; seborrheic keratosis—SK; and seborrheic lichenoid keratosis—SLK). Image samples were collected through the Integrated Dermoscopy Score (iDScore) project. The statistical analysis of the dataset shows that the patients mean age was 65.5 ± 14.2, and the gender was equally distributed (580 males—48.5%; 617 females—51.5%). A total of 41.7% of the sample constituted malignant lesions (LM and LMM). Meanwhile, the benign lesions were mainly PAK (19.3%), followed by SL (22.2%), AN (10.4%), SK (4.0%), and SLK (2.3%). The lesions were mainly localised in the cheek and nose areas. A stratified analysis of the assessment provided by the enrolled dermatologists was also performed, resulting in 2445 evaluations of the 1197 images (2.1 evaluations per image on average). The physicians demonstrated higher accuracy in differentiating between malignant and benign lesions (71.2%) than in distinguishing between the seven specific diagnoses across all the images (42.9%). The logistic regression model obtained a precision of 39.1%, a sensitivity of 100%, a specificity of 33.9%, and an accuracy of 53.6% on the test set, while the CNN model showed lower sensitivity (58.2%) and higher precision (47.0%), specificity (90.8%), and accuracy (59.5%) for melanoma diagnosis. This research demonstrates how AI can enhance the diagnostic accuracy in complex dermatological cases like aPFLs by integrating AI models with clinical data and evaluating different diagnostic approaches, paving the way for more precise and scalable AI applications in dermatology, showing their critical role in improving patient management and the outcomes in dermatology. [ABSTRACT FROM AUTHOR]

This article discusses a case of Muir-Torre Syndrome (MTS), a variant of hereditary non-polyposis colorectal cancer (HNPCC) syndrome, in a 46-year-old man with Fitzpatrick skin phototype V. MTS is characterized by cutaneous sebaceous tumors and keratoacanthomas, and is caused by mutations in genes involved in the mismatch repair system. The patient had a family history of HNPCC and sebaceous carcinomas, and had previously undergone genetic testing. The article describes the clinical presentation, dermoscopy findings, reflectance confocal microscopy (RCM) findings, and histopathology of the patient's lesions. It also discusses the challenges of diagnosing and differentiating sebaceoma using dermoscopy and RCM, particularly in skin of color. The authors suggest that RCM can be a useful adjunctive diagnostic tool for sebaceous tumors and call for further research on rare tumor types in skin of color. [Extracted from the article]

Purpose: Even today, melanoma is a highly aggressive neoplasm with a high mortality rate. The nodular type is very aggressive and has cerebroid nests of melanocytes (CNMs) at the growth edge, morphologically similar to the poorly differentiated neoplastic epithelial cell clusters described in colorectal, breast, and endometrioid endometrial cancers. Patients and methods: We selected 25 nodular melanomas (NMs) with known molecular profiles, of which the entire paraffin-embedded lesion was available. We counted CNMs under a microscopic at a magnification of 20x (i.e., a microscopic field with a major axis of 1 mm). Based on the number of CNMs in the area, melanomas were classified into three groups: G1 (CNMs ranging from 0 to 4), G2 (CNMs ranging from 5 to 9), and G3 (CNMs ≥ 10). The presence of CNMs and their counts were compared with molecular and histopathological data. Results: Seventeen (NMs) were grouped as G1 (68%), 5 as G2 (20%), and 3 as G3 (12%) based on CNMs count. The presence of CNMs correlated with epithelioid cell morphology (p < 0.05), Clark IV and V levels (p < 0.05), vascular invasion (p < 0.05), and biological mutants (p < 0.05). Melanomas with ≥ 10 CNMs more frequently show ulceration (p < 0.02) and the BRAF V600E mutation (p < 0.02). Conclusion: CNMs count has a predictive role regardless of tumor size; their association with the BRAF V600E mutation suggests their predictive significance in response to biologics. However, further investigations are needed to strengthen this hypothesis. [ABSTRACT FROM AUTHOR]

BackgroundSome results from laboratory and epidemiologic studies suggest that diet may influence the risk of melanoma, but convincing evidence for a role of single nutrients or food items is lacking. Diet quality, which considers the combined effect of multiple food items, may be superior for examining this relation.ObjectiveWe sought to assess whether diet quality, evaluated with the use of 4 different dietary indexes, is associated with melanoma risk.MethodsIn this population-based case-control study, we analyzed the relation between 4 diet quality indexes, the Healthy Eating Index 2010 (HEI-2010), Dietary Approaches to Stop Hypertension (DASH) index, Greek Mediterranean Index (GMI), and Italian Mediterranean Index (IMI), and melanoma risk in a northern Italian community, with the use of data from 380 cases and 719 matched controls who completed a semiquantitative food frequency questionnaire.ResultsIn the overall sample, we found an inverse association between disease risk and the HEI-2010 and DASH index, but not the Mediterranean indexes, adjusting for potential confounders (skin phototype, body mass index, energy intake, sunburn history, skin sun reaction, and education). However, in sex stratified analyses, the association appeared only in women (P-trend: 0.10 and 0.04 for the HEI-2010 and DASH index, respectively). The inverse relations were stronger in women younger than age 50 y than in older women, for whom the GMI and IMI scores also showed an inverse association with disease risk (P-trend: 0.05 and 0.02, respectively).ConclusionsThese results suggest that diet quality may play a role in cutaneous melanoma etiology among women.

The dermoscopic diagnosis of amelanotic/hypomelanotic lentigo maligna/lentigo maligna melanoma (AHLM/LMM) may be very difficult in its early stages because of lack of pigment. Reflectance confocal microscopy (RCM) is an imaging technique that is especially helpful for the diagnosis of lentigo maligna. To determine the diagnostic performances of dermoscopy and RCM in the diagnosis of AHLM/LMMs we evaluated dermoscopic and RCM images of consecutive cases of histopathologically confirmed AHLM/LMMs, amelanotic/hypomelanotic basal cell carcinoma and squamous cell carcinoma (AHBCCs/AHSCCs), amelanotic/hypomelanotic benign lesions (AHBLs), and actinic keratoses (AKs) from five participating centers. Sensitivity, specificity, accuracy, predictive values, and level of diagnosis confidence were calculated for both diagnostic procedures. Both dermoscopy and RCM showed diagnostic performance >97% in the diagnosis of AHLM/LMMs versus AHBCC/AHSCCs and their combination slightly improved diagnostic performance, with accuracy increasing from 98.0% to 99.1%. Similarly, RCM in combination with dermoscopy showed a tiny increase in the diagnostic performance in the diagnosis of AHLM/LMMs versus AHBLs (accuracy increased from 87.2% to 88.8%) and versus AKs (accuracy increased from 91.4% to 93.4%). Although the increase in diagnostic performance due to RCM was modest, the combination of dermoscopy and RCM greatly increased the level of confidence; high confidence in the diagnosis of AHLM/LMMs versus AHBLs increased from 36.2% with dermoscopy alone to 76.6% with dermoscopy plus RMC. Based on our results, dermoscopy and RCM should be complementary to improve not only diagnostic accuracy but also the level of diagnostic certainty in the diagnosis of AHLM/LMMs. [ABSTRACT FROM AUTHOR]

Background: Reflectance confocal microscopy (RCM) has a defined in vivo morphology of vitiligo and re-pigmentation. Combination therapies seem more effective than monotherapies. Objective: We aim to describe the clinical and RCM features of re-pigmentation with combined narrowband ultraviolet B (NB-UVB) and piperine-based topical treatment in localized vitiligo. Methods: Eight patients enrolled at a single center received combined treatment: topical treatment was applied twice daily + NB-UVB twice weekly for 2 × 2-month periods. Clinical changes were analyzed by the Vitiligo Noticeability Scale (VNS) and percentage of re-pigmentation. The evaluator agreement was assessed. Predefined RCM features had the presence/absence of (i) blood vessels, (ii) dendritic cells, and the quantity of (i) an irregular honeycombed pattern and (ii) non-pigmented papillae. Clinical and RCM monitoring was performed at the baseline, 2, 3, 5, and 7 months. Results: Macules were "slightly less noticeable" with 25–50% re-pigmentation. Irregular honeycomb patterns and non-pigmented papillae were significantly less frequently observed, and in less extended areas (T1 vs. T2, p = 0.039; T0 vs. T1, p = 0.005 and T2 vs. T4, p = 0.033). Dendritic cells and blood vessels improved, with significant changes in blood vessels (T1 vs. T2, p = 0.005 and T3 vs. T4, p = 0.008). Conclusions: RCM confirms the morphological changes induced by combined treatment for localized vitiligo. [ABSTRACT FROM AUTHOR]

Introduction: Basal cell carcinoma (BCC) represents around 80% of all malignant skin cancers worldwide, constituting a substantial burden on healthcare systems. Due to excellent clearance rates (around 95%), surgery is the current gold-standard treatment. However, surgery is not always possible or preferred by patients. Numerous non-surgical therapies, sometimes combined, have been associated with promising tumor free survival rates (80–90%) in non-melanoma skin cancers (NMSCs). Most research has enrolled superficial basal cell carcinomas (sBCCs), with limited recent studies also involving low-risk nodular BCCs (nBCCs). Given lower efficacy rates compared to surgery, close monitoring during the follow-up period is essential for patients treated with non-surgical therapies. Monitoring with dermoscopy is constrained by low sensitivity rates. Reflectance confocal microscopy (RCM) is more sensitive in monitoring non-surgically treated NMSCs. Case presentation: A 41-year-old woman with a single nBCC relapse following photodynamic therapy (PDT) located on the dorsum of the nose presented to our center. Given the aesthetically sensitive location of the lesion and the patient's preference for a non-surgical approach, a combined treatment of CO2 laser and PDT was prescribed. A superpulsed CO2 laser (power: 0.5–3 W, frequency: 10 Hz, spot size 2 mm) with two PDT sessions (2 weeks apart) were conducted. At 6 weeks follow-up, monitoring performed with RCM revealed a reduction but not eradication of basaloid tumor islands. Another 2 sessions of PDT were recommended. At 3, 12 and 30 months of follow-up, the nasal dorsum area of the previous nBBC lesion was noted to be slightly hypopigmented (observed clinically), with a mild erythematous background (observed by dermoscopy). RCM evaluation confirmed the absence of RCM BCC criteria. The cosmetic outcome was very much improved. Conclusions: Combined CO2 laser and PDT for the treatment of a localized nBCC on the dorsum of the nose of a 41-year-old proved to offer tumor free survival at 30-month follow-up, as monitored with RCM. RCM is useful for the evaluation of non-surgical therapies as it has comparably higher sensitivity than dermoscopy and is especially useful in cases of suspected late recurrence. Further studies are needed to validate ongoing tumor free survival following this combined nonsurgical approach in the treatment of nBCC. [ABSTRACT FROM AUTHOR]

Background:Atypical pigmented facial lesions (aPFLs) often display clinical and dermoscopic equivocal and/or overlapping features, thus causing a challenging and delayed diagnosis and/or inappropriate excisions. No specific registry dedicated to aPFL paired with clinical data is available to date. Methods: The dataset is hosted on a specifically designed web platform. Each complete case was composed of the following data: (1) one dermoscopic picture; (2) one clinical picture; (3) two lesion data, that is, maximum diameter and facial location (e.g., orbital area/forehead/nose/cheek/chin/mouth); (4) patient's demographics: family history of melanoma, history of sunburns in childhood, phototype, pheomelanine, eyes/hair color, multiple nevi/dysplastic nevi on the body; and (5) acquisition device (videodermatoscope/camera-based/smartphone-based system). Results:A total of 11 dermatologic centers contributed to a final teledermoscopy database of 1,197 aPFL with a distribution of 353 lentigo maligna (LM), 146 lentigo maligna melanoma (LMM), 231 pigmented actinic keratoses, 266 solar lentigo, 125 atypical nevi, 48 seborrheic keratosis, and 28 seborrheic-lichenoid keratoses. The cheek site was involved in half of aPFL cases (50%). Compared with those with the other aPFL cases, patients with LM/LMM were predominantly men, older (69.32 ± 12.9 years on average vs. 62.69 ± 14.51), exhibited larger lesions (11.88 ± 7.74 mm average maximum diameter vs. 9.33 ± 6.46 mm), and reported a positive history of sunburn in childhood. Conclusions:The iDScore facial dataset currently represents a precious source of data suitable for the design of diagnostic support tools based on risk scoring classifiers to help dermatologists in recognizing LM/LMM among challenging aPFL in clinical practice. [ABSTRACT FROM AUTHOR]

Few studies have combined high‐resolution, non‐invasive imaging, such as standardized clinical images, reflectance confocal microscopy (RCM) and optical coherence tomography (OCT), for age‐related skin change characterization according to age groups. This study aimed to correlate clinical manifestations of ageing with skin cytoarchitectural background observed with high‐resolution, non‐invasive imaging according to age‐related skin pattern distribution. A set of 140 non‐pathological facial skin images were retrospectively retrieved from a research database. Subjects, aged between 20 and 89, were divided into 7 age groups. Clinical features were explored with VISIA, including hyperpigmentation, skin texture, wrinkles, pores and red areas, quantified and expressed as automated absolute scores. Previously described RCM and OCT epidermal and dermal features associated with ageing were investigated. All features were assessed for distribution and correlation among age groups. Significant direct correlations between age and clinical features were proven for cutaneous hyperpigmentation, skin texture, wrinkles and red areas. As age advances, RCM epidermal irregular honeycomb and mottled pigmentation are more frequently observed and collagen is more frequently coarse, huddled and curled, while the epidermis in OCT is thickened and the dermal density is decreased with more disrupted collagen fibres. RCM and OCT feature changes correlate directly and indirectly as well as correlating directly and indirectly with standardized clinical images. Clinical manifestations of ageing correlate with skin cytoarchitectural background observed with RCM and OCT. In conclusion, complimentary information between standardized clinical images and high‐resolution, non‐invasive imaging will assist in the development of future studies dedicated to skin ageing assessment and treatment effectiveness. [ABSTRACT FROM AUTHOR]