Search Results (25)

Background: Diagnosing facial melanoma, specifically lentigo maligna (LM) and lentigo maligna melanoma (LMM), is a daily clinical challenge, particularly for small or traumatized lesions. LM and LMM are part of the broader group of atypical pigmented facial lesions (aPFLs), which also includes benign look-alikes such as solar lentigo (SL), atypical nevi (AN), seborrheic keratosis (SK), and seborrheic-lichenoid keratosis (SLK), as well as pigmented actinic keratosis (PAK), a potentially premalignant keratinocytic lesion. Standard dermoscopy with handheld devices is the most widely used diagnostic tool in dermatology, but its accuracy heavily depends on the clinician’s experience and the perceived difficulty of the case. As a result, many benign aPFLs are excised for histological analysis, often leading to aesthetic concerns. Reflectance confocal microscopy (RCM) can reduce the need for biopsies, but it is limited to specialized centers and requires skilled operators. Aims: This study aimed to assess the impact of personal skill, diagnostic confidence, and perceived difficulty on the diagnostic accuracy and management in the differential dermoscopic diagnosis of aPFLs. Methods: A total of 1197 aPFLs dermoscopic images were examined on a teledermoscopic web platform by 155 dermatologists and residents with 4 skill levels (<1, 1–4, 5–8, >8 years). They were asked to give a diagnosis, to estimate their confidence and rate the case, and choose a management strategy: “follow-up”, “RCM” or “biopsy”. Diagnostic accuracy was examined according to the personal skill level, confidence level, and rating in three settings: (I) all seven diagnoses, (II) LM vs. PAK vs. fully benign aPFLs, (III) malignant vs benign aPFLs. The same analyses were performed for management decisions. Results: The diagnostic confidence has a certain impact on the diagnostic accuracy, both in terms of multi-class diagnosis of six aPFLs in diagnostic (setting 1) and in benign vs malignant (setting 3) or benign vs. malignant/premalignant discrimination (setting 2). The perceived difficulty influences the management of benign lesions, with easy ratings predominantly matching with “follow-up” decision in benign cases, but not that of malignant lesions assigned to “biopsy”. The experience level had an impact on the perception of the number of real easy cases and had no to minimal impact on the average diagnostic accuracy of aPFLs. It, however, has an impact on the management strategy and specifically in terms of error reduction, namely the lowest rates of missed malignant cases after 8 years of experience and the lowest rates of inappropriate biopsies of benign lesions after 1 year of experience. Conclusions: The noninvasive diagnosis and management of aPFLs rest on a daily challenge. Highlighting which specific subgroups of lesions need attention and second-level examination (RCM) or biopsy can help detect early malignant cases, and, in parallel, reduce the rate of unnecessary removal of benign lesions. Full article

Background/Introduction: Margin assessment in Lentigo maligna (LM) and Lentigo maligna melanoma (LMM) is challenging. Many of these lesions require extensive surgical procedures for R0 resections with unclear histological and clinical features predicting lateral spread. Recently, PRAME was described as a useful antibody to determine margins in these entities. However, several questions, like acceptable PRAME⁺ cell number and density in resection margins and optimal safety margins, especially in head and neck areas, remain. Methods: We analyzed cases of LMIS and LMM since the introduction of PRAME and before the introduction of PRAME, with more than 171 cases in total. We re-stained security margins with PRAME. Results: We identified a correlation between reported dermal mitoses in LMM and the number of surgical procedures. In many LMM cases before the widespread use of PRAME from our archives, we detected a high density of PRAME⁺ cells in melanoma security margins previously labeled tumor-free. No local recurrence could be identified in these cases, with the caveat of limited follow-up and small case numbers. Conclusions: Our findings raise important questions regarding margin assessment with PRAME and the reporting of residual cells in margins. Full article

Background: The relationship between occupational sun exposure and melanoma risk is complex and multifaceted, with existing evidence yielding contradictory findings. Unlike Non-Melanoma Skin Cancer (NMSC), for which occupational sun exposure is a well-established risk factor, the link with cutaneous melanoma remains contentious. Objectives: This study aimed to evaluate whether, in a cohort of patients with cutaneous melanoma, an association existed between occupational sun exposure and melanoma, specifically with histotype, site of occurrence, and Breslow index. Methods: This is a retrospective cohort analysis conducted to evaluate whether occupational sun exposure constitutes a risk factor for the development of cutaneous melanoma in patients diagnosed between January 2005 and October 2023 at the Dermatology Unit, Azienda USL Toscana Centro, Florence. Occupational ultraviolet (UV) exposure was examined by classifying each participant’s job into categories based on solar UV exposure levels—outdoor (e.g., agriculture and construction roles), mixed indoor/outdoor (e.g., trades and public safety professions), and indoor settings (e.g., office-based work). Results: A final total of 1417 patients were analyzed. Occupational categorization revealed that 1171 patients (82.64%) were classified as non-occupationally exposed (indoor), while 246 (17.36%) were occupationally exposed to solar UV radiation (including 14.82% mixed indoor/outdoor and 2.54% outdoor workers). A significant association was observed between occupational sun exposure and lentigo maligna, which was more prevalent among exposed workers and even more so in the outdoor subgroup. Anatomical site distribution exhibited a significant association with occupational sun exposure. Indeed occupationally exposed individuals showed a higher prevalence of melanomas in the head and neck region, a distribution pattern particularly evident among outdoor workers, suggesting that these sites may be more susceptible to chronic sun exposure in outdoor and mixed occupations. Moreover, a significant association was found between occupational exposure and Breslow thickness, with exposed workers presenting with thicker melanomas at diagnosis, suggesting more advanced disease. Conclusions: The finding of this study may reflect variations in occupational sun exposure patterns and warrants further investigation into protective measures and early-detection strategies tailored to occupational groups. Full article

Background/Objectives: Facial lesions, including lentigo maligna and lentigo maligna melanoma (LM/LMM), both malignant, present significant diagnostic challenges due to their clinical similarity to benign conditions. Although standard dermoscopy is a well-established tool for diagnosis, its inability to reveal cellular-level details highlights the necessity of new magnified techniques. This study aimed to assess the role of standard dermoscopy, high-magnification dermoscopy, and fluorescence-advanced videodermatoscopy (FAV) in diagnosing LM/LMM and differentiating them from benign facial lesions. Methods: This retrospective, observational, multicenter study evaluated 85 patients with facial skin lesions (including LM, LMM, basal-cell carcinoma, solar lentigo, seborrheic keratosis, actinic keratosis, and nevi) who underwent dermatological examination for skin tumor screening. Standard dermoscopy at 30× magnification (D30), high-magnification dermoscopy at 150× magnification (D150), and FAV examination were performed. Dermoscopic images were retrospectively evaluated for the presence of fifteen 30× and twenty-one 150× dermoscopic features, and their frequency was calculated. To compare D30 with D150 and D150 with FAV, the Gwet AC1 concordance index and the correct classification rate (CCR) were estimated. Results: Among 85 facial lesions analyzed, LM/LMM exhibited distinctive dermoscopic features at D30, including a blue–white veil (38.9% vs. 1.7%, p < 0.001), regression structures (55.6% vs. 21.7%, p = 0.013), irregular dots or globules (50.0% vs. 10%, p = 0.001), angulated lines (72.2% vs. 6.7%, p < 0.001), an annular granular pattern (61.1% vs. 20%, p = 0.002), asymmetrical pigmented follicular openings (100.0% vs. 21.7%; p < 0.001), and follicular obliteration (27.8% vs. 3.3%). At D150, roundish melanocytes (87.5% vs. 18.2%, p < 0.001) and melanophages (43.8% vs. 14.5%, p = 0.019) were predominant. FAV examination identified large dendritic cells, isolated melanocytes, and free melanin in LM/LMM (all p < 0.001) with high concordance to D150. Conclusions: Integrating D30, D150, and FAV into clinical practice may enhance diagnostic precision for facial lesions by combining macroscopic and cellular insights, thereby reducing unnecessary biopsies. However, future studies are essential to confirm these results. Full article

Background/Objectives: Facial pigmented skin lesions are extremely common, starting from the fourth to fifth decades, especially in South-European countries, often located in the periorbital region. These include malignant forms, Lentigo maligna (LM) and lentigo maligna melanoma (LMM), characterized by growing incidence, and a series of benign simulators, including solar lentigo (SL), pigmented actinic keratosis (PAK), seborrheic keratosis (SK) and lichen planus-like keratosis (LPK). The clinical differential diagnosis of atypical pigmented skin lesions (aPFLs) can be difficult, even for dermatologists, leading to inappropriate skin biopsies with consequent aesthetic impacts. Dermoscopy of the facial area is a specific dermoscopic field that requires dedicated training and proved to increase diagnostic accuracy in dermatologists. Since these lesions are often seen by ophthalmologists at first, we aimed to evaluate the effect of a focused dermoscopy training course on a group of ophthalmologists naïve to the use of a dermatoscope. Methods: A set of 80 periorbital pigmented skin lesions with both clinical and dermoscopic images was selected and evaluated by six ophthalmologists before and after a one-day intensive dermoscopic training course. They were required to evaluate 80 periorbital lesions one month before and after a one-day intensive dermoscopic training course, illustrating second-level diagnostic options such as reflectance confocal microscopy (RCM), obtaining a total of 480 evaluations. Specifically, they had to provide, for each case, a punctual diagnosis and a management option among dermoscopic follow-up/skin biopsy/RCM/LC-OCT. Descriptive statistics were carried out, and the accuracy (ACC), sensitivity (SE), and specificity (SP), with their 95% confidence interval (95% CI), were estimated. Results: In the pre-course test, ophthalmologists achieved 84.0% SP, 33.3% SE and 63.7% ACC, while after the course, SE increased by +9% (i.e., 41.7%), SP decreased by 4%, and ACC remained comparable, i.e., 64.6%. In the management study, the percentage of benign lesions for which a close dermoscopic follow-up was suggested significantly decreased (51.6% versus 22.2%), in parallel with an increase in the number of lesions referred for RCM. As for malignant cases, the reduction in responses “close dermoscopic follow-up” decreased from 37.0% to 9.9%, (−27%), in favor of RCM (+15%) and skin biopsy (+12%). Conclusions: The ophthalmologists proved to be very receptive in quickly metabolizing and putting into practice the concepts learned during the one-day intensive dermoscopy training course. Indeed, after only a one-day lesson, they were able to increase their SE by 9% and to improve their management strategy. The present findings highlight the importance of providing training ophthalmologists in dermoscopy during residency programs, in terms of benefits for the correct patient care. Full article

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. Full article

Background: In melanomas, mutations in the BRAF gene are common and their occurrence represents an early oncogenic event. Our goal was to determine and compare the frequency of BRAF gene mutations in dysplastic nevi (ND) and melanomas in situ (MIS), as well as whether there is a correlation between the presence of BRAF gene mutations and various anamnestic, clinical, and histopathologic variables. Methods: A total of 175 patients—106 with ND, 41 with MIS, and 28 with lentigo maligna (LM) were included in the study. DNA was extracted from tissue samples and analyzed using the competitive allele-specific TaqMan chain reaction by polymerase in real time to detect the presence of BRAF V600E and V600K mutations. The data were compared with anamnestic, clinical, and histopathological data. Results: There is a statistically significant correlation between the presence of BRAF mutation and the diagnosis of melanoma in situ (χ² test, χ² = 29.17, p < 0.0001). Patients with LM had a significantly lower incidence of BRAF mutations compared to patients with ND and MIS. There was a significant correlation between the presence of a BRAF mutation and tumor localization, as well as the age of the patient, but no statistically significant correlation between the presence of a BRAF mutation and sex, tumor size, or previous melanoma diagnosis. Conclusions: BRAF mutations in ND are essentially required; however, they are an insufficient oncogenic trigger for the development of melanoma. This research contributes to a better understanding of the etiopathogenesis of melanoma and the role of ND as possible precursor lesions. Full article

Background/Objectives: Lentigo maligna (LM) and lentigo maligna melanoma (LMM) are significant subtypes of melanoma, with an annual incidence of 1.37 per 100,000 people in the U.S. These skin tumors, often found in photo-exposed areas such as the face, are frequently misdiagnosed, leading to delayed treatment or unnecessary excisions, especially in the elderly. Facial melanocytic skin tumors (lentigo maligna—LM/lentigo maligna melanoma—LMM) and their simulators (solar lentigo, pigmented actinic keratosis, seborrheic keratosis and lichen planus-like keratosis) often affect the periocular region. Thus, their diagnosis and management can involve different medical figures, mainly dermatologists and ophthalmologists. This study aimed to evaluate the ability of ophthalmologists to diagnose and manage pigmented skin lesions of the periorbital area. Methods: A multicentric, retrospective, cross-sectional study on a dataset of 79 periorbital pigmented skin lesions with both clinical and dermoscopic images was selected. The images were reviewed by six ophthalmologists and two dermatologists. Descriptive statistics were carried out, and the accuracy, sensitivity, and specificity, with their 95% confidence interval (95% CI), were estimated. Results: Ophthalmologists achieved a diagnostic accuracy of 63.50% (95% CI: 58.99–67.85%), while dermatologists achieved 66.50% (95% CI: 58.5–73.8). The sensitivity was lower for ophthalmologists in respect to dermatologists, 33.3% vs. 46.9%, respectively. Concerning the case difficulty rating, ophthalmologists rated as “difficult” 84% of cases, while for dermatologists, it was about 30%. Management was also consistently different, with a “biopsy” decision being suggested in 25.5% of malignant lesions by ophthalmologists compared with 50% of dermatologists. Conclusions: Ophthalmologists revealed a good diagnostic potential in the identification of periorbital LMs/LMMs. Given progressive population ageing and the parallel increase in facial/periorbital skin tumors, the opportunity to train new generations of ophthalmologists in the early diagnosis of these neoformations should be considered in the next future, also taking into account the surgical difficulty/complexity of this peculiar facial area. Full article

Background: Cutaneous melanoma (CM) is one of the most lethal tumors among skin cancers and its incidence is rising worldwide. Recent data support the role of microRNAs (miRNAs) in melanoma carcinogenesis and their potential use as disease biomarkers. Methods: We quantified the expression of miR-146a-5p and miR-21-5p in 170 formalin-fixed paraffin embedded (FFPE) samples of CM, namely 116 superficial spreading melanoma (SSM), 26 nodular melanoma (NM), and 28 lentigo maligna melanoma (LMM). We correlated miRNA expression with specific histopathologic features including Breslow thickness (BT), histological subtype, ulceration and regression status, and mitotic index. Results: miR-146a-5p and miR-21-5p were significantly higher in NM compared to SSM and LMM. The positive correlation between miR-146a-5p and miR-21-5p expression and BT was confirmed for both miRNAs in SSM. Considering the ulceration status, we assessed that individual miR-21-5p expression was significantly higher in ulcerated CMs. The increased combined expression of the two miRNAs was strongly associated with ulceration (p = 0.0093) and higher mitotic rate (≥1/mm²) (p = 0.0005). We demonstrated that the combination of two-miRNA expression and prognostic features (BT and ulceration) can better differentiate cutaneous melanoma prognostic groups, considering overall survival and time-to-relapse clinical outcomes. Specifically, miRNA expression can further stratify prognostic groups among patients with BT ≥ 0.8 mm but without ulceration. Our findings provide further insights into the characterization of CM with specific prognostic features. The graphical abstract was created with BioRender.com. Full article

Lentigo maligna (LM) is a melanoma in situ that is prevalent in chronically sun-damaged skin. Characterized by a slow growth pattern and high mutation rates due to chronic UV exposure, LM poses diagnostic and therapeutic challenges, particularly given its tendency to mimic other skin lesions and its occurrence in cosmetically sensitive areas. Its diagnosis is based on an integrated approach using dermoscopy and reflectance confocal microscopy (RCM). Despite its slow progression, LM can evolve into lentigo maligna melanoma (LMM), making its treatment necessary. Treatment modalities encompass both surgical and non-surgical methods. Surgical treatments like Wide Local Excision (WLE) and Mohs Micrographic Surgery (MMS) aim for clear histological margins. WLE, a standard melanoma surgery, faces challenges from LM’s subclinical extensions, which increase the recurrence risk. MMS, effective for large or poorly defined lesions, is defined by precise margin control while considering cosmetic outcomes. Non-surgical options, including radiotherapy and imiquimod, are alternatives for non-surgical candidates. Radiotherapy has been effective since the 1950s, offering good control and cosmetic results, especially for older patients. Imiquimod, an immunomodulator, shows promise in treating LM, though its application remains off-label. The increasing incidence of LM/LMM necessitates a balance in treatment choices to minimize recurrence and maintain cosmetic integrity. A multidisciplinary approach, integrating clinical examination with dermoscopy and RCM and histological assessment, is essential for accurate diagnosis and effective LM management. Full article

(1) Background: Ultraviolet (UV) radiation and sunburns are associated with an increased incidence of acquired nevi and melanomas. However, the data are controversial as to whether chronic UV exposure or high intermittent UV exposure is the major carcinogenic factor in melanocytic tumors. In this study, we compared the degree of actinic elastosis (AE) as a surrogate for lifetime UV exposure in nevi and different clinical melanoma subtypes (i.e., superficial spreading melanoma (SSM), nodular malignant melanoma (NMM), acral lentiginous melanoma (ALM), and lentigo maligna melanoma (LMM)) with respect to clinical variables (age, sex, and body site). (2) Methods: We defined a semi-quantitative score for the degree of AE ranging from 0 = none to 3 = total loss of elastic fibers (basophilic degeneration) and multiplied it by the perilesional vertical extent (depth), measured histometrically (tumor-associated elastosis grade (TEG)). We matched the TEG of n = 595 melanocytic lesions from 559 patients with their clinical variables. (3) Results: The TEG was correlated with age and UV-exposed body sites. Furthermore, the TEG was significantly higher in LMM than in all other types of melanomas and the TEG in NMM was higher than in SSM, irrespective of patient age and tumor site. (4) Conclusions: High cumulative UV exposure is more strongly associated with LMM and NMM than with other melanoma subtypes. Full article

The incidence of in situ melanoma (MIS) has increased over the last decades. The mainstay of treatment for MIS, including lentigo maligna (LM), is complete surgical excision with clear margins (0.5 to 1.0 cm). Nevertheless, MIS lesions often affect elderly patients with comorbidities and involve large lesions in cosmetically sensitive areas, which means surgery is not always appropriate. Non-surgical treatments have a role in these cases, and include radiotherapy, cryosurgery, immunotherapy, laser therapy, and other topical medications. This study aims to review the applications of immunotherapy in MIS, either in monotherapy or in combination with other therapeutic alternatives. The main forms of immunotherapy used are imiquimod and, to a lesser extent, intralesional interferon-α (IL-INF-α) and ingenol mebutate (IM). IL-INF-α and IM have not been studied as extensively as imiquimod, whose results in real-life practice are encouraging. The clearance and recurrence rates reported in MIS treated with imiquimod as monotherapy, or as an adjuvant after surgery with affected or narrow margins, make imiquimod a reliable therapeutic alternative in selected cases. Also, its use as a neoadjuvant therapy before surgery was shown to reduce the final surgical defect size required to confirm negative histologic margins. In conclusion, local immunotherapy is frequently used in clinical practice and experience confirms it to be an excellent option for certain patients. Full article

(1) Introduction: The association between melanoma (MM) and the occurrence of second primary neoplasms (SPNs) has been extensively studied, with reported incidence rates ranging from 1.5% to 20%. This study aims to evaluate the occurrence of SPNs in patients with a history of primary MM and to describe the factors that make the risk higher in our population. (2) Material and Methods: We conducted a prospective cohort study and calculated the incidence rates and relative risks (RR) for the development of different SPNs in 529 MM survivors from 1 January 2005 to 1 August 2021. Survival and mortality rates were obtained, and the Cox proportional hazards model was used to determine the demographic and MM-related factors that influence the overall risk. (3) Results: Among the 529 patients included, 89 were diagnosed with SPNs (29 prior to MM diagnosis, 11 synchronous, and 49 after MM), resulting in 62 skin tumors and 37 solid organ tumors. The estimated probability of developing SPNs after MM diagnosis was 4.1% at 1 year, 11% at 5 years, and 19% at 10 years. Older age, primary MM location on the face or neck, and histologic subtype of lentigo maligna mm were significantly associated with a higher risk of SPNs. (4) Conclusions: In our population, the risk of developing SPNs was higher in patients with primary MM located on the face and neck and with the histological subtype of lentigo maligna-MM. Age also independently influences the risk. Understanding these hazard factors can aid in the development of MM guidelines with specific follow-up recommendations for individuals with the highest risk. Full article

Background: The study investigated the long-term efficacy of imiquimod 5% cream for LM, with a focus on disease recurrence and the possible prognostic factors of disease-free survival (DFS) in a cohort, with long-term follow-up. Methods: Consecutive patients with histologically confirmed LM were included. Imiquimod 5% cream was applied until weeping erosion appeared on the LM-affected skin. The evaluation was performed through clinical examination and dermoscopy. Results: We analyzed 111 patients with LM (median age: 72 years, 61.3% women) with tumor clearance after imiquimod therapy, with a median follow-up of 8 years. The overall patient survival rates were 85.5% (95% confidence interval (CI): 78.5–92.6) and 70.4% (95% CI: 60.3–80.5) at 5 and 10 years, respectively. Among the 23 patients (20.1%) with relapse at follow-up, 17 (73.9%) were treated with surgery, five (21.7%) continued imiquimod therapy, and one (4.3%) underwent both surgery and radiotherapy. After adjustment for age and LM area in multivariable models, localization of LM in the nasal region was identified as a prognostic factor for DFS (HR = 2.66; 95% CI: 1.06–6.64). Conclusion: If surgical excision is not possible due to the patients’ age/comorbidities or critical cosmetic localization, imiquimod could provide optimal outcomes with an optimal risk of relapse for the management of LM. Full article

Lentigo maligna (LM) is an early form of pre-invasive melanoma that predominantly affects sun-exposed areas such as the face. LM is highly treatable when identified early but has an ill-defined clinical border and a high rate of recurrence. Atypical intraepidermal melanocytic proliferation (AIMP), also known as atypical melanocytic hyperplasia (AMH), is a histological description that indicates melanocytic proliferation with uncertain malignant potential. Clinically and histologically, AIMP can be difficult to distinguish from LM, and indeed AIMP may, in some cases, progress to LM. The early diagnosis and distinction of LM from AIMP are important since LM requires a definitive treatment. Reflectance confocal microscopy (RCM) is an imaging technique often used to investigate these lesions non-invasively, without biopsy. However, RCM equipment is often not readily available, nor is the associated expertise for RCM image interpretation easy to find. Here, we implemented a machine learning classifier using popular convolutional neural network (CNN) architectures and demonstrated that it could correctly classify lesions between LM and AIMP on biopsy-confirmed RCM image stacks. We identified local z-projection (LZP) as a recent fast approach for projecting a 3D image into 2D while preserving information and achieved high-accuracy machine classification with minimal computational requirements. Full article