Artificial Intelligence-Assisted reflectance confocal microscopy for Real-Time intraoperative margin assessment in oral squamous cell carcinoma.

We prospectively enrolled 131 lesions of 104 patients to confirm or rule out the diagnosis of BCC. Dermoscopy, line-field optical coherence tomography (LC-OCT), and Reflectance confocal microscopy 1500 (RCM) images were evaluated by one blinded expert (OM). The primary objective of this study was to assess the diagnostic performance of LC-OCT in lesions clinically suspicious for basal cell carcinoma (BCC), by determining the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of this technique. Diagnostic performances were evaluated in two distinct real-life settings: lesions for which tissue-coupled reflectance confocal microscopy (RCM) served as the reference standard, and lesions for which histopathological examination following biopsy was used as the reference standard. The secondary objectives were to assess clinician confidence when using dermoscopy, LC-OCT, and RCM, and to estimate the agreement rate between LC-OCT and RCM findings. Design: Single-center, nonrandomized, blinded, prospective, observational study. OptiSkin. Patients with Fitzpatrick Skin Types I-IV between the ages of 29-92 years from OptiSkin are eligible for this study. Clinical, dermoscopic, and LC-OCT images were obtained for all subjects. Further, measurements on the lesion included either an RCM examination or a traditional cutting biopsy, depending on body location, insurance coverage, or patient preference. At each stage, the clinician provided her confidence level in her diagnosis. A total of 131 lesions clinically suspicious for BCC were imaged with LC-OCT in 104 patients. LC-OCT successfully imaged all 131 lesions, including those in challenging anatomical regions inaccessible to RCM, such as the nose. Tissue-coupled RCM was performed on 63 lesions, for which LC-OCT achieved 95.9% sensitivity, 85.7% specificity, and 93.7% accuracy (PPV 95.9%, NPV 85.7%). This analysis revealed four disagreements: two FN and two FP. The remaining 68 lesions, diagnosed with histology, showed 86.4% sensitivity, 79.2% specificity, and 83.8% accuracy (PPV 88.4%, NPV 76.0%). This analysis revealed 11 disagreements, 6 FN, and 5 FP. Using RCM or histology when available as the gold standard, LC-OCT had an overall sensitivity of 91.2%, specificity of 77.50%, and accuracy of 86.92%. For the 63 lesions evaluated with both LC-OCT and RCM, the agreement rate was 93.6% (Cohen's Kappa 0.81), with only 4 diagnostic discrepancies (2 FN and 2 FP). High-confidence LC-OCT diagnoses (≥ 8/10) achieved 100% sensitivity. Our findings demonstrate that LC-OCT provides high sensitivity, specificity, accuracy, PPV, and NPV when tested against both tissue-coupled RCM and histopathology. LC-OCT was easy to use in challenging facial regions where the RCM device can be difficult to operate. This high diagnostic accuracy suggests that LC-OCT may reduce the need for immediate biopsy, streamline clinical decision-making, and minimize scarring, thereby improving cosmetic outcomes. Although the widespread adoption of LC-OCT in the United States remains limited by current reimbursement barriers, this technology has the potential to become an essential tool in modern dermatologic oncology.

Noninvasive Imaging Modalities for Evaluating Patch Testing: A Systematic Review.

Accurate staging of vitiligo is essential for effective treatment. Current staging primarily relies on clinical manifestations, patients' subjective reports, and physicians' assessments, which may introduce inaccuracies. Reflectance confocal microscopy (RCM) and dermoscopy are auxiliary diagnostic tools in dermatology that support the diagnosis and differentiation of vitiligo; they also assist in staging and evaluating therapeutic efficacy. This study aimed to compare the sensitivity and specificity of RCM and dermoscopy in vitiligo staging, providing a more reliable reference for clinical application. A retrospective review was conducted of clinical and imaging data from 218 patients with vitiligo who attended the Department of Dermatology at Wuhan No. 1 Hospital between December 2023 and November 2024. Clinical assessment methods-clinical features, Vitiligo Disease Activity score, Wood's lamp examination, and Koebner phenomenon-served as the reference standard for staging. Blinded evaluators independently conducted staging using RCM and dermoscopy. Each modality's sensitivity and specificity were calculated. Staging results based on RCM and dermoscopy showed strong concordance with clinical evaluation; Kappa values were 0.74 and 0.718, respectively (p < 0.01). The positive percent agreement and negative percent agreement of RCM staging with clinical assessment were 94.16% and 78.12%, respectively; those metrics for dermoscopy were 87.01% and 89.06%. RCM demonstrated significantly higher sensitivity than dermoscopy (p = 0.013), whereas dermoscopy showed significantly higher specificity than RCM (p = 0.039). RCM and dermoscopy provide significant clinical value in vitiligo staging. RCM shows higher positive percent agreement for detecting progressive disease, whereas dermoscopy shows higher negative percent agreement for confirming stable disease. These tools offer an objective foundation for assessment and support clinical decision-making.

Basal cell carcinoma (BCC) is the most common type of skin carcinoma affecting the elderly worldwide, and it is the central focus of this study. Our research aims to evaluate the diagnostic effectiveness of various methods, including dermatoscopy (DE), high-frequency ultrasound (HFU), optical coherence tomography (OCT), reflectance confocal microscopy (RCM), and histopathological examination (HPE). This comparison was accomplished through a network meta-analysis of patients diagnosed with BCC. A comprehensive literature search was conducted across seven databases. Following this, both direct and indirect evidence were synthesized to assess the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of each diagnostic method. This thorough analysis helped to estimate the odds ratios (ORs) for different methods and calculate the surface under the cumulative ranking curve (SUCRA) values, offering a deeper insight into the diagnosis of BCC. The network meta-analysis integrated data from six eligible diagnostic trials. The results revealed that dermoscopy combining optical coherence tomography (DE-OCT) achieved the highest sensitivity (88.8%), specificity (70.7%), and NPV (84.2%), with the highest SUCRA value, indicating superior diagnostic performance. However, dermoscopy combining high-frequency ultrasound (DE-HFU) demonstrated the highest accuracy (90.1%) and PPV (73.8%). The sensitivity and accuracy for OCT (55.5%, 47.4%) and RCM (52.2%, 55.7%) were similar, with both methods ranking highest in these aspects. This network meta-analysis has several limitations, including the limited number of comparisons and potential heterogeneity across the original studies. This network meta-analysis found DE-OCT and DE-HFU most effective for BCC diagnosis, but further validation in larger studies is needed. Still, it offers initial guidance for clinical tool selection.

Imaging and machine learning reveal pigment ring spatial characteristics in vitiligo progression.

Secondary intent healing is a viable option for wound closure after facial tumour removal by Mohs micrographic surgery. Secondary intent healing involves prolonged healing time and carries risk of infection and complications related to scarring. Healing with an autologous patch made from the patient's own blood may be beneficial. This study on 22 patients evaluates the effect of applying an autologous patch to the wound after Mohs micrographic surgery. A randomized controlled assessor-blinded trial was carried out. Patients had Mohs micrographic surgery on day 0 and clinical evaluation on day 12, day 19, and after 6 months. Transepidermal water loss was measured on day 12 and day 19. Reflectance confocal microscopy was applied exploratively. At 6 months' follow-up the Patient and Observer Scar Assessment Scale was evaluated. Primary outcome was fully epithelialized wounds on day 19 and secondary outcome was 50% epithelialized wounds on day 12. One wound from each group was fully epithelialized and wound area reduction was higher in the patch group although not significant. Transepidermal water loss decreased to a larger extent, indicating that the patch creates a moist environment. Wound healing with an autologous patch is equivalent to secondary intent healing but may prompt benefits in certain wound healing factors. Patch healing appears safe with high patient satisfaction.

Skin imaging techniques for melanoma detection: A scoping review of modalities, clinical viability, and deployment strategies.

Cutaneous lupus erythematosus (CLE), particularly discoid lupus erythematosus (DLE), is a chronic autoimmune condition driven in part by type I interferon signaling. No systemic therapies are specifically approved for CLE, and management is often extrapolated from systemic lupus erythematosus. Deucravacitinib, a selective oral tyrosine kinase 2 (TYK2) inhibitor targeting the Janus kinase (JAK)-signal transducer and activator of transcription (STAT) pathway, has shown efficacy in psoriasis and emerging promise in lupus. We describe a 29-year-old woman with biopsy-proven DLE refractory to prednisone and hydroxychloroquine who subsequently developed moderate-to-severe plaque psoriasis (Psoriasis Area and Severity Index [PASI] 16). Initial treatment with ixekizumab improved psoriasis but failed to control DLE, and psoriatic lesions later relapsed. Therapy was switched to deucravacitinib 6mg daily. After 9weeks, marked improvement of both conditions was observed (PASI 0.2) with progressive regression of DLE lesions. By week 27, complete clinical remission of psoriasis (PASI 0) and full resolution of DLE lesions were achieved, confirmed by reflectance confocal microscopy. This case highlights the potential of deucravacitinib as an effective therapeutic option for refractory DLE, particularly in patients with concomitant psoriasis, supporting TYK2 inhibition as a promising targeted strategy in cutaneous autoimmunity.

Diagnostic Application of Bedside Reflectance Confocal Microscopy in Viral Skin Diseases: A case series.

Actinic keratosis (AK) reflects a field cancerization process in chronically sun-damaged skin, and relapse after diclofenac therapy is a frequent clinical scenario. Field-directed treatments such as 5-fluorouracil (5-FU), tirbanibulin, and photodynamic therapy (PDT) are widely used, yet comparative data in post-diclofenac relapse and the contribution of reflectance confocal microscopy (RCM) to therapeutic monitoring remain limited. To compare the clinical efficacy, tolerability, and subclinical response of 5-FU 4%, tirbanibulin 1%, and PDT in relapsing AK of the scalp, integrating RCM imaging to assess field response. A prospective randomized (1:1:1) study was conducted in 45 patients who previously achieved complete clearance with diclofenac 3% and relapsed within 12 months. Endpoints included clinical clearance at 12 weeks, RCM normalization, recurrence at 6 months, and local skin response (LSR) severity. Twelve-week clearance rates were 73.3% for 5-FU, 66.7% for tirbanibulin, and 80.0% for PDT (p=0.711). RCM normalization occurred in 66.7%, 60.0%, and 73.3% of patients, respectively (p=0.741). Recurrence among responders at 6 months was low and comparable (9.1%, 10.0%, and 8.3%; p=0.991). Tirbanibulin showed significantly lower LSR scores versus 5-FU and PDT (p<0.001), indicating superior tolerability. Short-term efficacy of 5-FU, tirbanibulin, and PDT was comparable, while tolerability differed markedly. Tirbanibulin demonstrated the most favorable inflammatory and cosmetic profile, whereas 5-FU and PDT may be preferred when a more intense field effect is desired. RCM detected subclinical persistence in select cases and may serve as an adjunctive imaging tool for monitoring and guiding retreatment in field cancerization.

Demodicosis comprises a spectrum of cutaneous conditions resulting from the overproliferation of Demodex mites. Multiple diagnostic techniques are available, although diagnosis can be challenging due to the presence of these mites as commensals in healthy individuals. Thus, the objective of this review is to evaluate the diagnostic performance of methods used for the diagnosis of demodicosis. A search was conducted on articles published between 2000 and 2025, using PubMed, Embase, Scopus, Cochrane Library and Dialnet to identify studies on diagnostic methods for cutaneous demodicosis. Of 1765 records screened, 18 studies met the inclusion criteria, focusing on diagnostic accuracy. A total of 3 cross-sectional, 8 prospective, 3 retrospective, 2 case-control studies and 2 controlled clinical trials have been included. These studies evaluated the diagnostic performance of standardized skin surface biopsy, direct microscopic examination, dermoscopy, reflectance confocal microscopy and molecular techniques in a combined population of 2187 patients. Direct microscopic examination and dermoscopy have been the most frequently used techniques in the enrolled studies. Among the genetic techniques, next-generation sequencing and polymerase chain reaction have been assessed. To our knowledge, this is the first systematic review dealing with diagnostic methods for demodicosis. Due to the heterogeneity of the included studies, identifying an optimal diagnostic method remains challenging. Therefore, diagnostic approaches should be selected according to clinical context and resource availability.

Diagnostic and therapeutic challenges in mammary and extra-mammary Paget disease: a retrospective case series.

Lentigo maligna (LM), traditionally observed in older adults, is increasingly reported among younger patients, in whom diagnostic suspicion is lower. To characterize clinical, dermoscopic, and reflectance confocal microscopy (RCM) features of LM in patients under and over 50 years of age. This retrospective, single-centre study analyzed 200 patients with 229 biopsy-confirmed LM lesions diagnosed between 2018 and 2023. Patients were stratified by age (<50 vs ≥50 years). Clinical presentation, dermoscopic features, and RCM findings were analyzed using chi-square, Mann-Whitney U tests, and linear regression (P < .05). Of 229 lesions, 33 occurred in patients <50 years. Younger patients, predominantly female (57% vs 40%, P = .067), showed less chronic actinic damage (41% vs 83%, P < .001) and more frequent trunk (36%) or lower limb (31%) lesions compared to older patients (face/neck 26.7%, trunk 40%, P = .004). Lesions in younger patients tended to be more clinically noticeable and solitary, but showed fewer dermoscopic features (mean 3.26 vs 6.92, P < .001). The 4 most common dermoscopic patterns-central featureless areas, irregular pigmentation foci, asymmetrical follicular pigmentation, and angular lines-though less frequent in younger patients, remain useful for early LM diagnosis. All lesions displayed at least 1 atypical colour, with dark brown being the most frequent (87%). RCM (23 younger, 145 older patients) revealed cytoarchitectural atypia. Invasion rates (21.2% vs 22.6%, P = .86) were similar. LM in younger patients presents as clinically prominent but dermoscopically subtle lesions, necessitating heightened suspicion. The use of RCM may be of value to ensure accurate diagnosis and avoid inappropriate treatments.

Oral mucosal melanoma (OMM) is a rare and aggressive malignancy that differs markedly from cutaneous melanoma in terms of epidemiology, genetic characteristics, clinical presentation, and treatment response. Despite advances in understanding OMM pathogenesis and the development of novel therapeutic strategies, early diagnosis remains challenging due to its low prevalence, anatomically concealed locations, and frequent multifocality. This review emphasizes the importance of the early detection of OMM using non-invasive imaging methods-specifically dermoscopy and reflectance confocal microscopy (RCM)-and explores their potential role in guiding treatment decisions, preventing disease progression, and improving prognosis. A narrative review of the PubMed database was conducted using the terms "oral melanoma," "oral melanoma dermoscopy," and "oral melanoma reflectance confocal microscopy." Seventy-two relevant review articles were included. In addition, two illustrative clinical cases from our practice are presented to demonstrate the diagnostic value of non-invasive imaging techniques. Although biopsy and histopathology remain the diagnostic gold standards, they are invasive, time-consuming, and may be poorly tolerated, particularly in patients with multifocal lesions. Dermoscopy and RCM provide real-time, high-resolution imaging that enables the detection of early tissue abnormalities not visible to the naked eye. These techniques show good correlation with clinical and histopathological findings, thereby enhancing diagnostic accuracy and facilitating follow-up without the need for repeated biopsies. In our cases, they were instrumental in identifying recurrence and guiding clinical management. However, several limitations should be considered, including restricted accessibility, anatomical constraints, and the requirement for specialized training and expertise. Non-invasive imaging techniques may support clinicians in the early recognition and evaluation of suspicious oral lesions; however, histopathologic examination remains essential for definitive diagnosis. Wider implementation and further technological refinement are needed to optimize their integration into clinical practice.

Pigmented Bowen disease (pBD) may closely mimic lentigo maligna (LM) both clinically and dermoscopically. Accurate differentiation between these entities is clinically crucial, as misclassification may lead to overtreatment or undertreatment. Noninvasive imaging techniques, including dermoscopy and reflectance confocal microscopy (RCM), have improved diagnostic accuracy, but direct comparative data between pBD and LM remain limited. This observational cohort study included 10 consecutive cases of pBD and 10 consecutive cases of LM diagnosed between January and July 2024 at a tertiary referral dermatologic oncology center. All lesions were located on the head and neck and underwent dermoscopic and/or RCM evaluation prior to definitive diagnosis. Epidemiological, clinical, dermoscopic, and confocal features were retrospectively analyzed and compared between groups. The median age at diagnosis did not differ significantly between pBD and LM (64 vs. 56 years; p = 0.29). Surface scale was significantly more frequent in pBD (70.0% vs. 10.0%; p = 0.020). Dermoscopy showed substantial overlap between groups, although follicular-centric gray patterns were more commonly observed in LM. RCM demonstrated the highest discriminatory value: disarrayed keratinocytes were present in all pBD lesions compared with 30.0% of LM lesions (p = 0.003), while pagetoid cells were significantly more frequent in LM (70.0% vs. 10.0%; p = 0.020). In conclusion, a multimodal imaging approach integrating dermoscopy and RCM improves diagnostic discrimination between pBD and LM. RCM provides decisive cellular-level information and represents a valuable second-level tool in the evaluation of equivocal pigmented lesions.

Abstract Aims Skin cancer is one of the most common malignancies, with &amp;gt;17 000 melanoma diagnoses annually in the UK (2016–2019). This review assessed non-invasive diagnostic methods for skin cancer and their potential role as alternatives or adjuncts to clinician face-to-face assessment. Methods A literature search of PubMed, Medline, and Embase identified studies reporting diagnostic accuracy, sensitivity, specificity, and outcomes (N = 208). Results Lesions were classified as malignant or as melanoma, squamous cell carcinoma (SCC), or basal cell carcinoma (BCC). Reflectance Confocal Microscopy (RCM) demonstrated high sensitivity for BCC (0.911) and, when combined with dermatoscopic interpretation, achieved sensitivity of 0.948 for malignancy and 0.931 for melanoma. However, application is limited by small study sizes, high cost, and the need for specialist expertise. Artificial intelligence (AI) analysis of dermatoscopic images outperformed clinicians for diagnosing malignancy (AI versus all clinicians: 0.837 versus 0.777, P &amp;lt; 0.0001; AI versus specialists: 0.837 versus 0.744, P &amp;lt; 0.0001), melanoma (0.869 versus 0.802 and 0.869 versus 0.819, both P &amp;lt; 0.0001), and BCC (0.891 versus 0.847, P &amp;lt; 0.0001). AI using both clinical and dermatoscopic images achieved higher sensitivity for melanoma compared with combined clinician and dermatoscopic assessment (0.869 versus 0.802, P &amp;lt; 0.0001) and experts (0.869 versus 0.819, P &amp;lt; 0.0001), though evidence remains limited for BCC and SCC. Conclusions AI-based diagnostic tools can improve skin lesion triage, referral optimisation, clinical decision making and remote assessment, particularly in primary care settings.

The correct diagnosis of basal cell carcinoma (BCC) histopathological subtype is crucial for treatment design. Although the diagnostic accuracy of reflectance confocal microscopy (RCM) and dermoscopy for BCC has been studied, the literature of RCM and dermoscopy in predicting BCC subtype remain limited. To assess the diagnostic accuracy of confocal and dermoscopic criteria for predicting BCC subtype. Confocal and dermoscopic images of histopathologically confirmed BCC were retrospectively analyzed. Multivariate and adjusted odds ratios were computed, along with sensitivity and specificity. Receiver operating characteristic (ROC) curve was plotted, and the area under the curve (AUC) was calculated. The study included 103 patients with 124 lesions. And 84 (105 lesions) were assigned to the confocal analysis group and 49 (62 lesions) to the dermoscopic analysis group. Multivariate analysis yielded three confocal models for predicting a diagnosis of nodular BCC (nBCC) with sensitivity of 91.7% and specificity of 80.7% (AUC, 0.913), superficial BCC (sBCC) with sensitivity of 82.3% and specificity of 91.5% (AUC, 0.932), and aggressive BCC (aBCC) with sensitivity of 87.5% and specificity of 97.8% (AUC, 0.945). We developed three dermoscopic models for diagnosing nBCC with sensitivity of 76.5% and specificity of 82.1% (AUC, 0.891), sBCC with sensitivity of 95.0% and specificity of 95.2% (AUC, 0.973), and aBCC with sensitivity of 62.5% and specificity of 90.7% (AUC, 0.849). Both RCM and dermoscopy are reliable tools for the identification of BCC subtypes. RCM is more accurate for nBCC and aBCC, whereas dermoscopy is more accurate for sBCC.

Lentigo maligna (LM) is a subtype of cutaneous melanoma insitu that develops on chronically sun-damaged skin in elderly individuals. Its diagnosis and management remain challenging due to its slow progression, frequent occurrence on cosmetically sensitive areas in frail individuals, and tendency for subclinical peripheral extension. Despite its potential for invasive transformation, the natural history of LM remains incompletely understood and evidence-based management strategies for this specific entity remain limited. This work aims to bridge the gap between scarce high-quality evidence and the clinicians' need for practical guidance on LM management by formulating evidence-based and expert consensus-driven recommendations for diagnosis, treatment and follow-up. Under the coordination of the International Dermoscopy Society, a global, multidisciplinary consortium of 53 experts-including dermatologists, dermato-oncologists, dermatologic surgeons, radiologists, radiotherapists, pathologists and epidemiologists-formulated recommendations through structured consensus, informed by a comprehensive review of current scientific evidence and clinical practice standards. Optimal management of LM requires accurate diagnosis and individualized treatment planning. Non-invasive skin imaging techniques, especially dermoscopy and reflectance confocal microscopy, aid in diagnosis, biopsy orientation, lesion delineation and post-treatment monitoring. Multiple partial biopsies help confirm diagnosis and rule out invasion. Complete surgical excision remains the first treatment option. No definitive safety margins can be recommended for standard surgery; margin-controlled techniques are preferable for large or ill-defined lesions. Topical imiquimod and radiotherapy are effective alternatives where surgery is unsuitable. Topical imiquimod is useful as primary, adjuvant or neoadjuvant therapy. Blind destructive methods should be avoided. Close clinical and imaging follow-up is needed. Patient-centred care, shared decision-making, and a multidisciplinary approach are critical for optimal outcomes. These international consensus recommendations summarize current best practices for LM management, offering practical, evidence-informed guidance to clinicians while acknowledging the potential of future research in refining these conclusions.

Introduction and Purpose: Vitiligo is a chronic, acquired autoimmune disorder characterized by the selective destruction of melanocytes, leading to the appearance of well-defined depigmented patches affecting the skin and mucous membranes. It is estimated to affect approximately 0.5 – 2% of the global population. Even though it was once regarded as mainly a cosmetic condition, now it is increasingly being recognized as a systemic disease with substantial psychological consequences. This review aims to summarize current knowledge regarding its genetic background, key immunological pathways and the emerging therapeutic approaches, constantly reshaping patient outcomes. Description of The State of Knowledge: Recent research has highlighted the complex nature of vitiligo pathogenesis, involving oxidative stress, genetic predisposition and immune-mediated mechanisms. In particular, the IFN-γ-chemokine axis, including CXCL9 and CXCL10, appears to play a central role in melanocyte loss. Clinically, Segmental Vitiligo usually follows a unilateral, dermatomal pattern and is often linked to somatic mosaicism, whereas Non-segmental Vitiligo remains as the most common form and typically presents with symmetrical distribution. Diagnostic precision has also advanced, through the introduction of non-invasive imaging techniques, including reflectance confocal microscopy and molecular biomarkers. From a therapeutic perspective, treatment strategies have moved beyond traditional phototherapy and topical agents to targeted interventions, most notably Janus Kinase inhibitors with ruxolitinib, representing one of the most promising options. Surgical procedures may also be considered in carefully selected patients with stable disease. Conclusions: Despite remaining a challenging dermatological condition, the progress made in understanding the immunological and molecular mechanisms underlying vitiligo, has opened new possibilities for more targeted and effective treatment. The modern approach increasingly combines precise diagnostic evaluation with individualized therapeutic strategies. Effective management now requires a holistic approach that balances both medical and psychological aspects faced by patients.