New horizons in dermatological education: Skin cancer screening with virtual reality.

BACKGROUND: Technological advances in the field of virtual reality (VR) offer new opportunities in many areas of life, including medical education. The University of Münster has been using VR scenarios in the education of medical students for several years, especially for situations that are difficult to reproduce in reality (e.g., brain death). Due to the consistently positive feedback from students, a dermatological VR scenario for skin cancer screening was developed. OBJECTIVES: Presentation and first evaluation of the skin cancer screening VR scenario to determine to what extent the technical implementation of the scenario was evaluated overall by the students and how their subjective competence to perform a skin cancer screening changed over the course of the teaching unit (theory seminar, VR scenario, theoretical debriefing). METHODS: Students (n = 140) participating in the curricular pilot project during the 2023 summer term were surveyed throughout the teaching unit using several established questionnaires (System Usability Scale, Simulation Task-Load-Index, Realism and Presence Questionnaire) as well as additional questions on cybersickness and subjective learning. RESULTS: (i) The use of VR is technically feasible, (ii) students evaluate the VR scenario as a useful curricular supplement, and (iii) from the students' subjective perspective, a good learning outcome is achieved. Although preparation and follow-up appear to be important for overall learning, the greatest increase in subjective competence to perform a skin cancer screening is achieved by the VR scenario. CONCLUSIONS: Technically feasible and positively evaluated by students, VR can already be a useful addition to dermatology education, although costs are still high. As a visual discipline, dermatology offers special opportunities to create VR scenarios that are not always available or comfortable for patients in reality. Additionally, VR scenarios guarantee the same conditions for all students, which is essential for a high-quality education.

Histology-based classifier to distinguish early mycosis fungoides from atopic dermatitis.

BACKGROUND: Histopathological differentiation of early mycosis fungoides (MF) from benign chronic inflammatory dermatoses remains difficult and often impossible, despite the inclusion of all available diagnostic parameters. OBJECTIVE: To identify the most impactful histological criteria for a predictive diagnostic model to discriminate MF from atopic dermatitis (AD). METHODS: In this multicentre study, two cohorts of patients with either unequivocal AD or MF were evaluated by two independent dermatopathologists. Based on 32 histological attributes, a hypothesis-free prediction model was developed and validated on an independent patient's cohort. RESULTS: A reduced set of two histological features (presence of atypical lymphocytes in either epidermis or dermis) was trained. In an independent validation cohort, this model showed high predictive power (95% sensitivity and 100% specificity) to differentiate MF from AD and robustness against inter-individual investigator differences. LIMITATIONS: The study investigated a limited number of cases and the classifier is based on subjectively evaluated histological criteria. CONCLUSION: Aiming at distinguishing early MF from AD, the proposed binary classifier performed well in an independent cohort and across observers. Combining this histological classifier with immunohistochemical and/or molecular techniques (such as clonality analysis or molecular classifiers) could further promote differentiation of early MF and AD.

ExAID: A multimodal explanation framework for computer-aided diagnosis of skin lesions.

BACKGROUND AND OBJECTIVES: One principal impediment in the successful deployment of Artificial Intelligence (AI) based Computer-Aided Diagnosis (CAD) systems in everyday clinical workflows is their lack of transparent decision-making. Although commonly used eXplainable AI (XAI) methods provide insights into these largely opaque algorithms, such explanations are usually convoluted and not readily comprehensible. The explanation of decisions regarding the malignancy of skin lesions from dermoscopic images demands particular clarity, as the underlying medical problem definition is ambiguous in itself. This work presents ExAID (Explainable AI for Dermatology), a novel XAI framework for biomedical image analysis that provides multi-modal concept-based explanations, consisting of easy-to-understand textual explanations and visual maps, to justify the predictions. METHODS: Our framework relies on Concept Activation Vectors to map human-understandable concepts to those learned by an arbitrary Deep Learning (DL) based algorithm, and Concept Localisation Maps to highlight those concepts in the input space. This identification of relevant concepts is then used to construct fine-grained textual explanations supplemented by concept-wise location information to provide comprehensive and coherent multi-modal explanations. All decision-related information is presented in a diagnostic interface for use in clinical routines. Moreover, the framework includes an educational mode providing dataset-level explanation statistics as well as tools for data and model exploration to aid medical research and education processes. RESULTS: Through rigorous quantitative and qualitative evaluation of our framework on a range of publicly available dermoscopic image datasets, we show the utility of multi-modal explanations for CAD-assisted scenarios even in case of wrong disease predictions. We demonstrate that concept detectors for the explanation of pre-trained networks reach accuracies of up to 81.46%, which is comparable to supervised networks trained end-to-end. CONCLUSIONS: We present a new end-to-end framework for the multi-modal explanation of DL-based biomedical image analysis in Melanoma classification and evaluate its utility on an array of datasets. Since perspicuous explanation is one of the cornerstones of any CAD system, we believe that ExAID will accelerate the transition from AI research to practice by providing dermatologists and researchers with an effective tool that they can both understand and trust. ExAID can also serve as the basis for similar applications in other biomedical fields.

EGFR/Ras-induced CCL20 production modulates the tumour microenvironment.

BACKGROUND: The activation of the EGFR/Ras-signalling pathway in tumour cells induces a distinct chemokine repertoire, which in turn modulates the tumour microenvironment. METHODS: The effects of EGFR/Ras on the expression and translation of CCL20 were analysed in a large set of epithelial cancer cell lines and tumour tissues by RT-qPCR and ELISA in vitro. CCL20 production was verified by immunohistochemistry in different tumour tissues and correlated with clinical data. The effects of CCL20 on endothelial cell migration and tumour-associated vascularisation were comprehensively analysed with chemotaxis assays in vitro and in CCR6-deficient mice in vivo. RESULTS: Tumours facilitate progression by the EGFR/Ras-induced production of CCL20. Expression of the chemokine CCL20 in tumours correlates with advanced tumour stage, increased lymph node metastasis and decreased survival in patients. Microvascular endothelial cells abundantly express the specific CCL20 receptor CCR6. CCR6 signalling in endothelial cells induces angiogenesis. CCR6-deficient mice show significantly decreased tumour growth and tumour-associated vascularisation. The observed phenotype is dependent on CCR6 deficiency in stromal cells but not within the immune system. CONCLUSION: We propose that the chemokine axis CCL20-CCR6 represents a novel and promising target to interfere with the tumour microenvironment, and opens an innovative multimodal strategy for cancer therapy.

Ingenol mebutate induces a tumor cell-directed inflammatory response and antimicrobial peptides thereby promoting rapid tumor destruction and wound healing.

BACKGROUND: Ingenol mebutat (IM)-gel is effective for the topical treatment of epithelial tumors, including actinic keratoses (AKs) or anogenital warts (AGW). AK patients treated with IM develop intensified inflammatory reactions on sights of prior clinical visible or palpable AKs as compared to the surrounding actinically damaged skin, suggesting the induction of a tumor cell-directed inflammation. AGW patients treated with IM develop even stronger inflammatory reactions with large erosions, suggesting a directed inflammatory response against HPV-infected keratinocytes. Of note, even widespread erosions heal very fast without any superinfections. Here, we set out to elucidate underlying molecular and cellular mechanisms of these clinical observations. METHODS: The effects of IM (10-9-10-5 M) on the expression and translation of a comprehensive set of chemokines (CXCL1, CXCL8, CXCL9, CXCL10, CXCL11, CXCL14, CCL2, CCL5, CCL20, CCL27) and antimicrobial peptides (AMP) (HBD1, HBD2, HBD3, LL37, RNase7) were analyzed in primary human epithelial keratinocytes (HEK) and a set of epithelial cancer cell lines by RT-qPCR and ELISA in vitro. To study the possible effects of different concentrations of IM on migratory, respectively wound healing responses, an in vitro scratch assay was conducted on HEK. RESULTS: Ingenol mebutat significantly and dose-dependently induced the expression of proinflammatory chemokines (CXCL8, CCL2) and AMP (RNase7, HBD3) in HEK and epithelial cancer cell lines. A significantly stronger induction of CXCL8 and CCL2 was observed in our tested tumor cells as compared to HEK. We did not observe any significant effect of IM on HEK migration, respectively wound healing responses in vitro for any tested concentration (10-9, 10-8, 10-6 M) except 10-7 M, which induced a significant inhibition. CONCLUSIONS: Our data suggest that tumor cells are more susceptible to IM as compared to differentiated HEK. This is evident by a stronger IM-mediated induction of proinflammatory chemokines in tumor cells, which may result in a tumor cell-directed inflammatory response and rapid tumor destruction. In addition, IM induces AMP in keratinocytes and seems not to severely interfere with keratinocyte migration, which contributes to a fast and uncomplicated wound healing. Surprising is a selective inhibition of keratinocyte migration by IM at the concentration of 10-7 M pointing to very dose depending biological effects, induced by IM.

Time-lapse imaging points towards a non-toxic, mainly immune-driven mode of action of ingenol mebutate in the treatment of anogenital warts.

Recently, it has been reported that ingenol mebutate (IM) is an effective treatment option for anogenital warts (AGW), inducing fast wart necrosis within 24 hours in vivo. With regard to its mode of action, IM is thought to act both as an inducer of direct cytotoxic effects and immunologic mechanisms. To distinguish whether the wart necrosis is mainly caused by cytotoxic effects, or whether immune mechanisms are leading, we used time-lapse imaging to analyse IM-treated warts ex vivo over 24 hours. Ex vivo IM-treated warts, which have been detached from the immune system, did not show destructive necrosis, pointing towards a primarily immune-driven mode of action of IM in the treatment of AGW.

Laser assisted Drug Delivery: Grundlagen und Praxis.

Die topische Applikation von Wirkstoffen ist eine zentrale Therapieoption der Dermatologie. Allerdings mindert die effektive Barrierefunktion der Haut die Bioverfügbarkeit der meisten Externa. Fraktionierte ablative Laser stellen ein innovatives Verfahren dar, um die epidermale Barriere standardisiert, kontaktfrei zu überwinden. Die Bioverfügbarkeit im Anschluss applizierter Externa wird im Sinne einer laser assisted drug delivery (LADD) signifikant gesteigert. Das Prinzip der LADD wird bereits in einigen Bereichen der Dermatologie erfolgreich eingesetzt. Die vorliegende Übersichtsarbeit soll einen Überblick über die aktuellen aber auch perspektivischen Einsatzmöglichkeiten der LADD bieten.

Laser-assisted drug delivery: mode of action and use in daily clinical practice.

Topical application of pharmaceutical agents is a basic principle of dermatological therapy. However, the effective barrier function of the skin significantly impairs the bioavailability of most topical drugs. Fractional ablative lasers represent an innovative strategy to overcome the epidermal barrier in a standardized, contact-free manner. The bioavailability of topical agents can be significantly enhanced using laser-assisted drug delivery (LADD). In recent years, the principle of LADD has become well established for various dermatological indications. Herein, we review the current literature on LADD and present potential future applications.