Prospective multicenter study using artificial intelligence to improve dermoscopic melanoma diagnosis in patient care.

BACKGROUND: Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting. METHODS: Therefore, we assessed "All Data are Ext" (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e., providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities. RESULTS: Overall, the AI shows higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779-0.814 vs. 0.781, 95% CI 0.760-0.802; p = 4.0e-145), obtaining a higher sensitivity (0.921, 95% CI 0.900-0.942 vs. 0.734, 95% CI 0.701-0.770; p = 3.3e-165) at the cost of a lower specificity (0.673, 95% CI 0.641-0.702 vs. 0.828, 95% CI 0.804-0.852; p = 3.3e-165). CONCLUSION: As the algorithm exhibits a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists, particularly in diagnosing challenging cases.

Melanoma is a type of skin cancer that can spread to other parts of the body, often resulting in death. Early detection improves survival rates. Computational tools that use artificial intelligence (AI) can be used to detect melanoma. However, few studies have checked how well the AI works on real-world data obtained from patients. We tested a previously developed AI tool on data obtained from eight different hospitals that used different types of cameras, which also included images taken of rare melanoma types and from a range of different parts of the body. The AI tool was more likely to correctly identify melanoma than dermatologists. This AI tool could be used to help dermatologists diagnose melanoma, particularly those that are difficult for dermatologists to diagnose.

Approach to Mycosis Fungoides in children: Consensus-based recommendations.

BACKGROUND: Pediatric Mycosis fungoides (MF) management extrapolates from adult guidelines, despite differing clinical aspects. Recommendations are essential to address unique challenges in this distinct patient group. OBJECTIVE: This project aims to derive consensus recommendations for pediatric MF management. METHODS: Experts from pediatric dermatology, general dermatology, dermatopathology, and pediatric hematology-oncology (N = 83) were invited to contribute to consensus recommendations. The process involved 3 electronic Delphi rounds, concluding with a final consensus meeting using a modified Nominal Group Technique for unresolved items. RESULTS: Consensus included more clinical severity measures than tumor-node-metastasis-blood staging: pruritus, functional or esthetic impairment (eg, palms, soles, genitalia), quality of life impact, and psychological aspects (eg, embarrassment, anxiety, depression), plus parental anxiety. Ten recommendations were made for managing early and advanced pediatric MF. Disagreement emerged in choosing therapies beyond stage I of the disease. DISCUSSION: This multinational initiative aimed to standardize optimal pediatric MF management and successfully generated consensus recommendations. Additional work is needed for structured, prospective protocols in advanced-stage pediatric MF. LIMITATIONS: Lack of pediatric hematologists-oncologists and patients' representatives. CONCLUSION: Documentation of extended clinical severity and outcome measures is recommended. Addressing the need for structured protocols in advanced-stage pediatric MF and implementing systematic, prospective data collection is crucial.

Oncogenic alterations in KIR3DL1 in cutaneous acral CD8+ lymphoproliferative disorder.

BACKGROUND: Primary cutaneous acral CD8+ T-cell lymphoproliferative disorder (TLPD) is a rare and indolent lymphoma entity. Although TLPD was first identified many years ago, the molecular pathogenesis is still not fully understood. OBJECTIVES: In order to better understand the molecular pathogenesis of cutaneous acral CD8+ TLPD and to identify further discriminatory markers to differentiate this lymphoma subtype from other CD8+ cutaneous lymphomas, we analysed five cases of cutaneous acral CD8+ TLPD for putative molecular alterations. METHODS: Somatic alterations were assessed using whole-exome and targeted sequencing of paraffin-embedded tissue. Results were evaluated using immunohistochemical staining of respective relevant proteins. CD8+ cutaneous T-cell lymphomas (n = 12) served as control for KIR3DL1 staining. RESULTS: Copy number variation analysis revealed a homozygous deletion of the KIR3DL1 gene in two of the analysed cases. This resulted in loss of KIR3DL1 protein expression, which was observed in all cases of cutaneous acral CD8+ TLPD. In contrast, KIR3DL1 expression was more variable in other CD8+ cutaneous T-cell lymphomas with 50% of analysed cases (n = 12) found to be positive. In addition, one further case of acral CD8+ TLPD harboured a loss-of-function mutation in the PIK3R1 gene, presumably activating the phosphoinositide 3-kinase-AKT pathway. CONCLUSIONS: Alterations of the KIR3DL1 gene may be of pathogenetic relevance for acral CD8+ TLPD. Loss of KIR3DL1 protein expression may support the diagnosis of this indolent lymphoma entity; however, this is not a subtype-specific discriminative feature.

Cutaneous acral CD8+ T-cell lymphoproliferative disorder (TLPD) is a very rare form of lymphoma, with only around 60 cases reported worldwide. The progression of this lymphoma is usually slow, and most people will present with a solitary plaque or a small papule, without any risk of rapid worsening. For this reason, treatment directly on the skin with topical steroids, excision or radiation are usually sufficient. However, it can be difficult to differentiate this type of lymphoma from other CD8+ cutaneous types upon microscopy. This is important because other CD8+ cutaneous lymphomas can follow an aggressive course and will need to be treated differently, using systemic therapies. Previous findings have shown that abnormal expression of a protein (called CD68) in a dotlike pattern is a specific feature of acral CD8+ TLPD and could help to accurately diagnose this lymphoma. Until now, the underlying molecular differences in cutaneous acral CD8+ TLPD have not been identified. Therefore, this German study was carried out to look at the genetic alterations in the tissue of five patients with this type of lymphoma. To do this, we used a method that examined whole-exome and targeted gene sequencing. We detected alterations in a gene important for T-cell function (called KIR3DL1), in two of five analysed cases. Of note, a loss of KIR3DL1 protein expression has been observed in all analysed cases of acral CD8+ TLPD. Our study findings suggest that genetic defects in KIR3DL1 in acral CD8+ TLPD could be a novel diagnostic marker for this lymphoma subtype and may help to better distinguish it from other, potentially aggressive forms of cutaneous lymphoma.

Susceptibility of Melanoma Cells to Targeted Therapy Correlates with Protection by Blood Neutrophils.

Elevated levels of peripheral blood and tumor tissue neutrophils are associated with poorer clinical response and therapy resistance in melanoma. The underlying mechanism and the role of neutrophils in targeted therapy is still not fully understood. Serum samples of patients with advanced melanoma were collected and neutrophil-associated serum markers were measured and correlated with response to targeted therapy. Blood neutrophils from healthy donors and patients with advanced melanoma were isolated, and their phenotypes, as well as their in vitro functions, were compared. In vitro functional tests were conducted through nonadherent cocultures with melanoma cells. Protection of melanoma cell lines by neutrophils was assessed under MAPK inhibition. Blood neutrophils from advanced melanoma patients exhibited lower CD16 expression compared to healthy donors. In vitro, both healthy-donor- and patient-derived neutrophils prevented melanoma cell apoptosis upon dual MAPK inhibition. The effect depended on cell-cell contact and melanoma cell susceptibility to treatment. Interference with protease activity of neutrophils prevented melanoma cell protection during treatment in cocultures. The negative correlation between neutrophils and melanoma outcomes seems to be linked to a protumoral function of neutrophils. In vitro, neutrophils exert a direct protective effect on melanoma cells during dual MAPK inhibition. This study further hints at a crucial role of neutrophil-related protease activity in protection.

S2k guideline for the treatment of hidradenitis suppurativa / acne inversa - Short version.

The S2k guideline on hidradenitis suppurativa/acne inversa (HS/AI) aims to provide an accepted decision aid for the selection/implementation of appropriate/sufficient therapy. HS/AI is a chronic recurrent, inflammatory, potentially mutilating skin disease of the terminal hair follicle-glandular apparatus, with painful, inflammatory lesions in the apocrine gland-rich regions of the body. Its point prevalence in Germany is 0.3%, it is diagnosed with a delay of 10.0 ± 9.6 years. Abnormal differentiation of the keratinocytes of the hair follicle-gland apparatus and accompanying inflammation form the central pathogenetic basis. Primary HS/AI lesions are inflammatory nodules, abscesses and draining tunnels. Recurrences in the last 6 months with at least 2 lesions at the predilection sites point to HS/AI with a 97% accuracy. HS/AI patients suffer from a significant reduction in quality of life. For correct treatment decisions, classification and activity assessment should be done with a validated tool, such as the International Hidradenitis Suppurativa Severity Scoring System (IHS4). HS/AI is classified into two forms according to the degree of detectable inflammation: active, inflammatory (mild, moderate, and severe according to IHS4) and predominantly inactive, non-inflammatory (Hurley grade I, II and III) HS/AI. Oral tetracyclines or 5-day intravenous therapy with clindamycin are equal to the effectiveness of clindamycin/rifampicin. Subcutaneously administered adalimumab, secukinumab and bimekizumab are approved for the therapy of HS/AI. Various surgical procedures are available for the predominantly non-inflammatory disease form. Drug/surgical combinations are considered a holistic therapy method.

Loss of p14 diminishes immunogenicity in melanoma via non-canonical Wnt signaling by reducing the peptide surface density.

Immunotherapy has achieved tremendous success in melanoma. However, only around 50% of advanced melanoma patients benefit from immunotherapy. Cyclin-dependent kinase inhibitor 2A (CDKN2A), encoding the two tumor-suppressor proteins p14ARF and p16INK4a, belongs to the most frequently inactivated gene loci in melanoma and leads to decreased T cell infiltration. While the role of p16INK4a has been extensively investigated, knowledge about p14ARF in melanoma is scarce. In this study, we elucidate the impact of reduced p14ARF expression on melanoma immunogenicity. Knockdown of p14ARF in melanoma cell lines diminished their recognition and killing by melanoma differentiation antigen (MDA)-specific T cells. Resistance was caused by a reduction of the peptide surface density of presented MDAs. Immunopeptidomic analyses revealed that antigen presentation via human leukocyte antigen class I (HLA-I) molecules was enhanced upon p14ARF downregulation in general, but absolute and relative expression of cognate peptides was decreased. However, this phenotype is associated with a favorable outcome for melanoma patients. Limiting Wnt5a signaling reverted this phenotype, suggesting an involvement of non-canonical Wnt signaling. Taken together, our data indicate a new mechanism limiting MDA-specific T cell responses by decreasing both absolute and relative MDA-peptide presentation in melanoma.

Patient-Centered Chronic Wound Care Mobile Apps: Systematic Identification, Analysis, and Assessment.

Background: The prevalence of chronic wounds is predicted to increase within the aging populations in industrialized countries. Patients experience significant distress due to pain, wound secretions, and the resulting immobilization. As the number of wounds continues to rise, their adequate care becomes increasingly costly in terms of health care resources worldwide. eHealth support systems are being increasingly integrated into patient care. However, to date, no systematic analysis of such apps for chronic wounds has been published. Objective: The aims of this study were to systematically identify and subjectively assess publicly available German- or English-language mobile apps for patients with chronic wounds, with quality assessments performed by both patients and physicians. Methods: Two reviewers independently conducted a systematic search and assessment of German- or English-language mobile apps for patients with chronic wounds that were available in the Google Play Store and Apple App Store from April 2022 to May 2022. In total, 3 apps met the inclusion and exclusion criteria and were reviewed independently by 10 physicians using the German Mobile App Rating Scale (MARS) and the System Usability Scale (SUS). The app with the highest mean MARS score was subsequently reviewed by 11 patients with chronic wounds using the German user version of the MARS (uMARS) and the SUS. Additionally, Affinity for Technology Interaction (ATI) scale scores were collected from both patients and physicians. Results: This study assessed mobile apps for patients with chronic wounds that were selected from a pool of 118 identified apps. Of the 73 apps available in both app stores, 10 were patient oriented. After excluding apps with advertisements or costs, 3 apps were evaluated by 10 physicians. Mean MARS scores ranged from 2.64 (SD 0.65) to 3.88 (SD 0.65) out of 5, and mean SUS scores ranged from 50.75 (SD 27) to 80.5 (SD 17.7) out of 100. WUND APP received the highest mean MARS score (mean 3.88, SD 0.65 out of 5) among physicians. Hence, it was subsequently assessed by 11 patients and achieved a similar rating (uMARS score: mean 3.89, SD 0.4 out of 5). Technical affinity, as measured with the ATI scale, was slightly lower in patients (score: mean 3.62, SD 1.35 out of 6) compared to physicians (score: mean 3.88, SD 1.03 out 6). Conclusions: The quality ratings from physicians and patients were comparable and indicated mediocre app quality. Technical affinity, as assessed by using the ATI scale, was slightly lower for patients. Adequate apps for patients with chronic wounds remain limited, emphasizing the need for improved app development to meet patient needs. The ATI scale proved valuable for assessing technical affinity among different user groups.

S2k guidelines on diagnosis and treatment of linear IgA dermatosis initiated by the European Academy of Dermatology and Venereology.

INTRODUCTION: Linear IgA dermatosis (LAD) is a rare subepidermal autoimmune bullous disease (AIBD) defined by predominant or exclusive immune deposits of immunoglobulin A at the basement membrane zone of skin or mucous membranes. This disorder is a rare, clinically and immunologically heterogeneous disease occurring both in children and in adults. The aim of this project is to present the main clinical features of LAD, to propose a diagnostic algorithm and provide management guidelines based primarily on experts' opinion because of the lack of large methodologically sound clinical studies. METHODS: These guidelines were initiated by the European Academy of Dermatology and Venereology (EADV) Task Force Autoimmune Bullous Diseases (AIBD). To achieve a broad consensus for these S2k consensus-based guidelines, a total of 29 experts from different countries, both European and non-European, including dermatologists, paediatric dermatologists and paediatricians were invited. All members of the guidelines committee agreed to develop consensus-based (S2k) guidelines. Prior to a first virtual consensus meeting, each of the invited authors elaborated a section of the present guidelines focusing on a selected topic, based on the relevant literature. All drafts were circulated among members of the writing group, and recommendations were discussed and voted during two hybrid consensus meetings. RESULTS: The guidelines summarizes evidence-based and expert opinion-based recommendations (S2 level) on the diagnosis and treatment of LAD. CONCLUSION: These guidelines will support dermatologists to improve their knowledge on the diagnosis and management of LAD.

Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics.

Importance: The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals. Objective: To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics. Design, Setting, and Participants: This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023. Exposures: All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care. Main Outcomes and Measures: The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity. Results: The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479). Conclusions and Relevance: The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma.

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists' decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists' diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists' confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists' willingness to adopt such XAI systems, promoting future use in the clinic.