Propensity of skin diseases to manifest in a variety of forms, lack and maldistribution of qualified dermatologists, and exigency of timely and accurate diagnosis call for automated Computer-Aided Diagnosis (CAD). This study aims at extending previous works on CAD for dermatology by exploring the potential of Deep Learning to classify hundreds of skin diseases, improving classification performance, and utilizing disease taxonomy. We trained state-of-the-art Deep Neural Networks on two of the largest publicly available skin image datasets, namely DermNet and ISIC Archive, and also leveraged disease taxonomy, where available, to improve classification performance of these models. On DermNet we establish new state-of-the-art with 80% accuracy and 98% Area Under the Curve (AUC) for classification of 23 diseases. We also set precedence for classifying all 622 unique sub-classes in this dataset and achieved 67% accuracy and 98% AUC. On ISIC Archive we classified all 7 diseases with 93% average accuracy and 99% AUC. This study shows that Deep Learning has great potential to classify a vast array of skin diseases with near-human accuracy and far better reproducibility. It can have a promising role in practical real-time skin disease diagnosis by assisting physicians in large-scale screening using clinical or dermoscopic images.

Histopathology is the reference standard for diagnosing the presence and nature of many diseases, including cancer. However, analyzing tissue samples under a microscope and summarizing the findings in a comprehensive pathology report is time-consuming, labor-intensive, and non-standardized. To address this problem, we present HistoGPT, a vision language model that generates pathology reports from a patient’s multiple full-resolution histology images. It is trained on 15,129 whole slide images from 6705 dermatology patients with corresponding pathology reports. The generated reports match the quality of human-written reports for common and homogeneous malignancies, as confirmed by natural language processing metrics and domain expert analysis. We evaluate HistoGPT in an international, multi-center clinical study and show that it can accurately predict tumor subtypes, tumor thickness, and tumor margins in a zero-shot fashion. Our model demonstrates the potential of artificial intelligence to assist pathologists in evaluating, reporting, and understanding routine dermatopathology cases.

Accurate melanoma diagnosis is crucial for patient outcomes and reliability of AI diagnostic tools. We assess interrater variability among eight expert pathologists reviewing histopathological images and clinical metadata of 792 melanoma-suspicious lesions prospectively collected at eight German hospitals. Moreover, we provide access to the largest panel-validated dataset featuring dermoscopic and histopathological images with metadata. Complete agreement is achieved in 53.5% of cases (424/792), and a majority vote ( ≥ five pathologists) in 90.9% (720/792). Considerable discordance is observed for non-invasive melanomas (complete agreement in only 10/73 cases). The expert panel disagrees with the local pathologists’ and dermatologists’ diagnoses in 14.9% and 33.5% of cases, respectively. This variability highlights the diagnostic challenges of early-stage melanomas and the need to reconsider how ground truth is established in routine care and AI research. Including at least two pathologists or virtual panels may contribute to more consistent diagnostic results.

Monkeypox (mpox), a former rare viral zoonosis, has increasingly made it into the public eye since the major outbreak that started in May 2022. Mpox presents with skin lesions that change over time and go through different stages (macular, papular, pustular, and early and late ulceration). In this study, we evaluated skin biopsies of all stages. Therefore, five biopsies from four patients were analyzed histologically, immunohistochemically with anti-Vaccinia virus antibodies, and electron-microscopically. Notably, the early macular stage only showed subtle viropathic changes; it did not express of Orthopoxvirus proteins in immunohistochemistry and therefore can easily be missed histologically. In later stages, immunohistochemistry with anti-Vaccinia virus antibodies might be useful to distinguish mpox from differential diagnoses such as herpes virus infections. In the ulcerative stages, the identified occlusive vasculopathic changes could be an explanation for the severe pain of the lesions reported by some patients. Despite the small number of samples examined, our analysis suggests that the histological findings of mpox are highly dependent on the stage of the biopsied lesion. Therefore, knowledge of all different stages of histology is necessary to reliably diagnose mpox histologically, especially when molecular testing is not available.

Background: The coronavirus disease 2019 (COVID‐19) is associated with a wide clinical spectrum of skin manifestations, including urticarial, vesicular, vasculitic and chilblain‐like lesions. Recently, delayed skin reactions have been reported in 1% individuals following mRNA vaccination against SARS-CoV-2. The exact pathophysiology and the risk factors still remain unclear. Patients and methods: 6821 employees and patients were vaccinated at our institutions between February and June 2021. Every patient received two doses of the mRNA-1273 vaccine in our hospitals, and reported back in case of any side effects which were collected in our hospital managed database. Results: Eleven of 6821 vaccinated patients (0.16%) developed delayed skin reactions after either the first or second dose of the mRNA-1273 vaccine against SARS-CoV-2. Eight of 11 patients (73%) developed a rash after the first dose, while in 3/11 (27%), the rash occurred after the second dose. More females (9/11) were affected. Four of 11 patients required antihistamines, with two needing additional topical steroids. All the cutaneous manifestations resolved within 14 days. None of the skin reactions after the first dose of the vaccine prevented the administration of the second dose. There were no long-term cutaneous sequelae in any of the affected individuals. Conclusion: Our data suggests that skin reactions after the use of mRNA-1273 vaccine against SARS-CoV-2 are possible, but rare. Further studies need to be done to understand the pathophysiology of these lesions.