Background: Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy. Methods: We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany.

Background: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists.

No abstract

Giant condyloma acuminatum (GCA; Buschke-Löwenstein tumor) is a human-papillomavirus-induced cauliflower-like tumor of the genitoanal region. It is characterized by its size, capability of local infiltration and high recurrence rate. We report on a 50-year-old patient presenting with a maximum finding of GCA with deep infiltration into the adductor and perineal musculature, the scrotum, the penis and the pararectum. After performing a temporary loop colostomy, the tumor was removed by wide radical excision following plastic reconstruction with a myocutaneous gracilis flap. During a follow-up period of more than 5 years, no recurrence developed. Many treatment strategies (e.g. chemotherapy, radiation) have been published in the literature. Most authors recommend the radical surgical excision, allowing a complete histological examination and assessment of tumor-free resection margins. Despite the benign histological pattern of GCA in most cases, transformations into verrucous carcinoma and squamous-cell carcinoma have been described. In our case, the GCA seems to represent a continuum between normal condyloma acuminatum and an initial verrucous carcinoma.

SummaryTopical photodynamic therapy (PDT) is a highly effective and safe treatment method for actinic keratoses with an excellent cosmetic outcome and is commonly used for the therapy of large areas of photodamaged skin with multiple clinically manifest and subclinical lesions. However, the major drawback of photodynamic therapy is the pain experienced during the treatment that can be intense and sometimes even intolerable for patients, requiring interruption or termination of the process. Several strategies for controlling pain during photodynamic therapy have been studied but few effective methods are currently available. Therefore, this review puts the spotlight on predictors on pain intensity and aspects of pain management during photodynamic therapy.

Summary Background Photodynamic therapy (PDT) is an effective therapy treating photodamaged areas with multiple actinic keratoses (AK). Still pain during therapy is one of the most challenging obstacles for patients. This retrospective study compares pain and efficacy intra‐individual in patients using conventional PDT (c‐PDT) compared to a low irradiance PDT protocol (li‐PDT) with a reduced irradiance to 25% of c‐PDT. Methods Thirty‐one patients were enrolled into this retrospective analysis treated with li‐PDT and c‐PDT on comparable fields of actinic damage on the forehead or the cheek. Pain was scored by the patients using a VAS. Moreover, number and time to therapy interruptions were documented. For effectiveness number and grade of AK were counted before and 4 weeks after PDT. Results Maintaining a total light dose of 37 J/cm2, a decrease in irradiation in li‐PDT patients resulted in significant less pain (VAS score 2.8 vs 7.6) and fewer therapy interruptions compared to treatment with c‐ PDT (P < 0.0005). No significant difference in treatment outcome was found (P = 0.068). Conclusion Our data shows that li‐PDT can reduce pain with at least comparable clinical outcome compared to c‐PDT. Therefore, it is an effective and well‐tolerated treatment for patients with multiple AK.

Review of the literature and the present case suggests that hyperuricemia is a necessary but probably not sufficient condition for gouty panniculitis. Why gouty panniculitis very seldom arises as a manifestation of gout is puzzling. In almost all reported patients, uricostatic or uricosuric therapy leads to clinical improvement of the disease.

No abstract