Image classification with convolutional neural networks (CNN) offers an unprecedented opportunity to medical imaging. Regulatory agencies in the USA and Europe have already cleared numerous deep learning/machine learning based medical devices and algorithms. While the field of radiology is on the forefront of artificial intelligence (AI) revolution, conventional pathology, which commonly relies on examination of tissue samples on a glass slide, is falling behind in leveraging this technology. On the other hand, ex vivo confocal laser scanning microscopy (ex vivo CLSM), owing to its digital workflow features, has a high potential to benefit from integrating AI tools into the assessment and decision-making process. Aim of this work was to explore a preliminary application of CNN in digitally stained ex vivo CLSM images of cutaneous squamous cell carcinoma (cSCC) for automated detection of tumor tissue. Thirty-four freshly excised tissue samples were prospectively collected and examined immediately after resection. After the histologically confirmed ex vivo CLSM diagnosis, the tumor tissue was annotated for segmentation by experts, in order to train the MobileNet CNN. The model was then trained and evaluated using cross validation. The overall sensitivity and specificity of the deep neural network for detecting cSCC and tumor free areas on ex vivo CLSM slides compared to expert evaluation were 0.76 and 0.91, respectively. The area under the ROC curve was equal to 0.90 and the area under the precision-recall curve was 0.85. The results demonstrate a high potential of deep learning models to detect cSCC regions on digitally stained ex vivo CLSM slides and to distinguish them from tumor-free skin.

BackgroundSurgical site infection (SSI) has a significant impact on patients’ morbidity and aesthetic results.ObjectiveTo identify risk factors for SSI in dermatologic surgery.Patients and MethodsThis prospective, single‐centre, observational study was performed between August 2020 and May 2021. Patients that presented for dermatologic surgery were included and monitored for the occurrence of SSI. For statistical analysis, we used a mixed effects logistic regression model.ResultsOverall, 767 patients with 1272 surgical wounds were included in the analysis. The incidence of SSI was 6.1%. Significant risk factors for wound infection were defect size over 10cm2 (OR 3.64, 95% confidence interval [CI] 1.80–7.35), surgery of cutaneous malignancy (OR 2.96, CI 1.41–6.24), postoperative bleeding (OR 4.63, CI 1.58–13.53), delayed defect closure by local skin flap (OR 2.67, CI 1.13–6.34) and localisation of surgery to the ear (OR 7.75, CI 2.07–28.99). Wound localisation in the lower extremities showed a trend towards significance (OR 3.16, CI 0.90–11.09). Patient‐related factors, such as gender, age, diabetes, or immunosuppression, did not show a statistically significant association with postoperative infection.ConclusionLarge defects, surgery of cutaneous malignancy, postoperative bleeding, and delayed flap closure increase the risk for SSI. High‐risk locations are the ears and lower extremities.