Search

Photodynamic therapy (PDT) with light emitting diode (LED) illumination is a frequently used treatment modality for actinic keratosis (AK) with excellent cosmetic outcome. A major disadvantage, however, is the high pain score. Pulsed dye laser (PDL) illumination has been suggested, but the long-term efficacy of this treatment is unknown. In this split-face study we prospectively treated 61 patients with AK, with both LED-PDT and PDL-PDT. The mean change in the number of lesions between the end of follow-up and start of therapy was -4.25 (95% confidence interval (95% CI) -5.07; -3.43) for LED-PDT and -3.88 (95% CI -4,76; -2.99) for PDL-PDT, with a non-significant difference (p = 0.258) of -0.46 (95% CI -1.28; 0.35). The percentage decrease from baseline in the total number of AK was 55.8% and 47.8%, respectively, at 12-month follow-up. Visual analogue scale pain score was lower after PDL (mean 2.64) compared with LED illumination (mean 6.47). These findings indicate that PDL-PDT is an effective alternative illumination source for AK when pain is a limiting factor for regular LED-PDT. [ABSTRACT FROM AUTHOR]

Background: Basal cell carcinoma (BCC) is the most common type of skin cancer with incidence rates rising each year. Mohs micrographic surgery (MMS) is most often chosen as treatment for BCC on the face for which each frozen section has to be histologically analysed to ensure complete tumor removal. This causes a heavy burden on health economics., Objectives: To develop and evaluate a deep learning model for the automated detection of BCC-negative slides and classification of BCC in histopathology slides of MMS based on whole-slide image (WSI)., Methods: Two deep learning models were developed on the basis of 171 digitized H&E frozen slides from 70 different patients. The first model had a U-Net architecture and was used for the segmentation of BCC. A subsequent convolutional neural network used the segmentation to classify the whole slide as BCC or BCC-negative., Results: Quantitative evaluation over manually labelled ground truth data resulted in a Dice score of 0.66 for the segmentation of BCC and an area under the receiver operating characteristic curve (AUC) of 0.90 for the slide-level classification., Conclusions: This study demonstrates that through WSIs deep learning models may be a feasible option to improve the clinical workflow and reduce costs in histological analysis of BCC in MMS., (© 2021 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)