The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild.

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of the AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (i.e., AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to the low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions in different positions and captured different contexts of perilesional skin. In total, 16,488 translation-augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-Net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving upon both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.

Image Perceptual Similarity Metrics for the Assessment of Basal Cell Carcinoma.

Efficient management of basal cell carcinomas (BCC) requires reliable assessments of both tumors and post-treatment scars. We aimed to estimate image similarity metrics that account for BCC's perceptual color and texture deviation from perilesional skin. In total, 176 clinical photographs of BCC were assessed by six physicians using a visual deviation scale. Internal consistency and inter-rater agreement were estimated using Cronbach's α, weighted Gwet's AC2, and quadratic Cohen's kappa. The mean visual scores were used to validate a range of similarity metrics employing different color spaces, distances, and image embeddings from a pre-trained VGG16 neural network. The calculated similarities were transformed into discrete values using ordinal logistic regression models. The Bray-Curtis distance in the YIQ color model and rectified embeddings from the 'fc6' layer minimized the mean squared error and demonstrated strong performance in representing perceptual similarities. Box plot analysis and the Wilcoxon rank-sum test were used to visualize and compare the levels of agreement, conducted on a random validation round between the two groups: 'Human-System' and 'Human-Human.' The proposed metrics were comparable in terms of internal consistency and agreement with human raters. The findings suggest that the proposed metrics offer a robust and cost-effective approach to monitoring BCC treatment outcomes in clinical settings.

The Feasibility of Immunocryosurgery in the Treatment of Non-Superficial, Facial Basal Cell Carcinoma That Relapsed after Standard Surgical Excision: An Experience Report from Two Centers.

In this retrospective, chart review study, we evaluated the feasibility of immunocryosurgery in facial, non-superficial basal cell carcinomas (BCC) that had relapsed after standard surgery. Inclusion criteria were (a) 'biopsy confirmed relapse of facial BCC', (b) known 'calendar year of surgical excision(s)', and (c) 'relapse within 10 years after the last surgical excision'. Tumors treated from 1 January 2011 to 31 December 2020 with a standard 5-week immunocryosurgery cycle (daily imiquimod application for 5 weeks and a cryosurgery session at day 14) were included. Descriptive statistics, Kaplan-Meier method, and Cox proportional hazards model were calculated with significance at p < 0.05. From the n = 27 BCC evaluated, n = 20 (74.1 ± 8.4%) cleared after one immunocryosurgery cycle. Two of the remaining cases cleared completely after a repeat cycle, one patient favored surgery, and four BCC did not clear despite additional immunocryosurgery cycles (feasibility 81.5 ± 7.5%). Of the 22 tumors with clinical outcome 'complete clearance with immunocryosurgery', three BCC relapsed at 9, 28, and 50 months. Overall, the 5-year treatment efficacy rate was 60.2 ± 13.4% (mean follow-up 94.6 ± 15.1 months). In total, 20/27 BCC relapses after surgery (74.1%) were tumor-free at the end of personalized follow-up times (66.7 ± 12.4% tumor free patients at 5-year follow-up). Number of tumor relapses before immunocryosurgery was the single predictor of tumor progression after immunocryosurgery (p = 0.012). Conclusively, immunocryosurgery could be further evaluated as an alternative, definitive treatment of selected facial BCC relapsing after surgery.