Swanson, David

Introduction: Porokeratosis is a group of keratinization disorders characterized by the histopathological presence of the cornoid lamella, a hallmark feature across all subtypes. The clinical diagnosis of porokeratosis can be challenging due to its similarity to other dermatological conditions. While polarized light dermatoscopy (PLD) enhances diagnostic accuracy, certain features remain difficult to identify. Ultraviolet-induced fluorescence dermatoscopy (UVFD) is a novel imaging technique that may improve the visualization of porokeratosis features, particularly the peripheral keratin rim. Objectives: This study aimed to assess the diagnostic utility of UVFD compared with PLD in identifying the dermatoscopic features of porokeratosis. Methods: In this retrospective study, dermatologists from five institutions in Chile, Brazil, Poland, and the United States contributed with dermatoscopic images of porokeratosis cases. Both PLD and UVFD images were obtained for each lesion. Two independent investigators evaluated each lesion in PLD and UVFD for the presence of peripheral keratin rim, rim continuity, central scaling, follicular plugs, vascular structures, and photodamaged surrounding skin. A third investigator reviewed discrepancies. Frequencies and means were calculated. McNemar’s chi-square was used for comparison. Results: A total of 136 lesions from 35 patients with biopsy-proven porokeratosis were analyzed. UVFD significantly improved the visualization of the peripheral keratin rim (95.6% vs. 66.2% in PLD; P<0.001) and increased identification rates for central scaling, follicular plugs, and interrupted rims. PLD remained superior for detecting vascular structures(P<0.001). Conclusions: UVFD enhances the visualization of key dermatoscopic features of porokeratosis, particularly the peripheral keratin rim and other keratin-related structures.

Background: Patients with skin lesions suspicious for skin cancer or atypical melanocytic nevi of uncertain malignant potential often present to dermatologists, who may have variable dermoscopy triage clinical experience. Objective: To evaluate the clinical utility of a digital dermoscopy image-based artificial intelligence algorithm (DDI-AI device) on the diagnosis and management of skin cancers by dermatologists. Methods: Thirty-six United States board-certified dermatologists evaluated 50 clinical images and 50 digital dermoscopy images of the same skin lesions (25 malignant and 25 benign), first without and then with knowledge of the DDI-AI device output. Participants indicated whether they thought the lesion was likely benign (unremarkable) or malignant (suspicious). Results: The management sensitivity of dermatologists using the DDI-AI device was 91.1%, compared to 84.3% with DDI, and 70.0% with clinical images. The management specificity was 71.0%, compared to 68.4% and 64.9%, respectively. The diagnostic sensitivity of dermatologists using the DDI-AI device was 86.1%, compared to 78.8% with DDI, and 63.4% with clinical images. Diagnostic specificity using the DDI-AI device increased to 80.7%, compared to 75.9% and 73.6%, respectively. Conclusion: The use of the DDI-AI device may quickly, safely, and effectively improve dermoscopy performance, skin cancer diagnosis, and management when used by dermatologists, independent of training and experience.