Recessive dystrophic epidermolysis bullosa (RDEB) is a devastating, genetic blistering condition caused by the absence of type VII collagen (C7), affecting the mucosa and skin. Patients often have recurrent and chronic open wounds, but one of the major barriers to the development of clinical trials is the lack of understanding of the natural history of RDEB wounds, as the measurement of target wound change has not been studied prospectively or validated. We conducted a longitudinal, clinical observational study of 10 patients with RDEB who used a mobile phone photography application, with built-in machine learning, to outline and track RDEB wounds autonomously. Patients used this mobile application to capture photographs weekly, alongside reporting associated pain and itch.507 photos of 10 participants with RDEB were collected: 202 of chronic open wounds (unhealed >12 weeks) and 290 of recurrent wounds (heal but re-open), with an average of 44.7 wound photos per participant. The top three locations recorded were hips or legs (n¼241), feet (n¼115) and upper extremity (n¼82). For chronic open wounds, there was a statistically significant positive correlation for both wound size and pain (0.76, p<0.001), and wound size and itch (0.74, p<0.001). Recurrent wounds also had a significant association between wound size and pain and itch, but the strength of the correlation was weaker; pain (0.37, p<0.0009), itch (0.32, p<0.005). Neither wound types significantly healed over an average follow up time of 95.5 days. This validated previously known information about the nature of RDEB wounds, and we found that use of a mobile application can be a valuable method to track the natural history. The covid-19 travel restrictions have shown the value of being able to obtain weekly wound images whilst participants are at home. The challenges we faced included encouraging regular submission of wound photographs, loss-to-follow up due to enrollment in other clinical trials, and technical difficulties associated with using the application.

Objectives: Reflectance confocal microscopy (RCM) generates scalar image data from serial depths in the skin, allowing in vivo examination of cellular features. The maximum imaging depth of RCM is approximately 250 µm, to the papillary dermis, or upper reticular dermis. Frequently, important diagnostic features are present in the dermis, hence improved visualization of deeper levels is advantageous. Methods: Low contrast and noise in dermal images were improved by employing a combination of wavelet-based transformations and contrast-limited adaptive histogram equalization. Results: Preserved details, noise reduction, increased contrast, and feature enhancement were observed in the resulting processed images. Conclusions: Complex and combined wavelet-based enhancement approaches for dermal level images yielded reconstructions of higher quality than less sophisticated histogram-based strategies. Image optimization may improve the diagnostic accuracy of RCM, especially for entities with dermal findings.