Computational characterization of reflectance confocal microscopy features reveals potential for automated photoageing assessment

Abstract

Skin photoageing results from a combination of factors including ultraviolet (sun) exposure, leading to significant changes in skin morphology and composition. Conventional methods assessing the degree of photoageing, in particular histopathological assessment involve an invasive multistep process. Advances in microscopy have enabled a shift towards non-invasive in vivo microscopy techniques such as reflectance confocal microscopy (RCM) in this context. Computational image analysis of RCM images has the potential to be of use in the non-invasive assessment of photoageing. In this report, we computationally characterized a clinical RCM data set from younger and older Caucasians with varying levels of photoageing. We identified several mathematical relationships that related to the degree of photoageing as assessed by conventional scoring approaches (clinical photography, SCINEXA and RCM). Furthermore, by combining the mathematical features into a single computational assessment score, we observed significant correlations with conventional RCM (P < 0.0001) and the other clinical assessment techniques.

Evaluation and assessment of photoaging

“…In this study, the authors were able to mathematically correlate RCM-identified photoaging with conventional scoring techniques including the SCINEXA scale and photograph scale. This suggests the possibility of automated, objective RCM analysis [39].…”

“…More objective tools are needed [24]. Histopathological assessment of dermal collagen degradation is currently the gold standard, but ultrasound and the development of non-invasive in vivo microscopy techniques are promising [39]. Ultrasound has been used to measure skin thickness non-invasively since skin becomes thinner as it ages [25].…”

“…RCM provides higher resolution imaging allowing for assessment of structural morphology changes and also allows for serial imaging over time [39]. More than 15 statistically significant RCM features are associated with forearm photoaging, including changes in architecture, cell morphology, and collagen at the level of the epidermis, dermo-epidermal junction, and papillary dermis [48].…”

Automated Segmentation of Skin Strata in Reflectance Confocal Microscopy Depth Stacks

“…This dataset thus forms an ideal testbed for algorithm development in the context of the most challenging phototypes to examine with RCM. This dataset forms a superset of the data from Australian participants examined for the signs of photoageing in [11] and also used in [7]. …”

“…These assessment approaches have focused on one of three main categories: 1) Quantifying and detecting specific features such as counting keratinocytes [5], detecting pagetoid cells [6] and evaluating photoageing [7], 2) Computer aided diagnosis of malignant melanocytic lesions [8] and 3) Identifying the anatomical structures of human skin [9,10]. Although both Somoza et al and Kurugol et al considered the problem of understanding human skin their work is limited: Kurugol et al consider only the location of the dermal-epidermal junction and showed good performance only in darker skin types: 89% of the epidermis and 87% of the dermis were correctly classified in dark skin, whereas in light skin only 64% and 75% of the epidermis and dermis were correctly classified.…”