Background: Accurate assessment of disease severity in atopic dermatitis (AD) is important in guiding management.
Objective: To evaluate the feasibility of raster-scanning optoacoustic mesoscopy (RSOM) imaging as an objective disease severity tool for AD.
Methods: This prospective study included 69 AD patients and 22 healthy volunteers. All AD participants were assessed using the Scoring Atopic Dermatitis (SCORAD) instrument and all participants had RSOM imaging using RSOM Explorer C50 system (iThera Medical GmbH, Germany). From the RSOM images generated, epidermis thickness (ET), total blood volume (TBV), vessel diameter in the dermis (VD), ratio of low and high frequency signals (LHFR) in the dermis were computed. We trained a linear kernel-based support vector machine model for eczema classification based on ET, TBV and LHFR. A novel Eczema Vascular and Structural Index (EVSI) was then formulated to assess eczema severity.
Results: EVSI accurately classified healthy and eczematous skin (p <0.0001). EVSI obtained a high cross-validated area under the curve of 0.921, accuracy of 0.872, with high sensitivity and specificity of 0.853 and 0.838 respectively. The Pearson’s correlation coefficient of EVSI and SCORAD was 0.768. Conclusion: RSOM provides an accurate, direct and objective assessment of the skin ultra-structures in a non-invasive manner.