Improved Cherenkov Imaging across a Wide Range of Skin Pigmentation Levels for the Inclusion of Diverse Patient Populations

Abstract

<h3>Purpose/Objective(s)</h3> Cherenkov imaging has recently emerged as a tool to visualize radiation dose and detect treatment incidents in real-time. The principle relies on the proportionality between Cherenkov light emission and dose deposited within tissue, introducing an additional opportunity to use the image information as a 2D surface dose map. The Cherenkov-dose relationship is affected by tissue optical properties, and recent studies have utilized routine CT-scans to correct for optical attenuation due to fibroglandular and adipose tissues, and blood volume, in the breast. However, the bulk of the reported <i>in vivo</i> data is limited to light-skinned patients due to limitations of geographical demographics. It is well documented that melanin is an optical absorber of Cherenkov photons, yet no prior <i>in vivo</i> work has been done to characterize the effect of different skin tones on Cherenkov dosimetry. We hypothesize that skin color information can be used to correct Cherenkov images for optical attenuation relating to melanin absorption across a diverse patient population. <h3>Materials/Methods</h3> A multi-institutional partnership was developed aiming to collect data from a more diverse patient population. A time-gated, intensified CMOS camera installed in the ceiling of a treatment room collects Cherenkov images of breast RT patients during their treatment. A standard color camera module is mounted adjacent to the Cherenkov camera to collect a color background image. Following a process developed with phantom studies, the two images are co-registered together in post-processing, RGB values are extracted from the skin over the treatment regions to calculate the relative skin luminance, L, and this value is compared to the optical emission from the corresponding Cherenkov image. A linear regression model is then used to assess the proportionality between L and Cherenkov emission intensity. <h3>Results</h3> The Cherenkov imaging system is being deployed in a clinic with a catchment area demographic of 67.4% Non-Hispanic White, an increase in diversity from 89.4% at the home institution. A clear relationship exists between skin color information and Cherenkov intensity, which cannot be determined like the bulk tissue properties from the CT scan alone. We found that L, derived from a wide range of melanin concentrations, is linearly proportional to Cherenkov intensity (R² = 0.98). Each Cherenkov image can be corrected based on skin luminance to improve the Cherenkov-dose relationship across various skin types. <h3>Conclusion</h3> The effect of both inter- and intra-patient skin color variations on the Cherenkov intensity can be corrected by using a linear regression model to increase the linearity between Cherenkov and deposited dose. This work will be used to improve our current CT-correction algorithm for all skin types and presents a major step towards expanding the inclusivity of Cherenkov imaging as a dosimetric tool for every patient.