Jones, G; Clancy, N; Helo, Y; Arridge, S; Elson, D; Stoyanov, D; (2017) Bayesian Estimation of Intrinsic Tissue Oxygenation and Perfusion from RGB Images. IEEE Transactions on Medical Imaging 10.1109/TMI.2017.2665627. (In press).

Preview

Text 07859372.pdf - Published Version Download (14MB) | Preview

Abstract

Multispectral imaging (MSI) can potentially assist the intra-operative assessment of tissue structure, function and viability, by providing information about oxygenation. In this paper, we present a novel technique for recovering intrinsic MSI measurements from endoscopic RGB images without custom hardware adaptations. The advantage of this approach is that it requires no modification to existing surgical and diagnostic endoscopic imaging systems. Our method uses a radiometric colour calibration of the endoscopic camera's sensor in conjunction with a Bayesian framework to recover a per-pixel measurement of the total blood volume (THb) and oxygen saturation (SO2) in the observed tissue. The sensor's pixel measurements are modelled as weighted sums over a mixture of Poisson distributions and we optimise the variables SO2 and THb to maximise the likelihood of the observations. To validate our technique, we use synthetic images generated from Monte Carlo (MC) physics simulation of light transport through soft tissue containing sub-surface blood vessels. We also validate our method on in vivo data by comparing it to a MSI dataset acquired with a hardware system that sequentially images multiple spectral bands without overlap. Our results are promising and show that we are able to provide surgeons with additional relevant information by processing endoscopic images with our modelling and inference framework.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item