Estimation of Tissue Oxygen Saturation from RGB Images based on Pixel-level Image Translation

TL;DR

This paper introduces a real-time, non-invasive method using cGANs to estimate tissue oxygen saturation directly from RGB images, facilitating integration into surgical workflows without extra hardware.

Contribution

It presents a novel pixel-level image translation approach using cGANs to estimate StO2 from RGB images, eliminating the need for specialized imaging equipment.

Findings

Achieved visually identical StO2 estimations with comparable accuracy

Validated on simulated and real tissue images from HSI data

Demonstrated real-time performance suitable for surgical use

Abstract

Intra-operative measurement of tissue oxygen saturation (StO2) has been widely explored by pulse oximetry or hyperspectral imaging (HSI) to assess the function and viability of tissue. In this paper we propose a pixel- level image-to-image translation approach based on conditional Generative Adversarial Networks (cGAN) to estimate tissue oxygen saturation (StO2) directly from RGB images. The real-time performance and non-reliance on additional hardware, enable a seamless integration of the proposed method into surgical and diagnostic workflows with standard endoscope systems. For validation, RGB images and StO2 ground truth were simulated and estimated from HSI images collected by a liquid crystal tuneable filter (LCTF) endoscope for three tissue types (porcine bowel, lamb uterus and rabbit uterus). The result show that the proposed method can achieve visually identical images with comparable accuracy.