Rapid tissue oxygenation mapping from snapshot structured-light images with adversarial deep learning

Abstract

Significance: Spatial frequency-domain imaging (SFDI) is a powerful technique for mapping tissue oxygen saturation over a wide field of view. However, current SFDI methods either require a sequence of several images with different illumination patterns or, in the case of singlesnapshot optical properties (SSOP), introduce artifacts and sacrifice accuracy. Aim: We introduce OxyGAN, a data-driven, content-aware method to estimate tissue oxygenation directly from single structured-light images. Approach: OxyGAN is an end-to-end approach that uses supervised generative adversarial networks. Conventional SFDI is used to obtain ground truth tissue oxygenation maps for ex vivo human esophagi, in vivo hands and feet, and an in vivo pig colon sample under 659-and 851-nm sinusoidal illumination. We benchmark OxyGAN by comparing it with SSOP and a two-step hybrid technique that uses a previously developed deep learning model to predict optical properties followed by a physical model to calculate tissue oxygenation. Results: When tested on human feet, cross-validated OxyGAN maps tissue oxygenation with an accuracy of 96.5%. When applied to sample types not included in the training set, such as human hands and pig colon, OxyGAN achieves a 93% accuracy, demonstrating robustness to various tissue types. On average, OxyGAN outperforms SSOP and a hybrid model in estimating tissue oxygenation by 24.9% and 24.7%, respectively. Finally, we optimize OxyGAN inference so that oxygenation maps are computed ∼10 times faster than previous work, enabling video-rate, 25-Hz imaging. Conclusions: Due to its rapid acquisition and processing speed, OxyGAN has the potential to enable real-time, high-fidelity tissue oxygenation mapping that may be useful for many clinical applications.

Spatial Frequency Domain Imaging System Calibration, Correction and Application for Pear Surface Damage Detection

“…The principle of the technique is based on diffusion theory, introducing a spatially modulated source into the steady-state diffusion equation and realizing spatial resolution measurements. In the past 10 years, SFDI has been mainly used in medical and biomedical fields, such as skin disease detection [12,13], blood oxygen content detection [14,15], pig skin burn level detection [16], etc. In recent years, SFDI has been applied to agricultural product quality detection, such as apple bruise detection [17] and pear bruise detection [18,19].…”

Discrimination of the Skin Microcirculatory Status Using Photoacoustic Technique and Long Short-term Memory Network

“…Meanwhile a comparison with the state-of-the-art techniques in Table 3 showed superiority in the performance of our diagnostic method. Unlike the study in [23], our technique is unaffected to ambient light with the use of the high power laser source. In addition, SFDI is reported in [23] to suffer from limited imaging depth and require rigid control of technique.…”

“…But variability in the quality of the image captured using the CytoCam incident dark field imaging camera system and the background noises were reported as the potential confounding factors precluding clinical evaluation. Two other works in this direction is by Mason et al [23] and Ossama et al [24]. The authors in [23] suggested the use of generative adversarial network (GAN) to estimate both uncorrected and profile-corrected tissues oxygenation, and showed an accuracy of 96.5 %.…”

“…Two other works in this direction is by Mason et al [23] and Ossama et al [24]. The authors in [23] suggested the use of generative adversarial network (GAN) to estimate both uncorrected and profile-corrected tissues oxygenation, and showed an accuracy of 96.5 %. Meanwhile the method in [24] includes a two-step training of CNN model to classify microscopic images for functional blood flow, and achieved an accuracy of 83 %.…”

Deep Learning in Biomedical Optics

“…Optical properties can also be estimated more quickly using a lighter‐weight twin U‐Net architecture with a GPU‐optimized look‐up table [103]. Further, chromophores can be computed in real‐time with reduced error compared with an intermediate optical property inference by directly computing concentrations from structured illumination at multiple wavelengths using conditional GANs [155].…”