1. Rapid tissue oxygenation mapping from snapshot structured-light images with adversarial deep learning
- Author
-
Mason T. Chen and Nicholas J. Durr
- Subjects
Paper ,FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer science ,Swine ,optical property ,Computer Vision and Pattern Recognition (cs.CV) ,Biomedical Engineering ,Computer Science - Computer Vision and Pattern Recognition ,Special Series on Artificial Intelligence and Machine Learning in Biomedical Optics ,spatial frequency-domain imaging ,01 natural sciences ,Data modeling ,Machine Learning (cs.LG) ,010309 optics ,Biomaterials ,Deep Learning ,Robustness (computer science) ,0103 physical sciences ,FOS: Electrical engineering, electronic engineering, information engineering ,Animals ,Lung ,Ground truth ,business.industry ,Deep learning ,Image and Video Processing (eess.IV) ,Pattern recognition ,Oxygenation ,Electrical Engineering and Systems Science - Image and Video Processing ,Hand ,Atomic and Molecular Physics, and Optics ,Electronic, Optical and Magnetic Materials ,machine learning ,Snapshot (computer storage) ,Artificial intelligence ,business ,Preclinical imaging ,Structured light - 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 single-snapshot 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.
- Published
- 2020
- Full Text
- View/download PDF