Transient Motion Classification Through Turbid Volumes via Parallelized Single-Photon Detection and Deep Contrastive Embedding

• DOI: 10.3389/fnins.2022.908770
• Publication Date: 2022-07-08T07:34:48Z
• Authors: Shiqi Xu; Wenhui Liu; Xi Yang; Joakim Jönsson; Ruobing Qian; Paul McKee; Kanghyun Kim; Pavan Chandra Konda; Kevin C. Zhou; Lucas Kreiß; Haoqian Wang; Edouard Berrocal; Scott A. Huettel; Roarke Horstmeyer
• Keywords: FOS: Computer and information sciences; contrastive learning; Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Computer Science - Computer Vision and Pattern Recognition; FOS: Physical sciences; Neurosciences. Biological psychiatry. Neuropsychiatry; SPAD array; Electrical Engineering and Systems Science - Image and Video Processing; multimode fiber; diffuse correlation; self-supervised learning; FOS: Electrical engineering, electronic engineering, information engineering; ddc:620; zero-shot learning; RC321-571; Physics - Optics; Neuroscience; Optics (physics.optics)

Fast noninvasive probing of spatially varying decorrelating events, such as cerebral blood flow beneath the human skull, is an essential task in various scientific and clinical settings. One of the primary optical techniques used is diffuse correlation spectroscopy (DCS), whose classical implementation uses a single or few single-photon detectors, resulting in poor spatial localization accuracy and relatively low temporal resolution. Here, we propose a technique termed ClassifyingRapid decorrelationEvents viaParallelized single photon dEtection (CREPE), a new form of DCS that can probe and classify different decorrelating movements hidden underneath turbid volume with high sensitivity using parallelized speckle detection from a 32 × 32 pixel SPAD array. We evaluate our setup by classifying different spatiotemporal-decorrelating patterns hidden beneath a 5 mm tissue-like phantom made with rapidly decorrelating dynamic scattering media. Twelve multi-mode fibers are used to collect scattered light from different positions on the surface of the tissue phantom. To validate our setup, we generate perturbed decorrelation patterns by both a digital micromirror device (DMD) modulated at multi-kilo-hertz rates, as well as a vessel phantom containing flowing fluid. Along with a deep contrastive learning algorithm that outperforms classic unsupervised learning methods, we demonstrate our approach can accurately detect and classify different transient decorrelation events (happening in 0.1–0.4 s) underneath turbid scattering media, without any data labeling. This has the potential to be applied to non-invasively monitor deep tissue motion patterns, for example identifying normal or abnormal cerebral blood flow events, at multi-Hertz rates within a compact and static detection probe.