- Medical Signal and Image Processing
- Optical Imaging
- Computational Neuroscience
- Machine learning and deep learning in BME
The first project that I’m working on is a non – invasive way to detect blood flow in deeper layers of the brain. We performed the first clinical use of time- gated diffuse correlation spectroscopy (TG-DCS) using SNSPD at 1064 nm on mice and human data to resolve non-invasive, continuous, and pulsatile blood flow within brain tissue after injury. In this study, I was able to adjust the photon gating to manipulate the temporal resolution such that pulsatile blood flow could be resolved in a specific layer of brain.
The second project is to develop a deep learning model that that can extract a well fitting model for g2 curve. Diffuse correlation spectroscopy (DCS) is increasingly used in the optical imaging field to assess blood flow in humans due to its non-invasive, real-time characteristics and its ability to provide label- free, bedside monitoring of blood flow changes. Previous DCS studies have utilized a traditional curve fitting of the analytical or Monte Carlo models to extract the blood flow changes, which are computationally demanding and less accurate when the signal to noise ratio decreases. The proposed deep learning inverse model will enable real-time and accurate tissue blood flow quantification with the DCS technique.
The third project is using a 500 × 500 SPAD pixel array, fabricated in 0.18 μm CMOS technology. The sensor has two contiguous time gates, a novel addition that allows for a temporal aperture of 100%. The gates are adjustable with a temporal resolution of 17.9 ps. We will use this camera to measure blood flow changes in deep layer of the brain since it is high-speed, and large-format image sensors.
