Presentation
9 March 2023 In-vivo demonstration and validation of U-net based real-time photoacoustic imaging with LED arrays
Avijit Paul, Allison Sweeney, Christopher Nguyen, Srivalleesha Mallidi
Author Affiliations +
Abstract
Portable LED-based systems attempt to replace the bulky laser-based photoacoustic (PA) systems. The problem with LEDs is their low energy which generates low signal-to-noise-ratio (SNR) images. To obtain a high SNR image in real-time, we built a deep learning U-net model which transforms a low no. of frame-averaged image into a high no. of frame-averaged quality image. Both laser-based Vevo LAZR-X system and immunofluorescence histology staining show similar vascular organizations with hypoxic cores. We also achieved high SNR by running the algorithm on acoustic-resolution PA microscopy captured images. This generic network can be implemented in multiple scenarios.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Avijit Paul, Allison Sweeney, Christopher Nguyen, and Srivalleesha Mallidi "In-vivo demonstration and validation of U-net based real-time photoacoustic imaging with LED arrays", Proc. SPIE PC12379, Photons Plus Ultrasound: Imaging and Sensing 2023, PC1237919 (9 March 2023); https://doi.org/10.1117/12.2650767
Advertisement
Advertisement
KEYWORDS
Light emitting diodes

In vivo imaging

Signal to noise ratio

Image quality

Imaging arrays

Imaging systems

Photoacoustic imaging

Back to Top