Deep image prior for undersampling high-speed photoacoustic microscopy
25 January 2022 • 2:45 PM - 3:00 PM PST | Room 211 (Level 2 South)
Limited by the laser’s repetition rate, state-of-the-art high-speed photoacoustic microscopy (PAM) often sacrifices spatial sampling density for increased imaging speed over a large field-of-view. Here, we propose the use of deep image prior (DIP) to improve the image quality of undersampled PAM images. DIP requires neither pre-training nor fully-sampled ground truth, enabling its flexible adaptation on various imaging targets. Our results have demonstrated substantial improvement in PAM images with as few as 1.4 % of fully sampled pixels. Our approach outperforms interpolation methods, is competitive with pre-trained supervised deep-learning methods, and is readily translatable to other high-speed imaging modalities.
Duke Univ. (United States)
Tri Vu received his bachelor’s degree in Biomedical Engineering from State University of New York at Buffalo. He is currently a PhD candidate at Department of Biomedical Engineering in Duke University. His research interests are high-speed small-animal photoacoustic imaging systems and photoacoustic image enhancement using deep learning.