Photonics West 2022 in San Francisco
Starts Saturday
>
Conference 11960 > Paper 11960-77
Paper 11960-77

Deep image prior for undersampling high-speed photoacoustic microscopy

25 January 2022 • 2:45 PM - 3:00 PM PST | Room 211 (Level 2 South)

Abstract

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.

Presenter

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.
Presenter/Author
Duke Univ. (United States)
Author
Duke Univ. (United States)
Author
Daiwei Li
Duke Univ. (United States)
Author
Harvard Medical School (United States)
Author
Xiaoyi Zhu
Duke Univ. (United States)
Author
Duke Univ. (United States)
Author
The Univ. of Southern California (United States)
Author
Tsinghua Univ. (China)
Author
Tsinghua Univ. (China)
Author
Yu Shrike Zhang
Harvard Medical School (United States)
Author
The Univ. of Southern California (United States)
Author
Roarke Horstmeyer
Duke Univ. (United States)
Author
Duke Univ. (United States)