Contrast-free segmentation of blood vessels using deep learning

Maryse Lapierre-Landry; Yehe Liu; Mahdi Bayat; David L. Wilson; Michael W. Jenkins M.D.

doi:10.1117/12.2650480

17 March 2023 Contrast-free segmentation of blood vessels using deep learning

Maryse Lapierre-Landry, Yehe Liu, Mahdi Bayat, David L. Wilson, Michael W. Jenkins M.D.

Proceedings Volume PC12355, Diagnostic and Therapeutic Applications of Light in Cardiology 2023; PC123550E (2023) https://doi.org/10.1117/12.2650480
Event: SPIE BiOS, 2023, San Francisco, California, United States

Abstract

Advances in three-dimensional (3D) microscopy are providing never-before-seen images of coronary microvasculature organization. However, it remains inaccessible to researchers due to difficult sample preparation and image analysis. We present a deep learning network that can segment the coronary microvasculature in 3D microscopy without vessel staining. The network is based on 3D U-net and accepts DAPI (nuclei) and autofluorescence (tissue structure) volumes as inputs. The network detects vessels with high accuracy when compared to the ground truth obtained from isolectin staining. Contrast-free segmentation of vessels simplifies sample preparation, frees fluorescent channels during imaging and opens the door toward user-friendly 3D microscopy.

Conference Presentation

Citation Download Citation

Maryse Lapierre-Landry, Yehe Liu, Mahdi Bayat, David L. Wilson, and Michael W. Jenkins M.D. "Contrast-free segmentation of blood vessels using deep learning", Proc. SPIE PC12355, Diagnostic and Therapeutic Applications of Light in Cardiology 2023, PC123550E (17 March 2023); https://doi.org/10.1117/12.2650480

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available