Drosophila melanogaster heart tube segmentation in optical coherence tomography through an attention LSTM U-Net model

Xiangping Ouyang; Abigail Matt; Fei Wang; Elena Gracheva; Chao Zhou

doi:10.1117/12.3000648

12 March 2024 Drosophila melanogaster heart tube segmentation in optical coherence tomography through an attention LSTM U-Net model

Xiangping Ouyang, Abigail Matt, Fei Wang, Elena Gracheva, Chao Zhou

Author Affiliations +

Proceedings Volume 12819, Diagnostic and Therapeutic Applications of Light in Cardiology 2024; 128190W (2024) https://doi.org/10.1117/12.3000648
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

The Drosophila Melanogaster is a powerful tool for cardiac research due to its ability for disease modeling. OCM provides cross-sectional images of its beating heart tube, which can be segmented to quantify heart parameters. Here, we expanded upon an optimized LSTM U-Net model introduced in 2023, by Fishman et al., to improve segmentation performance when artifacts are present. We incorporated attention gates via skip connections between each level of the LSTM U-Net model. This model increases the prediction intersection over union (IOU) from 0.86 to 0.89 for images with reflection artifacts and from 0.81 to 0.89 for those depicting frequent heart movement.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiangping Ouyang, Abigail Matt, Fei Wang, Elena Gracheva, and Chao Zhou "Drosophila melanogaster heart tube segmentation in optical coherence tomography through an attention LSTM U-Net model", Proc. SPIE 12819, Diagnostic and Therapeutic Applications of Light in Cardiology 2024, 128190W (12 March 2024); https://doi.org/10.1117/12.3000648

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