Stent enhancement using marker response network and focus conversion learning in x-ray fluoroscopy sequences

Chengyang Wu; Pu Zhang; Yan Xu

doi:10.1117/12.2580810

15 February 2021 Stent enhancement using marker response network and focus conversion learning in x-ray fluoroscopy sequences

Chengyang Wu, Pu Zhang, Yan Xu

Author Affiliations +

Proceedings Volume 11595, Medical Imaging 2021: Physics of Medical Imaging; 115953B (2021) https://doi.org/10.1117/12.2580810
Event: SPIE Medical Imaging, 2021, Online Only

Conference Poster

Abstract

Coronary heart disease is a common cause of death for human being. To treat artery stenosis due to accumulation of atheromatous plaques, stents are implanted to support the narrowing vessel. The relative position between stent and vascular wall is a critical factor for evaluating the treatment. However, low signal to noise ratio (SNR) of fluoroscopy sequences make it difficult for doctors to observe the stents clearly. In order to improve the clarity of stent effectively, the paper describes a novel algorithm based on deep neural network for stent markers detection so as to realize the time domain stacking. In this step, the response map generation model with weighted loss was designed to concentrate on small objects detection, which has unbalanced annotation between background and targets. In addition, a focus conversion learning algorithm by deblurring network was proposed for edge sharpness and the spatial resolution improvement to decrease influences by focus size. It can locate the marker pair successfully in both phantom and clinical images with 84.04% correction rate in marker detection and decrease the mean square error in the focus conversion algorithm. After quantitative indexes comparison and observation, it reveals that the proposed algorithm can effectively enhance stents without manual annotation, which provides the assistance to evaluate the treatment exactly.

Conference Presentation

Citation Download Citation

Chengyang Wu, Pu Zhang, and Yan Xu "Stent enhancement using marker response network and focus conversion learning in x-ray fluoroscopy sequences", Proc. SPIE 11595, Medical Imaging 2021: Physics of Medical Imaging, 115953B (15 February 2021); https://doi.org/10.1117/12.2580810

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