Material decomposition for photon-counting CT using a flux-independent neural network

James D. Castiglioni; Emil Y. Sidky; Taly Gilat Schmidt

doi:10.1117/12.2655714

7 April 2023 Material decomposition for photon-counting CT using a flux-independent neural network

James D. Castiglioni, Emil Y. Sidky, Taly Gilat Schmidt

Proceedings Volume 12463, Medical Imaging 2023: Physics of Medical Imaging; 124634A (2023) https://doi.org/10.1117/12.2655714
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Photon counting detectors provide improved resolution and dose efficiency compared to scintillating detectors, with the potential for improved material decomposition. However, the measured counts may be inaccurate due to pulse pileup, which can cause material decomposition errors. Prior work demonstrated that Neural Networks (NN) can perform accurate material decomposition for a range of flux levels when trained at each specific tube current [1]. However, training a NN for each tube current is impractical for diagnostic CT because the tube current is continuously modulated. This study investigates a material decomposition NN trained and applied across a range of tube current settings. The NN was trained using calibration step-wedge data from a range of tube currents representing flux levels of 14% to 51.3% of the maximum detector count rate. We refer to this network as ‘flux-independent’ as it can be applied to flux levels not seen in training. The material decomposition accuracy of the flux-independent network was evaluated and compared to that of a NN trained at one flux level, (i.e., ‘flux-specific’ network). The networks were first compared using data from an experimentally-verified simulation model, while experimental evaluation is underway.

Citation Download Citation

James D. Castiglioni, Emil Y. Sidky, and Taly Gilat Schmidt "Material decomposition for photon-counting CT using a flux-independent neural network", Proc. SPIE 12463, Medical Imaging 2023: Physics of Medical Imaging, 124634A (7 April 2023); https://doi.org/10.1117/12.2655714

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