3D threat image projection through dual-energy decomposition

Alexander Emerman; Alexander DeMasi; Joshua Stroker; Patrick Cocola; Joe Palma; Ronald Krauss; Duane Karns

doi:10.1117/12.2665105

14 June 2023 3D threat image projection through dual-energy decomposition

Alexander Emerman, Alexander DeMasi, Joshua Stroker, Patrick Cocola, Joe Palma, Ronald Krauss, Duane Karns

Proceedings Volume 12531, Anomaly Detection and Imaging with X-Rays (ADIX) VIII; 125310D (2023) https://doi.org/10.1117/12.2665105
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Synthetic data are commonly used to train machine learning models in domains where real data are sparse. In this work, we describe a method to generate synthetic x-ray imaging data by inserting objects into a dual-energy computed tomography scan while simultaneously inserting the beam-hardening and noise artifacts that corrupt real data. This type of data augmentation is useful for training classifiers, for example, by artificially increasing the prevalence of objects of interest in a dataset. This work extends existing 3D Threat Image Projection methods by using dual-energy decomposition to model the energy-dependence of attenuation values in the sinogram data. By summing linear attenuation coefficient functions, objects can be inserted directly into a sinogram while accounting for beam-hardening in the insertion region. In addition, we introduce a calibration method to model the change in noise levels resulting from the insertion of attenuating objects. The performance of the method is demonstrated on a simple phantom scanned with a benchtop microCT system.

Conference Presentation

Citation Download Citation

Alexander Emerman, Alexander DeMasi, Joshua Stroker, Patrick Cocola, Joe Palma, Ronald Krauss, and Duane Karns "3D threat image projection through dual-energy decomposition", Proc. SPIE 12531, Anomaly Detection and Imaging with X-Rays (ADIX) VIII, 125310D (14 June 2023); https://doi.org/10.1117/12.2665105

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