Deep-QC: a quality-check framework for quantitative material estimation from single-kV CT data

Xin Tie; Yinsheng Li; Ran Zhang; Ke Li; Guanghong Chen

doi:10.1117/12.2654515

7 April 2023 Deep-QC: a quality-check framework for quantitative material estimation from single-kV CT data

Xin Tie, Yinsheng Li, Ran Zhang, Ke Li, Guanghong Chen

Proceedings Volume 12463, Medical Imaging 2023: Physics of Medical Imaging; 1246340 (2023) https://doi.org/10.1117/12.2654515
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

It has been demonstrated that deep learning (DL) can be used to estimate material density images from single-energy CT, albeit estimation errors often occur especially when individual patient data fall out of the training data distribution. This work presents a DL-based quality-check mechanism, Deep-QC network, to automatically assess the accuracy of DL material images. The central idea is to learn the physics of the image acquisition systems such that DL images can be used to synthesize virtual raw data; by quantifying the consistency between the synthesized and actual raw data, physicians can be informed about the reliability of DL images.

Citation Download Citation

Xin Tie, Yinsheng Li, Ran Zhang, Ke Li, and Guanghong Chen "Deep-QC: a quality-check framework for quantitative material estimation from single-kV CT data", Proc. SPIE 12463, Medical Imaging 2023: Physics of Medical Imaging, 1246340 (7 April 2023); https://doi.org/10.1117/12.2654515

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