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.
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.
Xin Tie,Yinsheng Li,Ran Zhang,Ke Li, andGuanghong 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.
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.
The alert did not successfully save. Please try again later.
Xin Tie, Yinsheng Li, Ran Zhang, Ke Li, 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