TY - GEN
T1 - Improved coronary artery calcium (CAC) detection in conventional CT with deep-learning image de-blurring
AU - Wülker, Christian
AU - van der Werf, Niels R.
AU - Schnellbächer, Nikolas D.
AU - Greuter, Marcel J.W.
AU - Grass, Michael
N1 - Publisher Copyright:
© 2024 SPIE.
PY - 2024/4/1
Y1 - 2024/4/1
N2 - We investigated the impact of a CNN-based deep-learning (DL) image de-blurring algorithm on coronary artery calcium (CAC) detection performance in conventional CT imaging. Our approach comprises first de-noising the image with a state-of-the-art CNN-based image de-noising algorithm. With improved SNR, it is then possible to sharpen the image with a CNN-based image de-blurring algorithm. We train such networks using natural images, i.e., a large set of diverse photographs. The de-noising strength in the final image can be adjusted by blending back the estimated noise from the first step to the desired degree. To assess the impact of the de-blurring algorithm, we scanned an anthropomorphic phantom containing 100 small calcifications on a CT system using a CAC scoring protocol. Data were acquired at clinical and high dose, and subsequently reconstructed with and without the DL de-blurring algorithm, using 25% of the maximum de-noising strength. For each small CAC, detectability was defined as the ability to calculate an Agatston score (at least 3 adjacent voxels exceeding 130 HU). For the high dose scans, CAC detectability increased from 39% for the standard reconstruction to 49% with de-blurring. The same 39% CAC detectability at high dose without de-blurring was obtained with routine dose with de-blurring. In this work, we also show some visual impressions of applying our DL de-blurring method to clinical cardiac data.
AB - We investigated the impact of a CNN-based deep-learning (DL) image de-blurring algorithm on coronary artery calcium (CAC) detection performance in conventional CT imaging. Our approach comprises first de-noising the image with a state-of-the-art CNN-based image de-noising algorithm. With improved SNR, it is then possible to sharpen the image with a CNN-based image de-blurring algorithm. We train such networks using natural images, i.e., a large set of diverse photographs. The de-noising strength in the final image can be adjusted by blending back the estimated noise from the first step to the desired degree. To assess the impact of the de-blurring algorithm, we scanned an anthropomorphic phantom containing 100 small calcifications on a CT system using a CAC scoring protocol. Data were acquired at clinical and high dose, and subsequently reconstructed with and without the DL de-blurring algorithm, using 25% of the maximum de-noising strength. For each small CAC, detectability was defined as the ability to calculate an Agatston score (at least 3 adjacent voxels exceeding 130 HU). For the high dose scans, CAC detectability increased from 39% for the standard reconstruction to 49% with de-blurring. The same 39% CAC detectability at high dose without de-blurring was obtained with routine dose with de-blurring. In this work, we also show some visual impressions of applying our DL de-blurring method to clinical cardiac data.
KW - clinical task-based metrics
KW - Computed tomography (CT)
KW - coronary artery calcium
KW - de-blurring
KW - deep learning
KW - denoising
KW - image quality
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85193538977&partnerID=8YFLogxK
U2 - 10.1117/12.3006693
DO - 10.1117/12.3006693
M3 - Conference contribution
AN - SCOPUS:85193538977
VL - 12925
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2024
A2 - Fahrig, Rebecca
A2 - Sabol, John M.
A2 - Li, Ke
PB - SPIE
T2 - Medical Imaging 2024: Physics of Medical Imaging
Y2 - 19 February 2024 through 22 February 2024
ER -