SyNCCT: Synthetic Non-Contrast Images of the Brain from Single-Energy Computed Tomography Angiography

Thamm F, Taubmann O, Denzinger F, Jürgens M, Ditt H, Maier A (2021)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2021

Publisher: Springer

City/Town: Cham

Conference Proceedings Title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

Event location: Strasbourg FR

URI: https://link.springer.com/chapter/10.1007/978-3-030-87234-2_64

DOI: 10.1007/978-3-030-87234-2_64

Abstract

By injecting contrast agent during a CT acquisition, the vascular system can be enhanced. This acquisition type is known as CT Angiography (CTA). However, due to typically lower dose levels of CTA scans compared to non-contrast CT acquisitions (NCCT) and the employed reconstruction designed specifically for vessel reconstruction, soft tissue contrast in the brain parenchyma is usually subpar. Hence, an NCCT scan is preferred for the visualization of such tissue. We propose SyNCCT, an approach which synthesizes NCCT images from the CTA domain by removing enhanced vessel structures and improving soft tissue contrast. Contrary to virtual non-contrast (VNC) images based on dual energy scans, which target the physically accurate removal of iodine rather than generating a realistic NCCT with improved gray/white matter separation, our approach only requires a conventional single-energy acquisition. By design, our method integrates prior domain knowledge and employs residual learning as well as a discriminator to achieve perceptual realism. In our data set of patients with ischemic stroke, the absolute differences in automatic ASPECT scoring, which rates early signs of an occlusion in the anterior circulation on a scale from 0 (most severe) to 10 (no signs), was 0.78±0.75 (median of 1) when comparing our SyNCCT to the real NCCT images. Qualitatively, realistic appearance of the images was confirmed by means of a Turing test with a radiologist, who classified 64% of 64 (32 real, 32 generated) images correctly. Two other physicians classified 65% correctly, on average.

Authors with CRIS profile

Florian Thamm Lehrstuhl für Informatik 5 (Mustererkennung) Felix Denzinger Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

Siemens Healthineers DE Germany (DE) Siemens AG, Healthcare Sector DE Germany (DE)

How to cite

APA:

Thamm, F., Taubmann, O., Denzinger, F., Jürgens, M., Ditt, H., & Maier, A. (2021). SyNCCT: Synthetic Non-Contrast Images of the Brain from Single-Energy Computed Tomography Angiography. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. Strasbourg, FR: Cham: Springer.

MLA:

Thamm, Florian, et al. "SyNCCT: Synthetic Non-Contrast Images of the Brain from Single-Energy Computed Tomography Angiography." Proceedings of the Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, Strasbourg Cham: Springer, 2021.

BibTeX: Download