Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 31;9(5):1629-1637.
doi: 10.3390/tomography9050130.

Deep Learning-Based Versus Iterative Image Reconstruction for Unenhanced Brain CT: A Quantitative Comparison of Image Quality

Andrea Cozzi  1 , Maurizio Cè  2 , Giuseppe De Padova  2 , Dario Libri  2 , Nazarena Caldarelli  2 , Fabio Zucconi  3 , Giancarlo Oliva  4 , Michaela Cellina  4
Affiliations

Deep Learning-Based Versus Iterative Image Reconstruction for Unenhanced Brain CT: A Quantitative Comparison of Image Quality

Andrea Cozzi et al. Tomography. .

Abstract

This exploratory retrospective study aims to quantitatively compare the image quality of unenhanced brain computed tomography (CT) reconstructed with an iterative (AIDR-3D) and a deep learning-based (AiCE) reconstruction algorithm. After a preliminary phantom study, AIDR-3D and AiCE reconstructions (0.5 mm thickness) of 100 consecutive brain CTs acquired in the emergency setting on the same 320-detector row CT scanner were retrospectively analyzed, calculating image noise reduction attributable to the AiCE algorithm, artifact indexes in the posterior cranial fossa, and contrast-to-noise ratios (CNRs) at the cortical and thalamic levels. In the phantom study, the spatial resolution of the two datasets proved to be comparable; conversely, AIDR-3D reconstructions showed a broader noise pattern. In the human study, median image noise was lower with AiCE compared to AIDR-3D (4.7 vs. 5.3, p < 0.001, median 19.6% noise reduction), whereas AIDR-3D yielded a lower artifact index than AiCE (7.5 vs. 8.4, p < 0.001). AiCE also showed higher median CNRs at the cortical (2.5 vs. 1.8, p < 0.001) and thalamic levels (2.8 vs. 1.7, p < 0.001). These results highlight how image quality improvements granted by deep learning-based (AiCE) and iterative (AIDR-3D) image reconstruction algorithms vary according to different brain areas.

Keywords: brain computed tomography; deep learning-based reconstruction algorithms; image noise; image quality; iterative reconstruction algorithms.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Demonstration of the region of interest placement in the frontal cortex and adjacent WM on iterative reconstructions (a) and artificial intelligence-based reconstructions (b).
Figure 2
Figure 2
Demonstration of the region of interest placement in the right thalamus and adjacent WM of the internal capsule on iterative reconstructions (a) and artificial intelligence-based reconstructions (b).
Figure 3
Figure 3
Demonstration of the region of interest placement in the intrapetrous region to assess the image noise in the posterior fossa on iterative reconstructions (a) and artificial intelligence-based reconstructions (b).
Figure 4
Figure 4
Demonstration of the region of interest placement in the right centrum semiovale on iterative reconstructions (a) and artificial intelligence-based reconstructions (b) to assess the image noise.
Figure 5
Figure 5
Violin plots comparing image noise in the centrum semiovale, artifact index in the posterior fossa, and CNRs at cortical and thalamic levels between AIDR-3D and AiCE reconstructions.
See this image and copyright information in PMC

References

    1. Cellina M., Panzeri M., Floridi C., Martinenghi C.M.A., Clesceri G., Oliva G. Overuse of computed tomography for minor head injury in young patients: An analysis of promoting factors. Radiol. Med. 2018;123:507–514. doi: 10.1007/s11547-018-0871-x. - DOI - PubMed
    1. Leone E., Ferrari R., Trinci M., Cingolani E., Galluzzo M. Imaging features of electric scooter trauma: What an emergency radiologist needs to know. Radiol. Med. 2022;127:872–880. doi: 10.1007/s11547-022-01519-z. - DOI - PubMed
    1. Willemink M.J., Noël P.B. The evolution of image reconstruction for CT—From filtered back projection to artificial intelligence. Eur. Radiol. 2019;29:2185–2195. doi: 10.1007/s00330-018-5810-7. - DOI - PMC - PubMed
    1. Agostini A., Borgheresi A., Carotti M., Ottaviani L., Badaloni M., Floridi C., Giovagnoni A. Third-generation iterative reconstruction on a dual-source, high-pitch, low-dose chest CT protocol with tin filter for spectral shaping at 100 kV: A study on a small series of COVID-19 patients. Radiol. Med. 2021;126:388–398. doi: 10.1007/s11547-020-01298-5. - DOI - PMC - PubMed
    1. Geyer L.L., Schoepf U.J., Meinel F.G., Nance J.W., Bastarrika G., Leipsic J.A., Paul N.S., Rengo M., Laghi A., De Cecco C.N. State of the Art: Iterative CT Reconstruction Techniques. Radiology. 2015;276:339–357. doi: 10.1148/radiol.2015132766. - DOI - PubMed