Radiation dose reduction and image quality improvement with ultra-high resolution temporal bone CT using deep learning-based reconstruction: An anatomical study - 14/05/24

Doi : 10.1016/j.diii.2024.05.001

Fatma Boubaker ^a, Ulysse Puel ^a,^b,^c, Michael Eliezer ^d, Gabriela Hossu ^b,^c, Bouchra Assabah ^e, Karim Haioun ^f, Alain Blum ^a,^b,^c, Pedro Augusto Gondim-Teixeira ^a,^b,^c, Cécile Parietti-Winkler ^g, Romain Gillet ^a,^b,^c,^⁎
^a Guilloz Imaging Department, Central Hospital, University Hospital Center of Nancy, 54000, Nancy, France
^b Université de Lorraine, INSERM, IADI, 54000, Nancy, France
^c Université de Lorraine, CIC, Innovation Technologique, University Hospital Center of Nancy, 54000, Nancy, France
^d Department of Radiology, Hôpital des 15-20, 75571 Paris, France
^e Department of Anatomy, University Hospital Center of Nancy, 54000, Nancy, France
^f Canon Medical Systems Corporation, Kawasaki-shi, 212-0015 Kanagawa, Japan
^g ENT Surgery Department, Central Hospital, University Hospital Center of Nancy, 54000 Nancy, France

^⁎Corresponding author.

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Tuesday 14 May 2024

Highlights

•	Ultra-high-resolution CT of the temporal bone with deep learning reconstruction can be performed with up to a tenfold reduction in radiation dose by comparison with conventional high-resolution CT while maintaining image quality.
•	The use of deep learning with ultra-high-resolution CT at the same radiation dose as conventional high-resolution CT allows a marked increase in image quality of the middle and inner ear.
•	The use of deep learning with ultra-high-resolution CT helps achieve more complete bony coverage of the facial nerve and better representation of the cochlear spiral osseous lamina compared to hybrid iterative reconstruction algorithms.

Le texte complet de cet article est disponible en PDF.

Abstract

Purpose

The purpose of this study was to evaluate the achievable radiation dose reduction of an ultra-high resolution computed tomography (UHR-CT) scanner using deep learning reconstruction (DLR) while maintaining temporal bone image quality equal to or better than high-resolution CT (HR-CT).

Materials and methods

UHR-CT acquisitions were performed with variable tube voltages and currents at eight different dose levels (volumic CT dose index [CTDIvol] range: 4.6–79 mGy), 1024² matrix, and 0.25 mm slice thickness and reconstructed using DLR and hybrid iterative reconstruction (HIR) algorithms. HR-CT images were acquired using a standard protocol (120 kV/220 mAs; CTDI vol, 54.2 mGy, 512² matrix, and 0.5 mm slice thickness). Two radiologists rated the image quality of seven structures using a five point confidence scale on six cadaveric temporal bone CTs. A global image quality score was obtained for each CT protocol by summing the image quality scores of all structures.

Results

With DLR, UHR-CT at 120 kV/220 mAs (CTDIvol, 50.9 mGy) and 140 kV/220 mAs (CTDIvol, 79 mGy) received the highest global image quality scores (4.88 ± 0.32 [standard deviation (SD)] [range: 4–5] and 4.85 ± 0.35 [range: 4–5], respectively; P = 0.31), while HR-CT at 120 kV/220 mAs and UHR-CT at 120 kV/20 mAs received the lowest (i.e., 3.14 ± 0.75 [SD] [range: 2–5] and 2.97 ± 0.86 [SD] [range: 1–5], respectively; P = 0.14). All the DLR protocols had better image quality scores than HR-CT with HIR.

Conclusion

UHR-CT with DLR can be performed with up to a tenfold reduction in radiation dose compared to HR-CT with HIR while maintaining or improving image quality.

Le texte complet de cet article est disponible en PDF.

Keywords : Computed tomography, Deep learning, Image enhancement, Image reconstruction, Temporal bone

Abbreviations : AiCE, CT, CTDI, DLR, HR-CT, HIR, HU, SD, UHR-CT