Detectability of Small Low-Attenuation Lesions with Deep Learning CT Image Reconstruction: A 24-Reader Phantom Study

8Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

BACKGROUND. Iterative reconstruction (IR) techniques are susceptible to contrast-dependent spatial resolution, limiting overall radiation dose reduction potential. Deep learning image reconstruction (DLIR) may mitigate this limitation. OBJECTIVE. The purpose of our study was to evaluate low-contrast detectability performance and radiation-saving potential of a DLIR algorithm in comparison with filtered back projection (FBP) and IR using a human multireader noninferiority study design and task-based observer modeling. METHODS. A dual-phantom construct, consisting of a low-contrast detectability module (21 low-contrast hypoattenuating objects in seven sizes [2.4–10.0 mm] and three contrast levels [–15, –10, –5 HU] embedded within liver-equivalent background) and a phantom, was imaged at five radiation exposures (CTDIvol range, 1.4–14.0 mGy; size-specific dose estimate, 2.5–25.0 mGy; 90%-, 70%-, 50%-, and 30%-reduced radiation levels and full radiation level) using an MDCT scanner. Images were reconstructed using FBP, hybrid IR (ASiR-V), and DLIR (TrueFidelity). Twenty-four readers of varying experience levels evaluated images using a two-alternative forced choice. A task-based observer model (detectability index [d’]) was calculated. Reader performance was estimated by calculating the AUC using a noninferiority method. RESULTS. Compared with FBP and IR methods at routine radiation levels, DLIR medium and DLIR high settings showed noninferior performance through a 90% radiation reduction (except DLIR medium setting at 70% reduced level). The IR method was noninferior to routine radiation FBP only for 30% and 50% radiation reductions. No significant difference in d’ was observed between routine radiation FBP and DLIR high setting through a 70% radiation reduction. Reader experience was not correlated with diagnostic accuracy (R2 = 0.005). CONCLUSION. Compared with FBP or IR methods at routine radiation levels, certain DLIR algorithm weightings yielded noninferior low-contrast detectability with radiation reductions of up to 90% as measured by 24 human readers and up to 70% as assessed by a task-based observer model. CLINICAL IMPACT. DLIR has substantial potential to preserve contrast-dependent spatial resolution for the detection of hypoattenuating lesions at decreased radiation levels in a phantom model, addressing a major shortcoming of current IR techniques.

Author supplied keywords

Cite

CITATION STYLE

APA

Toia, G. V., Zamora, D. A., Singleton, M., Liu, A., Tan, E., Leng, S., … Mileto, A. (2023). Detectability of Small Low-Attenuation Lesions with Deep Learning CT Image Reconstruction: A 24-Reader Phantom Study. In American Journal of Roentgenology (Vol. 220, pp. 283–295). American Roentgen Ray Society. https://doi.org/10.2214/AJR.22.28407

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free