Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta.

Andra Heinrich,Felix G Meinel,Ebba Beller,Marc-André Weber,Felix Streckenbach,Justus Groß

doi:10.3390/diagnostics11112037

Andra Heinrich, Felix G Meinel + Show 4 more

Open Access

https://doi.org/10.3390/diagnostics11112037

Copy DOI

Journal: Diagnostics	Publication Date: Nov 3, 2021
Citations: 7	License type: CC BY 4.0

Affiliation: University Hospital and Clinics

Abstract

To evaluate the impact of a novel, deep-learning-based image reconstruction (DLIR) algorithm on image quality in CT angiography of the aorta, we retrospectively analyzed 51 consecutive patients who underwent ECG-gated chest CT angiography and non-gated acquisition for the abdomen on a 256-dectector-row CT. Images were reconstructed with adaptive statistical iterative reconstruction (ASIR-V) and DLIR. Intravascular image noise, the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were quantified for the ascending aorta, the descending thoracic aorta, the abdominal aorta and the iliac arteries. Two readers scored subjective image quality on a five-point scale. Compared to ASIR-V, DLIR reduced the median image noise by 51–54% for the ascending aorta and the descending thoracic aorta. Correspondingly, median CNR roughly doubled for the ascending aorta and descending thoracic aorta. There was a 38% reduction in image noise for the abdominal aorta and the iliac arteries, with a corresponding improvement in CNR. Median subjective image quality improved from good to excellent at all anatomical levels. In CT angiography of the aorta, DLIR substantially improved objective and subjective image quality beyond what can be achieved by state-of-the-art iterative reconstruction. This can pave the way for further radiation or contrast dose reductions.

Highlights

CT angiography is the predominant imaging modality for diagnosis, treatment planning and follow-up of aortic pathologies [1]
We excluded repeat examinations of identical patients, CT examinations that were not reconstructed with deep-learning-based image reconstruction (DLIR) and examinations performed without ECG-gating for the thoracic aorta
We observed that DLIR significantly reduces image noise and provides significantly higher signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in CT angiography of the aorta than a state-of-the-art iterative reconstruction algorithm (ASIR-V)

Summary

Introduction

CT angiography is the predominant imaging modality for diagnosis, treatment planning and follow-up of aortic pathologies [1]. With modern CT scanners, CT angiography offers excellent spatial and temporal resolution, short examination times and is readily available both in the emergency setting in patients with acute aortic syndrome and for elective surveillance, pre- or post-treatment imaging. Despite the marked reduction of radiation exposure with state-of-the-art techniques such as reducing the tube voltage, prospective ECG triggering and tube current modulation, cumulative radiation exposure is still a concern in those patients requiring repeated followup examinations [2]. With reductions in radiation dose, higher levels of image noise can complicate accurate assessment [3]. Iterative image reconstruction has been developed to decrease image noise and preserve or even improve image quality at a reduced dose [4].

Methods

Findings

Discussion

Conclusion