Radiation dose reduction with deep-learning image reconstruction for coronary computed tomography angiography

Abstract

Objectives Deep-learning image reconstruction (DLIR) offers unique opportunities for reducing image noise without degrading image quality or diagnostic accuracy in coronary CT angiography (CCTA). The present study aimed at exploiting the capabilities of DLIR to reduce radiation dose and assess its impact on stenosis severity, plaque composition analysis, and plaque volume quantification. Methods This prospective study includes 50 patients who underwent two sequential CCTA scans at normal-dose (ND) and lower-dose (LD). ND scans were reconstructed with Adaptive Statistical Iterative Reconstruction-Veo (ASiR-V) 100%, and LD scans with DLIR. Image noise (in Hounsfield units, HU) and quantitative plaque volumes (in mm3) were assessed quantitatively. Stenosis severity was visually categorized into no stenosis (0%), stenosis (< 20%, 20–50%, 51–70%, 71–90%, 91–99%), and occlusion (100%). Plaque composition was classified as calcified, non-calcified, or mixed. Results Reduction of radiation dose from ND scans with ASiR-V 100% to LD scans with DLIR at the highest level (DLIR-H; 1.4 mSv vs. 0.8 mSv, p < 0.001) had no impact on image noise (28 vs. 27 HU, p = 0.598). Reliability of stenosis severity and plaque composition was excellent between ND scans with ASiR-V 100% and LD scans with DLIR-H (intraclass correlation coefficients of 0.995 and 0.974, respectively). Comparison of plaque volumes using Bland–Altman analysis revealed a mean difference of − 0.8 mm3 (± 2.5 mm3) and limits of agreement between − 5.8 and + 4.1 mm3. Conclusion DLIR enables a reduction in radiation dose from CCTA by 43% without significant impact on image noise, stenosis severity, plaque composition, and quantitative plaque volume. Key Points •Deep-learning image reconstruction (DLIR) enables radiation dose reduction by over 40% for coronary computed tomography angiography (CCTA). •Image noise remains unchanged between a normal-dose CCTA reconstructed by ASiR-V and a lower-dose CCTA reconstructed by DLIR. •There is no impact on the assessment of stenosis severity, plaque composition, and quantitative plaque volume between the two scans.

Deep learning image reconstruction algorithm: impact on image quality in coronary computed tomography angiography

“…The high image quality ensured by DLIR, along with its a time-effective reconstruction process (≤ 50 s for axial CCTAs [38]), paves the way for its implementation in routine clinical practice. Dedicated CCTA acquisition protocols can be designed to exploit DLIR capabilities of reconstructing high-quality of low-dose examinations [17,18,27]. The improved image quality ensured by DLIR might also allow the use of dedicated low-volume contrast media injection protocols, particularly useful in elderly individuals or in patients with heart failure and impaired renal function.…”

“…Deep learning image reconstruction (DLIR) algorithms, based on deep convolutional neural networks, have been recently released by vendors holding promise for shorter reconstruction time and significantly reduced noise while preserving image texture [11][12][13]. DLIR applied to CCTA is currently under active investigation in different tasks, such as image optimization, classification, segmentation, prognosis and outcome prediction [14][15][16]; in particular, DLIR is achieving promising results compared to IR at specific strength levels [17][18][19]. Nevertheless, to the best of our knowledge, no previous investigations have assessed DLIR image quality in a broad comparison with IR and FBP.…”

Artificial Intelligence in Coronary CT Angiography: Current Status and Future Prospects

“…AI reduces the radiation dose by learning from CT images in regular-dose phases to remove noise from low-dose phases while maintaining image details (19). In addition, several studies have used DL methods, the radiation dose of CCTA has been significantly reduced by using a low scanning voltage, and the degree of radiation dose reduction is 36%−55.65% (19)(20)(21)(22)(23).…”

Iterative Reconstruction: State-of-the-Art and Future Perspectives

“…Similar results were found for LD CCTA scans: DLIR-H allowed 43% radiation dose reduction compared with ASiR-V-100%, without meaningful impact on image noise, stenosis severity, plaque composition, and quantitative plaque volume assessment. 77 A retrospective study of Kim et al 78 showed that LD chest CT reconstructed with DLIR for lung cancer screening allowed significantly lower noise, higher SNR and CNR, higher image contrast, lower image noise, and better structure identification, when compared with the ASiR-V technique. Jensen et al, 79 in a retrospective study on 40 oncologic patients who underwent abdominal CECT, demonstrated that DLIR had a better CNR, had reduced noise of 47%, and increased overall image quality and lesion diagnostic confidence, in comparison with ASiR-V.…”