A deep-learning method for the denoising of ultra-low dose chest CT in coronary artery calcium score evaluation. Issue 7 (July 2022)

• Record Type: Journal Article
• Authors: Klug, M.; Shemesh, J.; Green, M.; Mayer, A.; Kerpel, A.; Konen, E.; Marom, E.M.
• Is Part Of: Clinical radiology. Volume 77:Issue 7(2022)
• Page Start: e509
• Page End: e517
• Publication Date: 2022-07
• Subjects: Medical radiology -- Periodicals; Radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiology -- Periodicals; Societies, Medical -- Periodicals; Medical radiology; Radiotherapy; Electronic journals; Periodicals; 616.0757
• DOI: 10.1016/j.crad.2022.03.005
• Languages: English
• ISSNs: 0009-9260

Abstract

Abstract : Aim: To evaluate a novel deep-learning denoising method for ultra-low dose CT (ULDCT) in the assessment of coronary artery calcium score (CACS). Materials and methods: Sixty adult patients who underwent two unenhanced chest CT examinations, a normal dose CT (NDCT) and an ULDCT, were enrolled prospectively between September 2017 to December 201. A special training set was created to learn the characteristics of the real noise affecting the ULDCT implementing a fully convolutional neural network with batch normalisation. Subsequently, the 60 ULDCTs of the evaluation set were denoised. Two blinded radiologists assessed the NDCT, ULDCT, and denoised-ULDCT (DULDCT), assigning a CACS and categorised each scan as having a score above or below 100 and presence of calcifications (score 0 versus >0). Statistical analysis was used to evaluate the agreement between the readers and differences in CACSs between each imaging method. Results: After excluding one patient, the cohort included 59 patients (median age 67 years, 58% men). The ULDCT median effective radiation dose (ERD) was 0.172 mSv, which was 2.8% of the NDCT median ERD. Denoising improved the signal-to-noise ratio by 27.7% ( p< 0.001). Interobserver agreement was almost perfect between readers (intraclass correlation coefficient >0.993). CACSs were lower for ULDCT and DULDCT as compared to the NDCT ( p ≤ 0.001). In differentiating between the presence and absence of coronary artery calcifications, DULDCT showed greater accuracy (98–100%) and positive likelihood ratio (14.29–>99) compared to ULDCT (92% and 2.78, respectively). Conclusion: DULCT significantly reduced the image noise and better identified patients with no coronary artery calcifications than native ULDCT. Highlights: Ultra-low dose CT (ULDCT) significantly reduces effective radiation dose. Denoised ultra-low dose CT (DULDCT) improved signal-to-noise ratio by 27.7%. DULDCT reduces calcium blooming and beam hardening artefacts DULDCT correctly identifies all patients with CACS≤100 and 93% with CACS>100. DULDCT better identifies patients with CACS = 0 compared to native ULDCT.