Deep Learning Denoising of Low-Dose Computed Tomography Chest Images: A Quantitative and Qualitative Image Analysis. Issue 2 (28th March 2023)

• Record Type: Journal Article
• Authors: Azour, Lea; Hu, Yunan; Ko, Jane P.; Chen, Baiyu; Knoll, Florian; Alpert, Jeffrey B.; Brusca-Augello, Geraldine; Mason, Derek M.; Wickstrom, Maj L.; Kwon, Young Joon (Fred); Babb, James; Liang, Zhengrong; Moore, William H.
• Is Part Of: Journal of computer assisted tomography. Volume 47:Issue 2(2023)
• Page Start: 212
• Page End: 219
• Publication Date: 2023-03-28
• Subjects: low-dose CT -- denoising -- neural network -- machine learning -- SSIM -- FID; Tomography -- Periodicals; Tomography -- Periodicals; Tomography; Periodicals; 616.0757
• DOI: 10.1097/RCT.0000000000001405
• Languages: English
• ISSNs: 0363-8715

Abstract

Abstract : Purpose: To assess deep learning denoised (DLD) computed tomography (CT) chest images at various low doses by both quantitative and qualitative perceptual image analysis. Methods: Simulated noise was inserted into sinogram data from 32 chest CTs acquired at 100 mAs, generating anatomically registered images at 40, 20, 10, and 5 mAs. A DLD model was developed, with 23 scans selected for training, 5 for validation, and 4 for test. Quantitative analysis of perceptual image quality was assessed with Structural SIMilarity Index (SSIM) and Fréchet Inception Distance (FID). Four thoracic radiologists graded overall diagnostic image quality, image artifact, visibility of small structures, and lesion conspicuity. Noise-simulated and denoised image series were evaluated in comparison with one another, and in comparison with standard 100 mAs acquisition at the 4 mAs levels. Statistical tests were conducted at the 2-sided 5% significance level, with multiple comparison correction. Results: At the same mAs levels, SSIM and FID between noise-simulated and reconstructed DLD images indicated that images were closer to a perfect match with increasing mAs (closer to 1 for SSIM, and 0 for FID). In comparing noise-simulated and DLD images to standard-dose 100-mAs images, DLD improved SSIM and FID. Deep learning denoising improved SSIM of 40-, 20-, 10-, and 5-mAs simulations in comparison with standard-dose 100-mAs images, with change in SSIM from 0.91 to 0.94, 0.87 to 0.93, 0.67 to 0.87, and 0.54 to 0.84, respectively. Deep learning denoising improved FID of 40-, 20-, 10-, and 5-mAs simulations in comparison with standard-dose 100-mAs images, with change in FID from 20 to 13, 46 to 21, 104 to 41, and 148 to 69, respectively. Qualitative image analysis showed no significant difference in lesion conspicuity between DLD images at any mAs in comparison with 100-mAs images. Deep learning denoising images at 10 and 5 mAs were rated lower for overall diagnostic image quality ( P < 0.001), and at 5 mAs lower for overall image artifact and visibility of small structures ( P = 0.002), in comparison with 100 mAs. Conclusions: Deep learning denoising resulted in quantitative improvements in image quality. Qualitative assessment demonstrated DLD images at or less than 10 mAs to be rated inferior to standard-dose images.