Noise Reduction Using Singular Value Decomposition with Jensen–Shannon Divergence for Coronary Computed Tomography Angiography

• Published in: Diagnostics (Basel) Vol. 13; no. 6; p. 1111
• Main Authors: Kasai, Ryosuke, Otsuka, Hideki
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 15.03.2023; MDPI
• Subjects: Analysis; Angiography; Approximation; Artificial intelligence; Cardiovascular disease; Care and treatment; coronary computed tomography angiography; Coronary heart disease; CT imaging; Decomposition; Deep learning; Diagnosis; Health aspects; Jensen–Shannon divergence; Linear algebra; Medical imaging; Methods; Neural networks; Noise control; noise reduction; Probability distribution; Risk factors; singular value decomposition; Tomography; Japan; noise reduction; coronary computed tomography angiography; Jensen–Shannon divergence; singular value decomposition
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics13061111

Coronary computed tomography angiography (CCTA) is widely used due to its improvements in computed tomography (CT) diagnostic performance. Unlike other CT examinations, CCTA requires shorter rotation times of the X-ray tube, improving the temporal resolution and facilitating the imaging of the beating heart in a stationary state. However, reconstructed CT images, including those of the coronary arteries, contain insufficient X-ray photons and considerable noise. In this study, we introduce an image-processing technique for noise reduction using singular value decomposition (SVD) for CCTA images. The threshold of SVD was determined on the basis of minimization of Jensen–Shannon (JS) divergence. Experiments were performed with various numerical phantoms and varying levels of noise to reduce noise in clinical CCTA images using the determined threshold value. The numerical phantoms produced 10% higher-quality images than the conventional noise reduction method when compared on a quantitative SSIM basis. The threshold value determined by minimizing the JS–divergence was found to be useful for efficient noise reduction in actual clinical images, depending on the level of noise.