A Novel Singular Value Decomposition-Based Denoising Method in 4-Dimensional Computed Tomography of the Brain in Stroke Patients with Statistical Evaluation

Abstract

Computed tomography (CT) is a widely used medical imaging modality for diagnosing various diseases. Among CT techniques, 4-dimensional CT perfusion (4D-CTP) of the brain is established in most centers for diagnosing strokes and is considered the gold standard for hyperacute stroke diagnosis. However, because the detrimental effects of high radiation doses from 4D-CTP may cause serious health risks in stroke survivors, our research team aimed to introduce a novel image-processing technique. Our singular value decomposition (SVD)-based image-processing technique can improve image quality, first, by separating several image components using SVD and, second, by reconstructing signal component images to remove noise, thereby improving image quality. For the demonstration in this study, 20 4D-CTP dynamic images of suspected acute stroke patients were collected. Both the images that were and were not processed via the proposed method were compared. Each acquired image was objectively evaluated using contrast-to-noise and signal-to-noise ratios. The scores of the parameters assessed for the qualitative evaluation of image quality improved to an excellent rating (p < 0.05). Therefore, our SVD-based image-denoising technique improved the diagnostic value of images by improving their quality. The denoising technique and statistical evaluation can be utilized in various clinical applications to provide advanced medical services.

CT image denoising methods for image quality improvement and radiation dose reduction

“… 150 , 151 with the remaining approaches including filter‐based methods as well as hybrid methods. 152 , 153 , 154 , 155 , 156 , 157 To be noted that some models are originally developed, 61 , 62 , 65 , 66 , 68 , 70 , 72 , 73 , 77 , 122 , 153 while some are developed by modifying original models through modifying loss functions, or layers, or extending original models to different domains. 60 , 63 , 64 , 69 , 71 , 72 , 74 , 75 , 76 , 78 , 82 , 84 , 102 , 121 , 123 , 124 , 125 , 147 , 150 , 151 , 152 , 155 , 158 …”

“…Generalizability is an important consideration when evaluating the effectiveness of DL‐based CT image denoising models. Among 99 papers reviewed, only five studies conducted the independent test 106,139,156,168,180 . An independent test if a mode can be able to effectively denoise CT images in a variety of contexts is necessary, however, this is not yet realized.…”

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

“…Noise reduction by SVD is performed by selecting an appropriate number of ranks k to estimate e in Equation ( 1 ). Various methods have been proposed for selecting the number of the rank [ 27 , 28 , 29 , 30 ]. However, in this study, the number of ranks that minimized the JS–divergence between the noise-free image and the noisy image was selected as the optimal number of ranks for denoising.…”

Coresets for the Average Case Error for Finite Query Sets

“…In addition, our algorithms extend also to SVD, PCA, and LMS where these methods are known for their usages and efficiencies in discovering a low dimensional representation of high dimensional data. From a practical point of view, SVD showed promising results when dealing with on calibration of a star sensor on-orbit calibration [ 52 ], denoising a 4-dimensional computed tomography of the brain in stroke patients [ 53 ], removal of cardiac interference from trunk electromyogram [ 54 ], among many other applications.…”