Pilot Lightweight Denoising Algorithm for Multiple Sclerosis on Spine MRI

Abstract

Multiple sclerosis (MS) is a severely debilitating disease which requires accurate and timely diagnosis. MRI is the primary diagnostic vehicle; however, it is susceptible to noise and artifact which can limit diagnostic accuracy. A myriad of denoising algorithms have been developed over the years for medical imaging yet the models continue to become more complex. We developed a lightweight algorithm which utilizes the image's inherent noise via dictionary learning to improve image quality without high computational complexity or pretraining through a process known as orthogonal matching pursuit (OMP). Our algorithm is compared to existing traditional denoising algorithms to evaluate performance on real noise that would commonly be encountered in a clinical setting. Fifty patients with a history of MS who received 1.5 T MRI of the spine between the years of 2018 and 2022 were retrospectively identified in accordance with local IRB policies. Native resolution 5 mm sagittal images were selected from T2 weighted sequences for evaluation using various denoising techniques including our proposed OMP denoising algorithm. Peak signal to noise ratio (PSNR) and structural similarity index (SSIM) were measured. While wavelet denoising demonstrated an expected higher PSNR than other models, its SSIM was variable and consistently underperformed its comparators (0.94 ± 0.10). Our pilot OMP denoising algorithm provided superior performance with greater consistency in terms of SSIM (0.99 ± 0.01) with similar PSNR to non-local means filtering (NLM), both of which were superior to other comparators (OMP 37.6 ± 2.2, NLM 38.0 ± 1.8). The superior performance of our OMP denoising algorithm in comparison to traditional models is promising for clinical utility. Given its individualized and lightweight approach, implementation into PACS may be more easily incorporated. It is our hope that this technology will provide improved diagnostic accuracy and workflow optimization for Neurologists and Radiologists, as well as improved patient outcomes.

Keywords: Computer vision; Denoising; MRI; Multiple sclerosis (MS); Orthogonal matching pursuit (OMP); Sparse representation.

Fig. 1

Representative display of an overcomplete dictionary from noisy patches. A matrix of vectors with more representative columns than rows is created using a modified least angle regression algorithm (LARS) which serves as an individualized “noise map” for the subsequent Orthogonal Matching Pursuit (OMP) denoising algorithm

Fig. 2

Denoising Examples with Compared Algorithms. Sagittal T2-weighted images of the thoracic spine demonstrating signal abnormalities of the spinal cord which were initially reported as artifact (a and b) versus true lesion (c and d). a Suspected Artifact #1, b Suspected Artifact #2, c Suspected Lesion #1, d Suspected Lesion #2