Open AccessMR Denoising Increases Radiomic Biomarker Precision and Reproducibility in Oncologic Imaging
Author(s) -
Matías Fernández-Patón,
L. Cerdá Alberich,
C. Sangüesa Nebot,
Blanca Martínez de las Heras,
Diana VeigaCanuto,
Adela Cañete Nieto,
Luis Martı́-Bonmatı́
Publication year - 2021
Publication title -
journal of digital imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.055
H-Index - 58
eISSN - 1618-727X
pISSN - 0897-1889
DOI - 10.1007/s10278-021-00512-8
Subject(s) - reproducibility , noise reduction , artificial intelligence , image quality , filter (signal processing) , noise (video) , computer science , median filter , metric (unit) , standard deviation , computer vision , mathematics , pattern recognition (psychology) , image processing , statistics , image (mathematics) , operations management , economics
Several noise sources, such as the Johnson-Nyquist noise, affect MR images disturbing the visualization of structures and affecting the subsequent extraction of radiomic data. We evaluate the performance of 5 denoising filters (anisotropic diffusion filter (ADF), curvature flow filter (CFF), Gaussian filter (GF), non-local means filter (NLMF), and unbiased non-local means (UNLMF)), with 33 different settings, in T2-weighted MR images of phantoms (N = 112) and neuroblastoma patients (N = 25). Filters were discarded until the most optimal solutions were obtained according to 3 image quality metrics: peak signal-to-noise ratio (PSNR), edge-strength similarity-based image quality metric (ESSIM), and noise (standard deviation of the signal intensity of a region in the background area). The selected filters were ADFs and UNLMs. From them, 107 radiomics features preservation at 4 progressively added noise levels were studied. The ADF with a conductance of 1 and 2 iterations standardized the radiomic features, improving reproducibility and quality metrics.