Effects of MRI acquisition parameter variations and protocol heterogeneity on the results of texture analysis and pattern discrimination: An application‐oriented study

TLDR

MRI texture features are known to be highly sensitive to signal‑to‑noise ratio and spatial resolution, limiting their clinical utility. The study aims to quantify how variations in acquisition parameters—number of acquisitions, repetition time, echo time, and sampling bandwidth—affect different texture feature categories across spatial resolutions, with a focus on protocol heterogeneity. Experiments used polystyrene sphere and agar gel phantoms imaged on a 3.0 T scanner with T2‑weighted multislice multiecho sequences, and pattern discrimination was performed using linear discriminant analysis and k‑nearest neighbor classification. Results show that texture features become increasingly sensitive at higher spatial resolution, yet at sufficiently high resolution variations in acquisition parameters have little impact on discrimination, and co‑occurrence matrix features outperform others, enabling reliable pattern discrimination even with heterogeneous acquisition settings.

Abstract

MRI texture features are generally considered to be sensitive to variations in signal‐to‐noise ratio and spatial resolution, which represents an obstacle for the widespread clinical application of texture‐based pattern discrimination with MRI. This study investigates the sensitivity of texture features of different categories (co‐occurrence matrix, run‐length matrix, absolute gradient, autoregressive model, and wavelet transform) to variations in the number of acquisitions (NAs), repetition time (TR), echo time (TE), and sampling bandwidth (SBW) at different spatial resolutions. Special emphasis was placed on the influence of MRI protocol heterogeneity and implications for the results of pattern discrimination. Experiments were performed using two polystyrene spheres and agar gel phantoms with different nodular patterns. T2‐weighted multislice multiecho images were obtained using a 3.0 T scanner equipped with a microimaging gradient insert coil. Linear discriminant analysis and k nearest neighbor classification were used for texture‐based pattern discrimination. Results show that texture features of all categories are increasingly sensitive to acquisition parameter variations with increasing spatial resolution. Nevertheless, as long as the spatial resolution is sufficiently high, variations in NA, TR, TE, and SBW have little effect on the results of pattern discrimination. Texture features derived from the co‐occurrence matrix are superior to features of other categories because they enable discrimination of different patterns close to the resolution limits for the smallest structures of physical texture even for datasets that are heterogeneous with regard to different acquisition parameters, including spatial resolution.