A multicenter study on radiomic features from T₂‐weighted images of a customized MR pelvic phantom setting the basis for robust radiomic models in clinics

Abstract

To investigate the repeatability and reproducibility of radiomic features extracted from MR images and provide a workflow to identify robust features. Methods: T 2-weighted images of a pelvic phantom were acquired on three scanners of two manufacturers and two magnetic field strengths. The repeatability and reproducibility of features were assessed by the intraclass correlation coefficient and the concordance correlation coefficient, respectively, and by the within-subject coefficient of variation, considering repeated acquisitions with and without phantom repositioning, and with different scanner and acquisition parameters. The features showing intraclass correlation coefficient or concordance correlation coefficient >0.9 were selected, and their dependence on shape information (Spearman's ρ > 0.8) analyzed. They were classified for their ability to distinguish textures, after shuffling voxel intensities of images. Results: From 944 two-dimensional features, 79.9% to 96.4% showed excellent repeatability in fixed position across all scanners. A much lower range (11.2% to 85.4%) was obtained after phantom repositioning. Three-dimensional extraction did not improve repeatability performance. Excellent reproducibility between scanners was observed in 4.6% to 15.6% of the features, at fixed imaging parameters. In addition, 82.4% to 94.9% of the features showed excellent agreement when extracted from images acquired with echo times 5 ms apart, but decreased with increasing 1714 | BIANCHINI et Al.

Quantitative Magnetic Resonance Imaging for Biological Image-Guided Adaptive Radiotherapy

“…Technical validation (124)(125)(126) of qMRI measurements on MRIgRT systems is required to ensure that the results are also relevant outside the MRIgRT domain, in particular because the MR-part of the MRIgRT systems is different from diagnostic systems. Digital and physical phantoms can be used to assess the accuracy and reproducibility of the qMRI measurements (127)(128)(129)(130)(131)(132)(133)(134). Furthermore, to know which changes in qMRI values can be attributed to the effect of the treatment, assessment of the repeatability of the measurements should be performed with test-retest studies (125).…”

Robustness of magnetic resonance radiomic features to pixel size resampling and interpolation in patients with cervical cancer

“…More recently, two studies have investigated the robustness of MR radiomic features [13,14]. Baeßler et al performed the test-retest analysis as well as intraobserver and interobserver analysis using multiple MR sequences [14].…”

“…Although pixel size resampling and interpolation have been known to be a necessary preprocessing step in radiomics research, the impact of slice thickness and pixel size on radiomic features has not been well understood. Although two phantom studies have reported the robustness of MR radiomic features recently [13,14], studies on the robustness of radiomic features have focused primarily on CT and PET datasets [11,[15][16][17]. Moreover, to our knowledge, no studies have analyzed the impact of pixel size resampling and interpolation on the robustness of MR radiomic features of real patients' dataset.…”

Effect of grey-level discretization on texture feature on different weighted MRI images of diverse disease groups

“…Owing to the dependency between performance and discretization parameters, it is crucial that studies only compare directly to other studies using the same number of bins and discretization techniques. Often times this is not the case; recent studies have been based on a variety of different D values (LRR technique, D = 256, 128, 32) [42][43][44] and B values (LAR technique, B = 5, 10) [45]. Furthermore, the orders of magnitude do not depend on disease groups (IS, MS, and TU) or imaging sequences analyzed (T1 or T2 image contrast).…”