Magnetic resonance imaging radiomic features stability in brain metastases: Impact of image preprocessing, image-, and feature-level harmonization

Khodabakhshi, Zahra; Gabrys, Hubert; Wallimann, Philipp; Guckenberger, Matthias; Andratschke, Nicolaus; Tanadini-Lang, Stephanie

doi:10.1016/j.phro.2024.100585

Citations

Citation copied

Khodabakhshi, Z., Gabrys, H., Wallimann, P., Guckenberger, M., Andratschke, N., & Tanadini-Lang, S. (2024). Magnetic resonance imaging radiomic features stability in brain metastases: Impact of image preprocessing, image-, and feature-level harmonization. Physics and Imaging in Radiation Oncology, 30, 100585. https://doi.org/10.1016/j.phro.2024.100585

Abstract

BACKGROUND AND PURPOSE

Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs).

MATERIALS AND METHODS

Two T1 contrast enhanced brain MRI data-sets were used in this study. The fir