Repeatability of Multiparametric Prostate MRI Radiomics Features

TL;DR

This study evaluates the repeatability of radiomics features in prostate MRI, revealing high sensitivity to processing parameters and emphasizing the need for detailed reporting and cautious interpretation in radiomics research.

Contribution

It systematically assesses how various preprocessing and extraction configurations affect the repeatability of radiomics features in prostate MRI.

Findings

Many features show high repeatability (ICC > 0.85) under certain conditions.

Repeatability is highly sensitive to processing parameters, with some configurations yielding ICC below 0.0.

Normalization and registration do not consistently improve feature repeatability.

Abstract

In this study we assessed the repeatability of the values of radiomics features for small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI) images. The premise of radiomics is that quantitative image features can serve as biomarkers characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics features under various preprocessing and extraction configurations including various image normalization schemes, different image pre-filtering, 2D vs 3D texture computation, and different bin widths for image discretization. Image registration as means to re-identify regions of interest across time points was evaluated against human-expert segmented regions in both time points. Even though we found many radiomics features and preprocessing combinations with a high repeatability (Intraclass Correlation Coefficient (ICC) > 0.85), our results indicate that overall the repeatability is highly sensitive to the processing parameters (under certain configurations, it can be below 0.0). Image normalization, using a variety of approaches considered, did not result in consistent improvements in repeatability. There was also no consistent improvement of repeatability through the use of pre-filtering options, or by using image registration between timepoints to improve consistency of the region of interest localization. Based on these results we urge caution when interpreting radiomics features and advise paying close attention to the processing configuration details of reported results. Furthermore, we advocate reporting all processing details in radiomics studies and strongly recommend making the implementation available.