文档文献名称 与 第一作者：
Repeatability of Multiparametric Prostate MRI Radiomics Features
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 thatquantitative 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 extractionconfigurations including various image normalization schemes, different image pre-filtering, 2D vs 3D texturecomputation, and different bin widths for image discretization. Image registration as means to re-identifyregions of interest across time points was evaluated against human-expert segmented regions in both timepoints. Even though we found many radiomics features and preprocessing combinations with a highrepeatability (Intraclass Correlation Coefficient (ICC) > 0.85), our results indicate that overall the repeatability ishighly sensitive to the processing parameters (under certain configurations, it can be below 0.0). Imagenormalization, using a variety of approaches considered, did not result in consistent improvements inrepeatability. There was also no consistent improvement of repeatability through the use of pre-filteringoptions, or by using image registration between timepoints to improve consistency of the region of interestlocalization. Based on these results we urge caution when interpreting radiomics features and advise payingclose attention to the processing configuration details of reported results. Furthermore, we advocate reportingall processing details in radiomics studies and strongly recommend making the implementation available.