{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/repeatability-of-multiparametric-prostate-mri","title":"Repeatability of Multiparametric Prostate MRI Radiomics Features","arxiv_id":"1807.06089","date":"2018-07-16","proceeding":null,"authors":["Michael Schwier","Joost van Griethuysen","Mark G Vangel","Steve Pieper","Sharon Peled","Clare M. Tempany","Hugo JWL Aerts","Ron Kikinis","Fiona M Fennessy","Andrey Fedorov"],"abstract":"In this study we assessed the repeatability of the values of radiomics\nfeatures for small prostate tumors using test-retest Multiparametric Magnetic\nResonance Imaging (mpMRI) images. The premise of radiomics is that quantitative\nimage features can serve as biomarkers characterizing disease. For such\nbiomarkers to be useful, repeatability is a basic requirement, meaning its\nvalue must remain stable between two scans, if the conditions remain stable. We\ninvestigated repeatability of radiomics features under various preprocessing\nand extraction configurations including various image normalization schemes,\ndifferent image pre-filtering, 2D vs 3D texture computation, and different bin\nwidths for image discretization. Image registration as means to re-identify\nregions of interest across time points was evaluated against human-expert\nsegmented regions in both time points. Even though we found many radiomics\nfeatures and preprocessing combinations with a high repeatability (Intraclass\nCorrelation Coefficient (ICC) > 0.85), our results indicate that overall the\nrepeatability is highly sensitive to the processing parameters (under certain\nconfigurations, it can be below 0.0). Image normalization, using a variety of\napproaches considered, did not result in consistent improvements in\nrepeatability. There was also no consistent improvement of repeatability\nthrough the use of pre-filtering options, or by using image registration\nbetween timepoints to improve consistency of the region of interest\nlocalization. Based on these results we urge caution when interpreting\nradiomics features and advise paying close attention to the processing\nconfiguration details of reported results. Furthermore, we advocate reporting\nall processing details in radiomics studies and strongly recommend making the\nimplementation available.","url_abs":"http://arxiv.org/abs/1807.06089v2","url_pdf":"http://arxiv.org/pdf/1807.06089v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"repeatability-of-multiparametric-prostate-mri","repo_url":"https://github.com/michaelschwier/QIN-PROSTATE-Repeatability-Radiomics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"repeatability-of-multiparametric-prostate-mri","repo_url":"https://github.com/QIICR/QIN-PROSTATE-Repeatability-Radiomics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-registration","task_name":"Image Registration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}