Abstract
Radiomic analysis has exponentially increased the amount of quantitative data that can be extracted from a single image. These imaging biomarkers can aid in the generation of prediction models aimed to further personalized medicine. However, the generalizability of the model is dependent on the robustness of these features. The purpose of this study is to review the current literature regarding robustness of radiomic features on magnetic resonance imaging. Additionally, a phantom study is performed to systematically evaluate the behavior of radiomic features under various conditions (signal to noise ratio, region of interest delineation, voxel size change and normalization methods) using intraclass correlation coefficients. The features extracted in this phantom study include first order, shape, gray level cooccurrence matrix and gray level run length matrix. Many features are found to be non-robust to changing parameters. Feature robustness assessment prior to feature selection, especially in the case of combining multi-institutional data, may be warranted. Further investigation is needed in this area of research.
Highlights
Overview of radiomics Radiomics is the extraction of high-dimensional and quantitative mineable data from digital medical images [1,2,3]
Radiomic analysis aims to maximize the amount of quantitative information that can be extracted from the existing medical images that may not be appreciable to the naked eye
Examples of semantic features include size, shape, location, vascularity, and spiculation [1, 2]. These are descriptors that are commonly used by radiologists in a qualitative fashion to identify and characterize disease, such as in the case of breast tumors where the size of tumor is indicative of treatment response (Response evaluation criteria in solid tumors criteria) and spiculation being a higher chance of malignancy (Breast Imaging Reporting and Data System) [1, 4,5,6]
Summary
Overview of radiomics Radiomics is the extraction of high-dimensional and quantitative mineable data from digital medical images [1,2,3]. In clinical practice, imaging data is only qualitatively or semi-quantitively utilized and a dictated report is created by the radiologist. Examples of semantic features include size, shape, location, vascularity, and spiculation [1, 2] These are descriptors that are commonly used by radiologists in a qualitative fashion to identify and characterize disease, such as in the case of breast tumors where the size of tumor is indicative of treatment response (Response evaluation criteria in solid tumors criteria) and spiculation being a higher chance of malignancy (Breast Imaging Reporting and Data System) [1, 4,5,6]. Quantitative extraction of semantic features is desired to give a more comprehensive and reproducible description of the region of interest (ROI), whereas visual inspection by radiologist has large intra- and inter-reader variability [5]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Visual Computing for Industry, Biomedicine, and Art
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.