Ubaldi, L. and Saponaro, S. and Giuliano, A. and Talamonti, C. and Retico, A. (2023) Robustness and predictivity of MRI-based radiomic features in glioma grade discrimination. Il nuovo cimento C, 46 (4). pp. 1-4. ISSN 1826-9885
|
Text
ncc12704.pdf - Published Version Download (202kB) | Preview |
Abstract
Analysis pipelines based on Radiomics are widely used exploration tools in medical imaging. This study aims to define a robust processing pipeline based on the computation of radiomic features on multiparametric Magnetic Reso nance Imaging data to make a Machine Learning classification between two diagnostic categories. As a case study, we considered the discrimination between high-grade and low-grade gliomas. The impact of intensity normalization techniques and different settings in image discretization on classification performances was studied. A set of MRI-reliable features was defined by selecting the most appropriate normalization and discretization settings. The results in glioma grade classification showed that the use of MRI-reliable features improves discrimination performances.
| Item Type: | Article |
|---|---|
| Subjects: | 500 Scienze naturali e Matematica > 530 Fisica |
| Depositing User: | Marina Spanti |
| Date Deposited: | 08 Mar 2024 13:52 |
| Last Modified: | 08 Mar 2024 13:52 |
| URI: | http://eprints.bice.rm.cnr.it/id/eprint/22720 |
Actions (login required)
 |
View Item |
