| Title: |
Exploring the Utility of Cardiovascular Magnetic Resonance Radiomic Feature Extraction for Evaluation of Cardiac Sarcoidosis |
| Authors: |
Mushari, Nouf A.; Soultanidis, Georgios; Duff, Lisa; Trivieri, Maria G.; Fayad, Zahi A.; Robson, Philip M.; Tsoumpas, Charalampos |
| Source: |
Mushari, N A, Soultanidis, G, Duff, L, Trivieri, M G, Fayad, Z A, Robson, P M & Tsoumpas, C 2023, 'Exploring the Utility of Cardiovascular Magnetic Resonance Radiomic Feature Extraction for Evaluation of Cardiac Sarcoidosis', Diagnostics, vol. 13, no. 11, 1865. https://doi.org/10.3390/diagnostics13111865 |
| Publication Year: |
2023 |
| Collection: |
University of Groningen research database |
| Subject Terms: |
feature selection; imaging; machine learning; PET-MRI; texture analysis |
| Description: |
Background: The aim of this study is to explore the utility of cardiac magnetic resonance (CMR) imaging of radiomic features to distinguish active and inactive cardiac sarcoidosis (CS). Methods: Subjects were classified into active cardiac sarcoidosis (CS active ) and inactive cardiac sarcoidosis (CS inactive ) based on PET-CMR imaging. CS active was classified as featuring patchy [ 18 F]fluorodeoxyglucose ([ 18 F]FDG) uptake on PET and presence of late gadolinium enhancement (LGE) on CMR, while CS inactive was classified as featuring no [ 18 F]FDG uptake in the presence of LGE on CMR. Among those screened, thirty CS active and thirty-one CS inactive patients met these criteria. A total of 94 radiomic features were subsequently extracted using PyRadiomics. The values of individual features were compared between CS active and CS inactive using the Mann–Whitney U test. Subsequently, machine learning (ML) approaches were tested. ML was applied to two sub-sets of radiomic features (signatures A and B) that were selected by logistic regression and PCA, respectively. Results: Univariate analysis of individual features showed no significant differences. Of all features, gray level co-occurrence matrix (GLCM) joint entropy had a good area under the curve (AUC) and accuracy with the smallest confidence interval, suggesting it may be a good target for further investigation. Some ML classifiers achieved reasonable discrimination between CS active and CS inactive patients. With signature A, support vector machine and k-neighbors showed good performance with AUC (0.77 and 0.73) and accuracy (0.67 and 0.72), respectively. With signature B, decision tree demonstrated AUC and accuracy around 0.7; Conclusion: CMR radiomic analysis in CS provides promising results to distinguish patients with active and inactive disease. |
| Document Type: |
article in journal/newspaper |
| File Description: |
application/pdf |
| Language: |
English |
| ISSN: |
2075-4418 |
| Relation: |
info:eu-repo/semantics/altIdentifier/hdl/https://hdl.handle.net/11370/166a35e7-46d5-4805-b5aa-52a21d70e1e1; info:eu-repo/semantics/altIdentifier/pissn/2075-4418 |
| DOI: |
10.3390/diagnostics13111865 |
| Availability: |
https://hdl.handle.net/11370/166a35e7-46d5-4805-b5aa-52a21d70e1e1; https://research.rug.nl/en/publications/166a35e7-46d5-4805-b5aa-52a21d70e1e1; https://doi.org/10.3390/diagnostics13111865; https://pure.rug.nl/ws/files/845532727/Exploring_the_Utility_of_Cardiovascular_Magnetic_Resonance_Radiomic_Feature_Extraction_for_Evaluation_of_Cardiac_Sarcoidosis.pdf; https://www.scopus.com/pages/publications/85161736120 |
| Rights: |
info:eu-repo/semantics/openAccess ; http://creativecommons.org/licenses/by/4.0/ |
| Accession Number: |
edsbas.42EC0572 |
| Database: |
BASE |