A Novel Data Augmentation Method for Radiomics Analysis Using Image Perturbations
Journal of Imaging Informatics in Medicine · 06.05.2024 · 37 (5) · 2401-2414
DOI: 10.1007/s10278-024-01013-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 06.05.2024. Verfasst von F Lo Iacono und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milan, Italy. francesca.loiacono@polimi.it. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Politecnico di Milano.
Abstract (Originalsprache)
Radiomics extracts hundreds of features from medical images to quantitively characterize a region of interest (ROI). When applying radiomics, imbalanced or small dataset issues are commonly addressed using under or over-sampling, the latter being applied directly to the extracted features. Aim of this study is to propose a novel balancing and data augmentation technique by applying perturbations (erosion, dilation, contour randomization) to the ROI in cardiac computed tomography images. From the perturbed ROIs, radiomic features are extracted, thus creating additional samples. This approach was tested addressing the clinical problem of distinguishing cardiac amyloidosis (CA) from aortic stenosis (AS) and hypertrophic cardiomyopathy (HCM). Twenty-one CA, thirty-two AS and twenty-one HCM patients were included in the study. From each original and perturbed ROI, 107 radiomic features were extracted. The CA-AS dataset was balanced using the perturbation-based method along with random over-sampling, adaptive synthetic (ADASYN) and the synthetic minority oversampling technique (SMOTE). The same methods were tested to perform data augmentation dealing with CA and HCM. Features were submitted to robustness, redundancy, and relevance analysis testing five feature selection methods ( p -value, least absolute shrinkage and selection operator (LASSO), semi-supervised LASSO, principal component analysis (PCA), semi-supervised PCA). Support vector machine performed the classification tasks, and its performance were evaluated by means of a 10-fold cross-validation. The perturbation-based approach provided the best performances in terms of f1 score and balanced accuracy in both CA-AS (f1 score: 80%, AUC: 0.91) and CA-HCM (f1 score: 86%, AUC: 0.92) classifications. These results suggest that ROI perturbations represent a powerful approach to address both data balancing and augmentation issues.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milan, Italy. francesca.loiacono@polimi.it.
- Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy.
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy.
- Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milan, Italy.
ORCID-Profile: F Lo Iacono, R Maragna, G Pontone, V D A Corino
Förderung
- Politecnico di Milano
Zitieren
APA
Lo Iacono, F., Maragna, R., Pontone, G., & Corino, V. D. A. (2024). A Novel Data Augmentation Method for Radiomics Analysis Using Image Perturbations. Journal of Imaging Informatics in Medicine, 37(5), 2401-2414. https://doi.org/10.1007/s10278-024-01013-0
Vancouver
Lo Iacono F, Maragna R, Pontone G, Corino VDA. A Novel Data Augmentation Method for Radiomics Analysis Using Image Perturbations. Journal of Imaging Informatics in Medicine. 2024;37(5):2401-2414. doi:10.1007/s10278-024-01013-0
BibTeX
@article{LoIacono2024,
author = {Lo Iacono, F and Maragna, R and Pontone, G and Corino, V D A},
title = {A Novel Data Augmentation Method for Radiomics Analysis Using Image Perturbations},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {37},
number = {5},
pages = {2401--2414},
doi = {10.1007/s10278-024-01013-0}
}
EUVIMED