Header

UZH-Logo

Maintenance Infos

Radiomics for Distinguishing Myocardial Infarction from Myocarditis at Late Gadolinium Enhancement at MRI: Comparison with Subjective Visual Analysis


Di Noto, Tommaso; von Spiczak, Jochen; Mannil, Manoj; Gantert, Elena; Soda, Paolo; Manka, Robert; Alkadhi, Hatem (2019). Radiomics for Distinguishing Myocardial Infarction from Myocarditis at Late Gadolinium Enhancement at MRI: Comparison with Subjective Visual Analysis. Radiology: Cardiothoracic Imaging, 1(5):2019180026.

Abstract

Radiomics features, identified through machine learning, help distinguish myocardial infarction from myocarditis on the basis of late gadolinium enhancement in MRI with high accuracy.
Purpose
To evaluate whether radiomics features of late gadolinium enhancement (LGE) regions at cardiac MRI enable distinction between myocardial infarction (MI) and myocarditis and to compare radiomics with subjective visual analyses by readers with different experience levels.
Materials and Methods
In this retrospective, institutional review board–approved study, consecutive MRI examinations of 111 patients with MI and 62 patients with myocarditis showing LGE were included. By using open-source software, classification performances attained from two-dimensional (2D) and three-dimensional (3D) texture analysis, shape, and first-order descriptors were compared, applying five different machine learning algorithms. A nested, stratified 10-fold cross-validation was performed. Classification performances were compared through Wilcoxon signed-rank tests. Supervised and unsupervised feature selection techniques were tested; the effect of resampling MR images was analyzed. Subjective image analysis was performed on 2D and 3D image sets by two independent, blinded readers with different experience levels.
Results
When trained with recursive feature elimination (RFE), a support vector machine achieved the best results (accuracy: 88%) for 2D features, whereas linear discriminant analysis (LDA) showed the highest accuracy (85%) for 3D features (P <.05). When trained with principal component analysis (PCA), LDA attained the highest accuracy with both 2D (86%) and 3D (89%; P =.4) features. Results found for classifiers trained with spline resampling were less accurate than those achieved with one-dimensional (1D) nearest-neighbor interpolation (P <.05), whereas results for classifiers trained with 1D nearest-neighbor interpolation and without resampling were similar (P =.1). As compared with the radiomics approach, subjective visual analysis performance was lower for the less experienced and higher for the experienced reader for both 2D and 3D data.
Conclusion
Radiomics features of LGE permit the distinction between MI and myocarditis with high accuracy by using either 2D features and RFE or 3D features and PCA.

Abstract

Radiomics features, identified through machine learning, help distinguish myocardial infarction from myocarditis on the basis of late gadolinium enhancement in MRI with high accuracy.
Purpose
To evaluate whether radiomics features of late gadolinium enhancement (LGE) regions at cardiac MRI enable distinction between myocardial infarction (MI) and myocarditis and to compare radiomics with subjective visual analyses by readers with different experience levels.
Materials and Methods
In this retrospective, institutional review board–approved study, consecutive MRI examinations of 111 patients with MI and 62 patients with myocarditis showing LGE were included. By using open-source software, classification performances attained from two-dimensional (2D) and three-dimensional (3D) texture analysis, shape, and first-order descriptors were compared, applying five different machine learning algorithms. A nested, stratified 10-fold cross-validation was performed. Classification performances were compared through Wilcoxon signed-rank tests. Supervised and unsupervised feature selection techniques were tested; the effect of resampling MR images was analyzed. Subjective image analysis was performed on 2D and 3D image sets by two independent, blinded readers with different experience levels.
Results
When trained with recursive feature elimination (RFE), a support vector machine achieved the best results (accuracy: 88%) for 2D features, whereas linear discriminant analysis (LDA) showed the highest accuracy (85%) for 3D features (P <.05). When trained with principal component analysis (PCA), LDA attained the highest accuracy with both 2D (86%) and 3D (89%; P =.4) features. Results found for classifiers trained with spline resampling were less accurate than those achieved with one-dimensional (1D) nearest-neighbor interpolation (P <.05), whereas results for classifiers trained with 1D nearest-neighbor interpolation and without resampling were similar (P =.1). As compared with the radiomics approach, subjective visual analysis performance was lower for the less experienced and higher for the experienced reader for both 2D and 3D data.
Conclusion
Radiomics features of LGE permit the distinction between MI and myocarditis with high accuracy by using either 2D features and RFE or 3D features and PCA.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Cardiology
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:19 December 2019
Deposited On:17 Feb 2020 16:32
Last Modified:29 Jul 2020 14:31
Publisher:Radiological Society of North America
ISSN:2638-6135
OA Status:Closed
Publisher DOI:https://doi.org/10.1148/ryct.2019180026

Download

Full text not available from this repository.
View at publisher

Get full-text in a library