Key result
Cine CMR-based neural network detects myocardial fibrosis with ~89% validation accuracy.
Why the study?
Artificial intelligence techniques can detect imperceptible patterns in cardiology, offering potential to identify myocardial texture patterns to characterize and quantify fibrosis on cine cardiac magnetic resonance imaging.
Does a convolutional neural network accurately identify fibrosis in cine cardiac magnetic resonance images in clinical subjects?
Observational (n=75)
No
Does a convolutional neural network accurately identify fibrosis in cine cardiac magnetic resonance images in clinical subjects?
A convolutional neural network can identify myocardial fibrosis directly from cine CMR images with 70% test accuracy, demonstrating potential for assessing myocardial viability without contrast.
May support non-contrast fibrosis detection on cine CMR; leaves open prospective validation before clinical adoption.
Background: Artificial intelligence techniques have demonstrated great potential in cardiology, especially to detect imperceptible patterns for the human eye. In this sense, these techniques seem to be adequate to identify patterns in the myocardial texture which could lead to characterize and quantify fibrosis. Purpose: The aim of this study was to postulate a new artificial intelligence method to identify fibrosis in cine cardiac magnetic resonance (CMR) imaging. Methods: A retrospective observational study was carried out in a population of 75 subjects from a clinical center of San Carlos de Bariloche. The proposed method analyzes the myocardial texture in cine CMR images using a convolutional neural network to determine local myocardial tissue damage. Results: An accuracy of 89% for quantifying local tissue damage was observed for the validation data set and 70% for the test set. In addition, the qualitative analysis showed a high spatial correlation in lesion location. Conclusions: The postulated method enables to spatially identify fibrosis using only the information from cine nuclear magnetic resonance studies, demonstrating the potential of this technique to quantify myocardial viability in the future or to study the lesions etiology
No takes yet. Share an insight, caveat, or question.
Curiale et al. (2022) conducted an observational in Myocardial fibrosis (n=75). Convolutional neural network for cine CMR texture analysis vs. Late gadolinium enhancement (LGE) sequences was evaluated on Accuracy for quantifying local tissue damage. A convolutional neural network identified local myocardial fibrosis using myocardial texture in cine cardiac magnetic resonance images with an accuracy of 89% in the validation set and 70% in the test set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: