Key result
Deep learning matches manual LV function analysis with ~0.90 correlation in HCM but struggles in DCM.
Why the study?
To evaluate the performance of a deep learning-based method to automatically quantify left ventricular function from MR images across different cardiomyopathies.
Does a deep learning-based method accurately quantify left ventricular function from MR images compared to manual measurement in patients with HCM, DCM, and healthy participants?
Observational (n=388)
No
Does a deep learning-based method accurately quantify left ventricular function from MR images compared to manual measurement in patients with HCM, DCM, and healthy participants?
A commercially available deep learning-based method for LV function evaluation performs differently across cardiomyopathies, with better performance in HCM than DCM.
Variable accuracy by cardiomyopathy type warrants caution in DCM; leaves open prospective validation before clinical adoption.
OBJECTIVES: To evaluate the performance of a deep learning-based method to automatically quantify left ventricular (LV) function from MR images in different cardiomyopathy. METHODS: This retrospective study included MRI data sets from 2013 to 2020. Data on left ventricular function from patients with hypertrophic cardiomyopathy (HCM), patients with dilated cardiomyopathy (DCM), and healthy participants were analyzed. MRI data from a total of 388 patients were measured manually and automatically.The performance of Convolutional Neural Networks (CNNs) was evaluated based on the manual notes of two experienced observers: (a) LV segmentation accuracy, and (b) LV functional parameter accuracy. Bland-Altman analysis, Receiver operating Characteristic (ROC) curve analysis and Pearson correlation analysis were used to evaluate the consistency between fully automatic and manual diagnosis of HCM and DCM. RESULTS: = 0.645). ROC curve analysis indicated that at the optimal cut-off value, EF from automatic segmentation identified DCM and HCM patients with sensitivity of 92.31 and 78.05%, specificity of 82.96 and 54.07%, respectively. CONCLUSION: Among different heart diseases, the analysis of cardiac function based on deep-learning CNN may have different performances, with DCM performing the worst and HCM the best and thus, special attention should be paid to DCM patients when assessing LV function through artificial intelligence method. LV function parameter obtained by artificial intelligence method may play an important role in the future AI diagnosis of HCM and DCM. ADVANCES IN KNOWLEDGE: These data for the first time objectively evaluate the performance of a commercially available deep learning-based method in cardiac function evaluation of different cardiomyopathy and point out its advantages and disadvantages in different cardiomyopathy. This work did not attempt to design the algorithm itself, but rather applied an already existing method to a test dataset of clinical data and evaluated the results for a limited number of cardiomyopathy.
No takes yet. Share an insight, caveat, or question.
Guo et al. (2022) conducted an observational in Hypertrophic cardiomyopathy and dilated cardiomyopathy (n=388). Deep learning-based CNN artificial intelligence method (cvi42 v5.0) vs. Manual segmentation was evaluated on Correlation of LV functional parameters (EDV, ESV, EF, SV) between automatic and manual segmentation. A deep learning-based convolutional neural network automatically quantified left ventricular function with high correlation to manual analysis in hypertrophic cardiomyopathy (r >0.901) but performed worse in dilated cardiomyopathy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: