CarpNet, a deep transformer network, achieved 71% accuracy in classifying mitral valve pathology from echocardiographic videos, outperforming single-frame CNN models.
Does CarpNet improve the accuracy of Carpentier functional classification of mitral valve disease in echocardiographic videos compared to single-frame CNN models?
A deep transformer network (CarpNet) analyzing consecutive echocardiographic frames improves the automated Carpentier functional classification of mitral valve disease compared to single-frame CNN models.
Abstract Mitral valve (MV) diseases constitute one of the etiologies of cardiovascular mortality and morbidity. MV pathologies need evaluating and classifying via echocardiographic videos. Transformers have significantly advanced video analytics. MV motion is divided by Carpentier functional classification into four types: normal, increased, restricted, and restricted only during systole. This paper introduces CarpNet, a deep transformer network that incorporates video transformers capable of direct MV pathology Carpentier's classification from the parasternal long‐axis (PLA) echocardiographic videos. The network, instead of processing frames independently, analyzes stacks of temporally consecutive frames using multi‐head attention modules to incorporate MV temporal dynamics into the learned model. To that end, different convolutional neural networks (CNNs) are evaluated as the backbone, and the best model is selected using the information of the PLA view. The use of information obtained by our proposed deep transformer network from consecutive echocardiographic frames yielded better results concerning the Carpentier functional classification than information obtained by CNN‐based (single‐frame) models. Using the InceptionResnetV2 architecture as the backbone, CarpNet achieved 71% accuracy in the test dataset. Deep learning and transformers in echocardiographic videos can render quick, precise, and stable evaluations of various MV pathologies.
Vafaeezadeh et al. (Wed,) conducted a other in Mitral valve disease. CarpNet (deep transformer network) vs. CNN-based (single-frame) models was evaluated on Carpentier functional classification accuracy. CarpNet, a deep transformer network, achieved 71% accuracy in classifying mitral valve pathology from echocardiographic videos, outperforming single-frame CNN models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: