Skip to main content
Fig. 2 | BMC Veterinary Research

Fig. 2

From: Deep learning-based evaluation of the severity of mitral regurgitation in canine myxomatous mitral valve disease patients using digital stethoscope recordings

Fig. 2

The architecture of the deep learning model for evaluating mitral regurgitation severity. This diagram illustrates how a deep learning model analyzes heart-sound data to categorize the intensity of heart murmurs in dogs. The model uses spectrogram data analyzed by a CNN6 model to determine murmur severity and categorizes it as mild, moderate, or severe. The layer details of the model are presented on the right. CNN, convolutional neural network; Fbank, filter bank; CE, cross-entropy; MR, mitral regurgitation; BN, batch normalization; ReLU, rectified linear unit; FC, fully connected

Back to article page

BMC Veterinary Research

ISSN: 1746-6148

Contact us