Automated Recognition of Ultrasound Cardiac Views Based on Deep Learning with Graph Constraint

Abstract

In transthoracic echocardiographic (TTE) examination, it is essential to identify the cardiac views accurately. Computer-aided recognition is expected to improve the accuracy of cardiac views of the TTE examination, particularly when obtained by non-trained providers. A new method for automatic recognition of cardiac views is proposed consisting of three processes. First, a spatial transform network is performed to learn cardiac shape changes during a cardiac cycle, which reduces intra-class variability. Second, a channel attention mechanism is introduced to adaptively recalibrate channel-wise feature responses. Finally, the structured signals by the similarities among cardiac views are transformed into the graph-based image embedding, which acts as unsupervised regularization constraints to improve the generalization accuracy. The proposed method is trained and tested in 171792 cardiac images from 584 subjects. The overall accuracy of the proposed method on cardiac image classification is 99.10%, and the mean AUC is 99.36%, better than known methods. Moreover, the overall accuracy is 97.73%, and the mean AUC is 98.59% on an independent test set with 37,883 images from 100 subjects. The proposed automated recognition model achieved comparable accuracy with true cardiac views, and thus can be applied clinically to help find standard cardiac views.

Artificial intelligence-based classification of echocardiographic views

“…For example, Gao et al . 14 used two 2D CNN networks, one of which was concentrated along spatial dimensions, and the other along the temporal dimension. Each network was executed separately, but input from both the spatial and temporal networks was combined to obtain final classification scores for eight views of interest.…”

“…Zhang et al . 14 trained a Visual Geometry Group (VGG) network to predict 23 view classes. The final output score was averaged for 10 randomly selected frames from each video.…”

Automatic alignment of standard views for transesophageal echocardiographic images

“…There have been several papers on automatic placement of the standard view in both TTE and TEE images. For 2D images, automatic determination of standard views images has been done by Gao et al 7 and østvik et al, 8 and for 3D images, automatic placement of the standard view has been studied by Orderud et al 9 and Lu et al 10 on TTE images and by Curiale et al 11 on TEE images. The latter work used Hough-transforms to find circular structures and compared that to known estimates of the size and thickness of the mitral and aortic valves.…”

“…There have been several papers on automatic placement of the standard view in both TTE and TEE images. For 2D images, automatic determination of standard views images has been done by Gao et al 7 . and østvik et al., 8 and for 3D images, automatic placement of the standard view has been studied by Orderud et al 9 .…”