Unsupervised Motion Tracking of Left Ventricle in Echocardiography

摘要

Accurate motion tracking of the left ventricle is critical in detecting wall motion abnormalities in the heart after aninjury such as a myocardial infarction. We propose an unsupervised motion tracking framework with physiologicalconstraints to learn dense displacement fields between sequential pairs of 2-D B-mode echocardiography images.Current deep-learning motion-tracking algorithms require large amounts of data to provide ground-truth, whichis di cult to obtain for in vivo datasets (such as patient data and animal studies), or are unsuccessful in trackingmotion between echocardiographic images due to inherent ultrasound properties (such as low signal-to-noise ratioand various image artifacts). We design a U-Net inspired convolutional neural network that uses manually tracedsegmentations as a guide to learn displacement estimations between a source and target image without ground-truth displacement fields by minimizing the difference between a transformed source frame and the original targetframe. We then penalize divergence in the displacement field in order to enforce incompressibility within the leftventricle. We demonstrate the performance of our model on synthetic and in vivo canine 2-D echocardiographydatasets by comparing it against a non-rigid registration algorithm and a shape-tracking algorithm. Our resultsshow favorable performance of our model against both methods.