Flow Network Tracking for Spatiotemporal and Periodic Point Matching: Applied to Cardiac Motion Analysis.

•We present a spatio-temporal (3D+t) correspondence solving algorithm and apply it to estimate cardiac deformation using echocardiographic images.•We use convolutional neural networks to encode feature information and facilitate the correspondence algorithm.•We validate our method using 8 synthetic 4D echocardiographic sequences and compare our method against other methods applied to similar problems.•We also validate our method using 8 open-chested canine echocardiographic 4D sequences with sonomicrometric crystal implantation that provided reference strain values.