Learning to Estimate Motion Between Non-adjacent Frames in Cardiac Cine MRI Data: A Fusion Approach

Nicolas Portal, Thomas Dietenbeck, Saud Khan, Vincent Nguyen, Mikaël Prigent, Mohamed Zarai, Khaoula Bouazizi-Verdier, Johanne Sylvain, Alban Redheuil, Gilles Montalescot, Nadjia Kachenoura, Catherine Achard

Abstract: Information about the motion of pixels between images is crucial for many computer vision tasks. When dealing with cardiac sequences, information about the heart’s motion can help physicians diagnose pathologies. Most methods that try to estimate this motion rely on pair of frames. This can lead to suboptimal performance when the amount of motion between them is important as it is the case when considering distant frames in a video sequence. Moreover, performing registration image by image leads to the integration of registration errors and is also suboptimal. In this work, a new registration method that uses all the frames in a video sequence is presented and applied to cardiac cine-MRI in short-axis views. A first neural network is used to compute motion flows between adjacent frames. Then, a second one processes the output of the first network to merge motion flows according to the time dimension throughout the sequence. Estimated flows are used to propagate segmentation masks across the sequence. The method is tested on an in-house dataset containing 271 patients. Segmentation, similarity and motion flow regularization metrics are computed to assess the model performance. The proposed approach achieves an average registration Dice score and SSIM between the end-diastole and end-systole frame of \(95.26 \pm 0.01\) and \(86 \pm 0.05\) respectively against \(93.24 \pm 0.02\) and \(82.75 \pm 0.06\) for the best Voxelmorph version.