Registration by tracking for sequential 2D MRI
This work addresses motion tracking in medical imaging for radiation therapy, but it is incremental as it builds on existing tracking and interpolation techniques.
The paper tackles the problem of estimating displacement fields for sequential 2D MRI images during radiation therapy by using discriminative correlation filters for point tracking and a neural network for sparse-to-dense interpolation, resulting in improved performance over conventional methods, especially for larger motions of small objects.
Our anatomy is in constant motion. With modern MR imaging it is possible to record this motion in real-time during an ongoing radiation therapy session. In this paper we present an image registration method that exploits the sequential nature of 2D MR images to estimate the corresponding displacement field. The method employs several discriminative correlation filters that independently track specific points. Together with a sparse-to-dense interpolation scheme we can then estimate of the displacement field. The discriminative correlation filters are trained online, and our method is modality agnostic. For the interpolation scheme we use a neural network with normalized convolutions that is trained using synthetic diffeomorphic displacement fields. The method is evaluated on a segmented cardiac dataset and when compared to two conventional methods we observe an improved performance. This improvement is especially pronounced when it comes to the detection of larger motions of small objects.