Dynamic MR Imaging Using Manifold Alignment
Estimating respiratory motion inside the lungs is useful for a range of clinical applications. However, estimating lung motion using MR has known problems: dynamic 3D images have poor contrast and resolution, so motion estimates tend to be interpolated from the high contrast areas at the lung boundary. However, dynamic 2D MR imaging has good resolution and excellent vessel contrast, due to the in-flow effect of unpolarised blood (see movies below)
This work aimed to combine the contrast/resolution advantages of 2D MR with the coverage of 3D MR. The technique used dynamic 2D coronal images acquired at shifting slice positions. A novel simultaneous groupwise manifold alignment scheme was then used to find motion state correspondences between the slices from different positions. This enabled them to be stacked into high resolution, high contrast 3D volumes (see movie below).
- C. F. Baumgartner, C. Kolbitsch, D. R. Balfour, P. K. Marsden, J. R. McClelland, D. Rueckert, A. P. King, "High-Resolution Dynamic MR Imaging Of The Thorax For Respiratory Motion Correction Of PET Using Groupwise Manifold Alignment", Medical Image Analysis 18(7):939-952, 2014. (paper)
- C. F. Baumgartner, J. R. McClelland, D. Rueckert, A. P. King, "Groupwise Simultaneous Manifold Alignment for High Resolution Dynamic MR Imaging of Respiratory Motion", Proceedings IPMI, pp232-243, 2013. (paper) - AWARDED BEST POSTER PRIZE
This work was subsequently extended, resulting in a manifold alignment scheme that did not require any inter-dataset comparisons between the high-dimensional data. Normally, such comparisons are an essential part of manifold alignment schemes, but in medical imaging it is often not feasible. For example, MR slices acquired at different positions image different parts of the anatomy, so direct comparison of the images is not meaningful. We developed a scheme based on graph theory that enabled signature vectors to be assigned to each node (i.e. 2D image). These signatures were characteristic of the local graph structure of the node, and were used in place of the imaging data as the high-dimensional data in the inter-dataset comparison. The resulting technique, which we term self-aligning manifolds, was one of very few manifold alignment techniques to work in this way, and it enabled the application of manifold alignment for the first time in applications featuring highly dissimilar medical image datasets.
- C. F. Baumgartner, A. Gomez, L. M. Koch, J. R. Housden, C. Kolbitsch, J. R. McClelland, D. Rueckert, and A. P. King, "Self-Aligning Manifolds for Matching Disparate Medical Image Datasets", Proceedings IPMI, 2015. (paper) - AWARDED BEST POSTER PRIZE
- D. R. Balfour, J. . Clough, X Chen, M. Belzunce, C. Prieto, P. K. Marsden, A. J. Reader, A. P. King, "PET-MR Respiratory Signal Estimation Using Semi-Supervised Manifold Alignment", Proceedings ISBI, pp599-603, 2018. (paper)
The work described above performed manifold alignment of reconstructed 2D imaging data. This places a fundamental limit on the achievable temporal resolution to the amount of time it takes to acquire enough k-space data to reconstruct each image. In subsequent work we extended the concept to perform manifold alignment of the 3D k-space data themselves, which enables much higher temporal resolution. This work built on the self-aligning manifolds work, and resulted in a scheme capable of retrospectively reconstructing dynamic images with high spatial and temporal resolution.
- X. Chen, M. Usman, C. F. Baumgartner, D. R. Balfour, P. K. Marsden, A. J. Reader, C. Prieto, A. P. King, "High-Resolution Self-Gated Dynamic Abdominal MRI Using Manifold Alignment", IEEE Transactions on Medical Imaging 36:960-971, 2017. (open access paper)
- X. Chen, M. Usman, D. Balfour, P. Marsden, A. Reader, C. Prieto and A. P. King, "Dynamic Volume Reconstruction From Multi-Slice Abdominal MRI Using Manifold Alignment", Proceedings MICCAI, pp493-501, 2016. (paper)
- X. Chen, M. Usman, C. Baumgartner, C. Prieto and A. P. King, "Motion-free Abdominal MRI using Manifold Alignment", Proceedings ISMRM, 2015.
The graph-based signatures employed by the self-aligning manifolds work have since been developed, resulting in a new technique based on wave kernel signatures which also permits the contributions of the different datasets to the aligned manifold to be individually weighted. This has been demonstrated to produce superior performance on the problem of 4D MR slice stacking and was also demonstrated on semi-supervised alignment of simultaneously acquired PET and MR data.
- J. R. Clough, D. R. Balfour, P. K. Marsden, C. Prieto, A. J. Reader, A. P. King, "MRI Slice Stacking Using Manifold Alignment and Wave Kernel Signatures", Proceedings ISBI, pp319-323, 2018. (paper)
- J. Clough, D. R. Balfour, G. Lima Da Cruz, P. Marsden, C. Prieto, A. Reader, A. P. King, "Weighted Manifold Alignment using Wave Kernel Signatures for Aligning Medical image Datasets", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019. (paper)