skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 5:00 PM ET until 11:00 PM ET on Friday, June 21 due to maintenance. We apologize for the inconvenience.

Title: Symplectomorphic registration with phase space regularization by entropy spectrum pathways

The ability to register image data to a common coordinate system is a critical feature of virtually all imaging studies. However, in spite of the abundance of literature on the subject and the existence of several variants of registration algorithms, their practical utility remains problematic, as commonly acknowledged even by developers of these methods.


A new registration method is presented that utilizes a Hamiltonian formalism and constructs registration as a sequence of symplectomorphic maps in conjunction with a novel phase space regularization. For validation of the framework a panel of deformations expressed in analytical form is developed that includes deformations based on known physical processes in MRI and reproduces various distortions and artifacts typically present in images collected using these different MRI modalities.


The method is demonstrated on the three different magnetic resonance imaging (MRI) modalities by mapping between high resolution anatomical (HRA) volumes, medium resolution diffusion weighted MRI (DW‐MRI) and HRA volumes, and low resolution functional MRI (fMRI) and HRA volumes.


The method has shown an excellent performance and the panel of deformations was instrumental to quantify its repeatability and reproducibility in comparison to several available alternative approaches.

more » « less
Author(s) / Creator(s):
Publisher / Repository:
Wiley Blackwell (John Wiley & Sons)
Date Published:
Journal Name:
Magnetic Resonance in Medicine
Page Range / eLocation ID:
p. 1335-1352
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Purpose

    To demonstrate a tagging method compatible with RT‐MRI for the study of speech production.


    Tagging is applied as a brief interruption to a continuous real‐time spiral acquisition. Tagging can be initiated manually by the operator, cued to the speech stimulus, or be automatically applied with a fixed frequency. We use a standard 2D 1‐3‐3‐1 binomial SPAtial Modulation of Magnetization (SPAMM) sequence with 1 cm spacing in both in‐plane directions. Tag persistence in tongue muscle is simulated and validated in vivo. The ability to capture internal tongue deformations is tested during speech production of American English diphthongs in native speakers.


    We achieved an imaging window of 650‐800 ms at 1.5T, with imaging signal to noise ratio ≥ 17 and tag contrast to noise ratio ≥ 5 in human tongue, providing 36 frames/s temporal resolution and 2 mm in‐plane spatial resolution with real‐time interactive acquisition and view‐sharing reconstruction. The proposed method was able to capture tongue motion patterns and their relative timing with adequate spatiotemporal resolution during the production of American English diphthongs and consonants.


    Intermittent tagging during real‐time MRI of speech production is able to reveal the internal deformations of the tongue. This capability will allow new investigations of valuable spatiotemporal information on the biomechanics of the lingual subsystems during speech without reliance on binning speech utterance repetition.

    more » « less
  2. Abstract Background

    In Alzheimer’s Diseases (AD) research, multimodal imaging analysis can unveil complementary information from multiple imaging modalities and further our understanding of the disease. One application is to discover disease subtypes using unsupervised clustering. However, existing clustering methods are often applied to input features directly, and could suffer from the curse of dimensionality with high-dimensional multimodal data. The purpose of our study is to identify multimodal imaging-driven subtypes in Mild Cognitive Impairment (MCI) participants using a multiview learning framework based on Deep Generalized Canonical Correlation Analysis (DGCCA), to learn shared latent representation with low dimensions from 3 neuroimaging modalities.


    DGCCA applies non-linear transformation to input views using neural networks and is able to learn correlated embeddings with low dimensions that capture more variance than its linear counterpart, generalized CCA (GCCA). We designed experiments to compare DGCCA embeddings with single modality features and GCCA embeddings by generating 2 subtypes from each feature set using unsupervised clustering. In our validation studies, we found that amyloid PET imaging has the most discriminative features compared with structural MRI and FDG PET which DGCCA learns from but not GCCA. DGCCA subtypes show differential measures in 5 cognitive assessments, 6 brain volume measures, and conversion to AD patterns. In addition, DGCCA MCI subtypes confirmed AD genetic markers with strong signals that existing late MCI group did not identify.


    Overall, DGCCA is able to learn effective low dimensional embeddings from multimodal data by learning non-linear projections. MCI subtypes generated from DGCCA embeddings are different from existing early and late MCI groups and show most similarity with those identified by amyloid PET features. In our validation studies, DGCCA subtypes show distinct patterns in cognitive measures, brain volumes, and are able to identify AD genetic markers. These findings indicate the promise of the imaging-driven subtypes and their power in revealing disease structures beyond early and late stage MCI.

    more » « less
  3. Cardiac Cine Magnetic Resonance (CMR) Imaging has made a significant paradigm shift in medical imaging technology, thanks to its capability of acquiring high spatial and temporal resolution images of different structures within the heart that can be used for reconstructing patient-specific ventricular computational models. In this work, we describe the development of dynamic patient-specific right ventricle (RV) models associated with normal subjects and abnormal RV patients to be subsequently used to assess RV function based on motion and kinematic analysis. We first constructed static RV models using segmentation masks of cardiac chambers generated from our accurate, memory-efficient deep neural architecture - CondenseUNet - featuring both a learned group structure and a regularized weight-pruner to estimate the motion of the right ventricle. In our study, we use a deep learning-based deformable network that takes 3D input volumes and outputs a motion field which is then used to generate isosurface meshes of the cardiac geometry at all cardiac frames by propagating the end-diastole (ED) isosurface mesh using the reconstructed motion field. The proposed model was trained and tested on the Automated Cardiac Diagnosis Challenge (ACDC) dataset featuring 150 cine cardiac MRI patient datasets. The isosurface meshes generated using the proposed pipeline were compared to those obtained using motion propagation via traditional non-rigid registration based on several performance metrics, including Dice score and mean absolute distance (MAD). 
    more » « less
  4. Purpose

    Ultra‐short echo time MRI is a promising alternative to chest CT for cystic fibrosis patients. Black‐blood imaging in particular could help discern small‐sized anomalies, such as mucoid plugging, which may otherwise be confused with neighboring blood vessels, particularly when contrast agent is not used. We, therefore, implemented and tested an ultra‐short echo time sequence with black‐blood preparation. Additionally, this sequence may also be used to generate bright‐blood angiograms.


    Using this sequence, data was acquired during free breathing in 10 healthy volunteers to obtain respiratory‐motion‐resolved 3D volumes covering the entire thorax with an isotropic resolution of (1 mm)3. The magnitude of signal suppression relative to a bright‐blood reference acquisition was quantified and compared with that obtained with a turbo‐spin echo (TSE) acquisition. Bright‐blood angiograms were also generated by subtraction. Finally, an initial feasibility assessment was performed in 2 cystic fibrosis patients, and images were visually compared with contrast‐enhanced images and with CT data.


    Black‐blood preparation significantly decreased the average normalized signal intensity in the vessel lumen (−66%;P< 0.001). Similarly, blood signal was significantly lowered (−60%;P= 0.001) compared with the TSE acquisition. In patients, mucoid plugging could be emphasized in the black‐blood datasets. An intercostal artery could also be visualized in the subtraction angiograms.


    Black‐blood free‐breathing ultra‐short echo time imaging was successfully implemented and motion‐resolved full volumetric coverage of the lungs with high spatial resolution was achieved, while obtaining an angiogram without contrast agent injection. Encouraging initial results in patients prompt further investigations in a larger cohort.

    more » « less
  5. This paper presents NeurEPDiff, a novel network to fast predict the geodesics in deformation spaces generated by a well known Euler-Poincaré differential equation (EPDiff). To achieve this, we develop a neural operator that for the first time learns the evolving trajectory of geodesic deformations parameterized in the tangent space of diffeomorphisms (a.k.a velocity fields). In contrast to previous methods that purely fit the training images, our proposed NeurEPDiff learns a nonlinear mapping function between the time-dependent velocity fields. A composition of integral operators and smooth activation functions is formulated in each layer of NeurEPDiff to effectively approximate such mappings. The fact that NeurEPDiff is able to rapidly provide the numerical solution of EPDiff (given any initial condition) results in a significantly reduced computational cost of geodesic shooting of diffeomorphisms in a high-dimensional image space. Additionally, the properties of discretization/resolution-invariant of NeurEPDiff make its performance generalizable to multiple image resolutions after being trained offline. We demonstrate the effectiveness of NeurEPDiff in registering two image datasets: 2D synthetic data and 3D brain resonance imaging (MRI). The registration accuracy and computational efficiency are compared with the state-of-the-art diffeomophic registration algorithms with geodesic shooting. 
    more » « less