skip to main content


Title: A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis
Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The out- put of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our pro- posed model is formulated as a variational problem that leverages several learnable modality-specific feature extractors and a multimodal synthesis module. We propose a learnable optimization algorithm to solve this model, which induces a multi-phase network whose parameters can be trained using multi-modal MRI data. Moreover, a bilevel-optimization framework is employed for robust parameter training. We demonstrate the effectiveness of our approach using extensive numerical experiments.  more » « less
Award ID(s):
2152961
NSF-PAR ID:
10396372
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
25th International Conference on Medical Image Computing and Computer Assisted Intervention
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. In this paper, we propose a deep multimodal fusion network to fuse multiple modalities (face, iris, and fingerprint) for person identification. The proposed deep multimodal fusion algorithm consists of multiple streams of modality-specific Convolutional Neural Networks (CNNs), which are jointly optimized at multiple feature abstraction levels. Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification. Features extracted at different convolutional layers of a modality-specific CNN represent the input at several different levels of abstract representations. We demonstrate that an efficient multimodal classification can be accomplished with a significant reduction in the number of network parameters by exploiting these multi-level abstract representations extracted from all the modality-specific CNNs. We demonstrate an increase in multimodal person identification performance by utilizing the proposed multi-level feature abstract representations in our multimodal fusion, rather than using only the features from the last layer of each modality-specific CNNs. We show that our deep multi-modal CNNs with multimodal fusion at several different feature level abstraction can significantly outperform the unimodal representation accuracy. We also demonstrate that the joint optimization of all the modality-specific CNNs excels the score and decision level fusions of independently optimized CNNs. 
    more » « less
  2. Introduction: Computed tomography perfusion (CTP) imaging requires injection of an intravenous contrast agent and increased exposure to ionizing radiation. This process can be lengthy, costly, and potentially dangerous to patients, especially in emergency settings. We propose MAGIC, a multitask, generative adversarial network-based deep learning model to synthesize an entire CTP series from only a non-contrasted CT (NCCT) input. Materials and Methods: NCCT and CTP series were retrospectively retrieved from 493 patients at UF Health with IRB approval. The data were deidentified and all images were resized to 256x256 pixels. The collected perfusion data were analyzed using the RapidAI CT Perfusion analysis software (iSchemaView, Inc. CA) to generate each CTP map. For each subject, 10 CTP slices were selected. Each slice was paired with one NCCT slice at the same location and two NCCT slices at a predefined vertical offset, resulting in 4.3K CTP images and 12.9K NCCT images used for training. The incorporation of a spatial offset into the NCCT input allows MAGIC to more accurately synthesize cerebral perfusive structures, increasing the quality of the generated images. The studies included a variety of indications, including healthy tissue, mild infarction, and severe infarction. The proposed MAGIC model incorporates a novel multitask architecture, allowing for the simultaneous synthesis of four CTP modalities: mean transit time (MTT), cerebral blood flow (CBF), cerebral blood volume (CBV), and time to peak (TTP). We propose a novel Physicians-in-the-loop module in the model's architecture, acting as a tunable layer that allows physicians to manually adjust the amount of anatomic detail present in the synthesized CTP series. Additionally, we propose two novel loss terms: multi-modal connectivity loss and extrema loss. The multi-modal connectivity loss leverages the multi-task nature to assert that the mathematical relationship between MTT, CBF, and CBV is satisfied. The extrema loss aids in learning regions of elevated and decreased activity in each modality, allowing for MAGIC to accurately learn the characteristics of diagnostic regions of interest. Corresponding NCCT and CTP slices were paired along the vertical axis. The model was trained for 100 epochs on a NVIDIA TITAN X GPU. Results and Discussion: The MAGIC model’s performance was evaluated on a sample of 40 patients from the UF Health dataset. Across all CTP modalities, MAGIC was able to accurately produce images with high structural agreement between the entire synthesized and clinical perfusion images (SSIMmean=0.801 , UQImean=0.926). MAGIC was able to synthesize CTP images to accurately characterize cerebral circulatory structures and identify regions of infarct tissue, as shown in Figure 1. A blind binary evaluation was conducted to assess the presence of cerebral infarction in both the synthesized and clinical perfusion images, resulting in the synthesized images correctly predicting the presence of cerebral infarction with 87.5% accuracy. Conclusions: We proposed a MAGIC model whose novel deep learning structures and loss terms enable high-quality synthesis of CTP maps and characterization of circulatory structures solely from NCCT images, potentially eliminating the requirement for the injection of an intravenous contrast agent and elevated radiation exposure during perfusion imaging. This makes MAGIC a beneficial tool in a clinical scenario increasing the overall safety, accessibility, and efficiency of cerebral perfusion and facilitating better patient outcomes. Acknowledgements: This work was partially supported by the National Science Foundation, IIS-1908299 III: Small: Modeling Multi-Level Connectivity of Brain Dynamics + REU Supplement, to the University of Florida. 
    more » « less
  3. The ability to estimate 3D human body pose and movement, also known as human pose estimation (HPE), enables many applications for home-based health monitoring, such as remote rehabilitation training. Several possible solutions have emerged using sensors ranging from RGB cameras, depth sensors, millimeter-Wave (mmWave) radars, and wearable inertial sensors. Despite previous efforts on datasets and benchmarks for HPE, few dataset exploits multiple modalities and focuses on home-based health monitoring. To bridge this gap, we present mRI1, a multi-modal 3D human pose estimation dataset with mmWave, RGB-D, and Inertial Sensors. Our dataset consists of over 160k synchronized frames from 20 subjects performing rehabilitation exercises and supports the benchmarks of HPE and action detection. We perform extensive experiments using our dataset and delineate the strength of each modality. We hope that the release of mRI can catalyze the research in pose estimation, multi-modal learning, and action understanding, and more importantly facilitate the applications of home-based health monitoring. 
    more » « less
  4. Brain imaging genetics studies the genetic basis of brain structures and functionalities via integrating genotypic data such as single nucleotide polymorphisms (SNPs) and imaging quantitative traits (QTs). In this area, both multi-task learning (MTL) and sparse canonical correlation analysis (SCCA) methods are widely used since they are superior to those independent and pairwise univariate analysis. MTL methods generally incorporate a few of QTs and could not select features from multiple QTs; while SCCA methods typically employ one modality of QTs to study its association with SNPs. Both MTL and SCCA are computational expensive as the number of SNPs increases. In this paper, we propose a novel multi-task SCCA (MTSCCA) method to identify bi-multivariate associations between SNPs and multi-modal imaging QTs. MTSCCA could make use of the complementary information carried by different imaging modalities. MTSCCA enforces sparsity at the group level via the G2,1-norm, and jointly selects features across multiple tasks for SNPs and QTs via the L2,1-norm. A fast optimization algorithm is proposed using the grouping information of SNPs. Compared with conventional SCCA methods, MTSCCA obtains better correlation coefficients and canonical weights patterns. In addition, MTSCCA runs very fast and easy-to-implement, indicating its potential power in genome-wide brain-wide imaging genetics. 
    more » « less
  5. Brain signals can be measured using multiple imaging modalities, such as magnetic resonance imaging (MRI)-based techniques. Different modalities convey distinct yet complementary information; thus, their joint analyses can provide valuable insight into how the brain functions in both healthy and diseased conditions. Data-driven approaches have proven most useful for multimodal fusion as they minimize assumptions imposed on the data, and there are a number of methods that have been developed to uncover relationships across modalities. However, none of these methods, to the best of our knowledge, can discover “one-to-many associations”, meaning one component from one modality is linked with more than one component from another modality. However, such “one-to-many associations” are likely to exist, since the same brain region can be involved in multiple neurological processes. Additionally, most existing data fusion methods require the signal subspace order to be identical for all modalities—a severe restriction for real-world data of different modalities. Here, we propose a new fusion technique—the consecutive independence and correlation transform (C-ICT) model—which successively performs independent component analysis and independent vector analysis and is uniquely flexible in terms of the number of datasets, signal subspace order, and the opportunity to find “one-to-many associations”. We apply C-ICT to fuse diffusion MRI, structural MRI, and functional MRI datasets collected from healthy controls (HCs) and patients with schizophrenia (SZs). We identify six interpretable triplets of components, each of which consists of three associated components from the three modalities. Besides, components from these triplets that show significant group differences between the HCs and SZs are identified, which could be seen as putative biomarkers in schizophrenia. 
    more » « less