NSF-2217089: Collaborative Research: PPoSS: Large : A Comprehensive Framework for Efficient, Scalable, and Performance-portable Tensor Applications
Funding source: NSF-CCF
Role: Co-Principal Investigator
Date: 07/01/2022 – 06/30/2027
This project brings together a team with complementary expertise with a focused plan to achieve significant advancement in performance-portability of tensor applications, as well as significant advancement in algorithm-architecture co-design methodology and tools for such computations. This project spans the full application-to-architecture software/hardware stack, along with consideration of the cross-cutting concern of accuracy/correctness.
R01-HL162353: Improved Imaging of Fibrosis in Atrial Fibrillation
Funding source: National Institutes of Health (NIH) / National Heart, Lung, and Blood Institute (NHLBI)
Role: Co-Principal Investigator
Date: 03/01/2022 – 02/28/2026
This project will offer a new MRI imaging technique and an associated machine learning approach to better assess the left atrium and to determine the repeatability of these measurements.
Contract: Vertebra Statistical Shape Model
Funding source: EOS Imaging
Role: Principal Investigator
Date: 08/01/2021 – 10/31/2022
In partnership with researchers at EOS Imaging, this project leverage the expertise in shape analysis of the ShapeWorks (SCI, Salt Lake City, US) research team to develop a process that can build a set of vertebra statistical shape models from a large-scale database composed of 3D models segmented from CT-Scan.
R01-EB016701: Computational and Statistical Framework to Model Tissue Shape and Mechanics
Funding source: National Institutes of Health (NIH) / National Institute of Biomedical Imaging and Bioengineering (NIBIB)
Role: Co-Investigator
Date: 08/01/2020 - 04/30/2024
This project will develop a framework to improve the efficiency in which computer models of tissue biomechanics and shape are developed and analyzed. Notably, we will apply techniques to visualize modeling data in aggregate form and will implement advanced statistical tests to evaluate group-differences in model predictions as well as findings from volumetric imaging. To impart broad impact, we will disseminate our methods to the community as open source software that will call core functionality provided by existing, open source software that has a large user base (FEBio, ShapeWorks).
R01-AR076120: Anatomy Directly from Imagery: General-purpose, Scalable, and Open-source Machine Learning Approaches
Funding source: National Institutes of Health (NIH) / National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS)
Role: Principal Investigator
Date: 07/01/2019 – 05/31/2023
This project aims at developing general-purpose, scalable, and open-source machine learning based computational tools to infer statistical shape representations of general anatomies directly from images, and hence bypassing the time-consuming and expert-driven anatomy segmentation step and subsequent user assistance and parameter tuning for building statistical shape models.
U24-EB029011: ShapeWorksStudio: An Integrative, User-Friendly, and Scalable Suite for Shape Representation and Analysis
Funding source: National Institutes of Health (NIH) / National Institute of Biomedical Imaging and Bioengineering (NIBIB)
Role: Principal Investigator
Date: 09/30/2019 - 06/30/2024
The goal of this project is to develop a software suite that leverages ShapeWorks for the automated population-/patient-level modeling of anatomical shapes, and Seg3D – a widely used open-source tool to visualize and process volumetric images – for flexible manual/semiautomatic segmentation and interactive manual correction of segmented anatomy.
R01-HL135568: New 3D and 4D Image-Based Clinical Measures of Atrial Structural and Functional Remodeling in Atrial Fibrillation
Funding source: National Institutes of Health (NIH) / National Heart, Lung, and Blood Institute (NHLBI)
Role: Co-Investigator
Date: 09/01/2017 – 08/31/2021
This project focuses on the development of new clinical measures of atrial shape for better individualized patient care of atrial fibrillation and advances the state-of-the art in computational methods for the statistical analysis of shape in clinical image data.
Contract: Advanced Image Processing Algorithms for Orthopedic Imaging
Funding source: Orthogrid Systems, Inc.
Role: Principal Investigator
Date: 10/01/2019 – 02/28/2021
In partnership with researchers at OrthoGrid Systems (OGS), this project pursues improving and / or applying existing image processing algorithms for orthopedic imaging and image analysis. Core areas of research considered are deep neural networks (DNN), statistical shape modeling (SSM), and distortion correction.
Contract: Euclid Ghosting: Auto Landmarking
Funding source: Orthogrid Systems, Inc.
Role: Principal Investigator
Date: 08/16/2018 – 08/15/2019
This project developed a machine learning approach for automating anatomical landmark detection in fluoro images of symptomatic joints and their corresponding asymptomatic side. These landmarks are used to perform smart image registration and quality control and derive quantitative measurements for comparing affected and unaffected sides in a surgical procedure.
Contract: Toward Faster and More Accurate Digigrid
Funding source: Orthogrid Systems, Inc.
Role: Principal Investigator
Date: 04/01/2018 – 05/15/2019
This project provided effective bounds on timing and accuracy performance of the current distortion correction approach using simulated calibration grids and distortion levels, and explored the feasibility of an updated calibration grid design to improve calibration accuracy near edges.
UR01630: Implicit Modeling of Geologic Structures
Funding source: ExxonMobil Upstream Research Company
Role: Co-Principal Investigator
Date: 01/10/2017 – 12/31/2019
This project developed a set of mathematical and visualization technologies and a software tool that would facilitate an easy construction and modification of geological structures, such that they can be combined with conceptual models for numerical simulations.
Contract: Monaco – Algorithms Prototyping and Development
Funding source: Siemens Medical Solutions
Role: Principal Investigator
Date: 05/15/2015 – 11/15/2019
This project developed algorithms for real-time 3D-2D image registration and visualization in DynaCT and fluoroscopy in electrophysiology for cardiac interventional procedures.
Copyright © 2022 Shireen Y. Elhabian. All rights reserved.