Technology ID
TAB-3810

High-Resolution and Artifact-Free Measurement and Visualization of Tissue Strain by Processing MRI Using a Deep Learning Approach

E-Numbers
E-203-2022-0
Lead Inventor
Abd-Elmoniem, Khaled (NIDDK)
Co-Inventors
Abdelfadeel, Ahmed (NIDDK)
Gharib, Ahmed (NIDDK)
Yassine, Inas (Cairo University)
Applications
Software / Apps
Research Materials
Non-Medical Devices
Medical Devices
Diagnostics
Therapeutic Areas
Ophthalmology
Oncology
Neurology
Infectious Disease
Endocrinology
Dental
Cardiology
Research Products
Computational models/software
Lead IC
NIDDK
ICs
NIDDK
This technology includes a system for automatic artifact-free measurement and visualization of tissue strain by MRI at native resolution. The investigation of regional soft tissue mechanical strain can serve as a unique indicator for different related disorders. For example, measurement of myocardial tissue during contraction can help calculate, track, and assess cardiac stress. Currently, methods such as tagging MRI (tMRI) are used for imaging soft tissue deformation. Despite being well validated, methods such as tMRI suffer from low spatial and temporal resolution. The current described technology obtains pixelwise native high-resolution imagery for strain-mapping using a deep learning convolutional neural network.
Commercial Applications
High-resolution imaging and analysis of tissue strain can be used to reduce the time to diagnosis and provide more informative information for the treatment of a variety of disorders, including:
  • liver inflammation and fibrosis assessment
  • heart strain, cardiac function early assessment
  • brain damage and tumor detection
  • tongue tumors and speech problems
Competitive Advantages
This method provides for a high anatomic, functional, and temporal resolution of tissue strain and deformation with unprecedented clarity.
Licensing Contact:
Knezevic, Vladimir
vlado.knezevic@nih.gov