NEURALTRAK (20240221247). SYSTEM AND METHOD FOR 3D IMAGING RECONSTRUCTION USING DUAL-DOMAIN NEURAL NETWORK simplified abstract
Contents
SYSTEM AND METHOD FOR 3D IMAGING RECONSTRUCTION USING DUAL-DOMAIN NEURAL NETWORK
Organization Name
Inventor(s)
Linxi Shi of Los Altos CA (US)
George Zdasiuk of Portola Valley CA (US)
SYSTEM AND METHOD FOR 3D IMAGING RECONSTRUCTION USING DUAL-DOMAIN NEURAL NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240221247 titled 'SYSTEM AND METHOD FOR 3D IMAGING RECONSTRUCTION USING DUAL-DOMAIN NEURAL NETWORK
The application describes a method and system for medical 3D imaging reconstruction based on limited-angle 2D image acquisition, requiring only 30-50% of the data compared to traditional scanner-based 3D reconstruction. This approach reduces radiation dose and improves clinical efficiency.
- Capturing a limited-angle of 2D projections of a target
- Calibrating the 2D projections to obtain calibrated images
- Generating a sinogram from the calibrated images
- Inputting the sinogram into a dual-domain neural network for 3D volumetric image reconstruction
Potential Applications: - Medical imaging - Radiology - Image-guided surgery - Biomedical research
Problems Solved: - Reducing radiation exposure - Improving clinical workflow - Enhancing image quality and accuracy
Benefits: - Lower radiation dose - Faster imaging process - Enhanced diagnostic capabilities
Commercial Applications: Title: "Advanced Medical Imaging Technology for Improved Patient Care" This technology can be used in hospitals, imaging centers, and research institutions to enhance medical imaging capabilities, improve patient outcomes, and streamline clinical workflows.
Questions about Medical 3D Imaging Reconstruction: 1. How does limited-angle 2D image acquisition improve the efficiency of 3D reconstruction in medical imaging? Limited-angle 2D image acquisition reduces the amount of data required for reconstruction, leading to faster imaging processes and lower radiation exposure for patients.
2. What are the potential applications of dual-domain neural networks in medical imaging? Dual-domain neural networks can be used for image reconstruction, denoising, and enhancement in various medical imaging modalities, improving diagnostic accuracy and efficiency.
Original Abstract Submitted
this application describes a method and system for medical 3d imaging reconstruction based on limited-angle 2d image acquisition, which only requires 30�50% of the data required by traditional scanner-based 3d reconstruction. this approach significantly reduces the radiation dose requirement and improves clinical efficiency. an example method includes: capturing a plurality of 2-dimensional (2d) projections of a target that cover a limited angle of the target; calibrating the plurality of 2d projections of the target to obtain a plurality of calibrated 2d projections; generating a sinogram based on the plurality of calibrated 2d projections; inputting the sinogram into a dual-domain neural network to obtain a 3d volumetric image of the target that is geometrically corrected and calibrated.