Related Experiment Video
Updated: May 30, 2026
05:57
Blood Flow Imaging with Ultrafast Doppler
Published on: October 14, 2020
A fast forward projection using multithreads for multirays on GPUs in medical image reconstruction
Cheng-Ying Chou1, Yi-Yen Chuo, Yukai Hung
1Department of Bio-lndustrial Mechatronics Engineering, National Taiwan University, Taipei 106, Taiwan.
Medical Physics
|August 24, 2011
Summary
Accelerated iterative reconstruction algorithms using graphics processing units (GPUs) significantly reduce computation times for medical imaging. This enables faster image reconstruction, potentially improving image quality and lowering patient radiation dose.
Area of Science:
- Medical Imaging
- Computational Science
- Computer Engineering
Background:
- Iterative reconstruction techniques offer potential for noise reduction and dose optimization in medical imaging.
- Current iterative reconstruction methods face limitations due to lengthy computation times, hindering clinical adoption.
Purpose of the Study:
- To accelerate iterative reconstruction algorithms by leveraging the parallel processing capabilities of graphics processing units (GPUs).
- To optimize the forward projection algorithm, a computationally intensive component not amenable to closed-form solutions, for GPU implementation.
Main Methods:
- Developed a novel, multithreaded forward projection algorithm optimized for GPUs, addressing divergence and bank conflicts.
- Implemented a tiled algorithm with three-level parallelization, optimized thread block sizes, and maximized data reuse.
- Utilized batched fast Fourier transform (FFT) for accelerating filtering in the Feldkamp-Davis-Kress (FDK) algorithm and projection bundling for backprojection in FDK and Expectation-Maximization (EM).
Main Results:
- Demonstrated significant computational time savings on a single NVIDIA Tesla C1060 GPU.
- Achieved reconstruction times of approximately 4.13s (forward projection), 0.65s (filtering), and 2.47s (backprojection) for a 512^3 volume.
- Showcased near-perfect speedups with multiple GPUs, reducing times further (e.g., 1.11s, 0.18s, 0.66s with four GPUs).
- GPU-based results were virtually indistinguishable from CPU-based results.
Conclusions:
- Proposed highly optimized GPU-based algorithms for forward projection, FDK, and EM reconstruction.
- Achieved substantial speedups in forward and backprojection using Compute Unified Device Architecture (CUDA) codes.
- Shortened reconstruction times considerably, paving the way for routine clinical use in image quality enhancement and dose reduction.
Related Concept Videos
01:20Parallel Processing
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
01:10Computed Tomography
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...