Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GPU-Based Parallel Computing Methods for Medical Photoacoustic Image Reconstruction

Xinyao Yi, Yuxin Qiao

TL;DR

This paper demonstrates that GPU-based parallel computing, particularly through CUDA, substantially accelerates iterative photoacoustic image reconstruction without compromising accuracy. By profiling the reconstruction pipeline, the authors identify matrix multiplication as the dominant bottleneck and implement GPU-accelerated tiling, shared-memory strategies, and a tree-based accumulation to boost throughput. Experimental results show that GPU reconstruction of select frames achieves about a 5.9× speedup over CPU-based processing, enabling closer to real-time performance for photoacoustic imaging workflows. The work highlights practical pathways for integrating GPUs into medical imaging pipelines, with implications for hemodynamic monitoring and disease diagnostics.

Abstract

Recent years have witnessed a rapid advancement in GPU technology, establishing it as a formidable high-performance parallel computing technology with superior floating-point computational capabilities compared to traditional CPUs. This paper explores the application of this technology in the field of photoacoustic imaging, an emerging non-destructive testing technique in biomedical engineering characterized by its high contrast, resolution, and penetration depth. We conduct a data parallelism analysis targeting the computationally intensive image reconstruction segment of photoacoustic imaging. By parallelizing the serial code for iterative reconstruction and optimizing memory access, we achieve significant improvements in processing speed. Our experiments compare the imaging speeds of vascular images reconstructed using CPUs and GPUs, with the results visualized using Matlab. The findings demonstrate that, while maintaining data accuracy, GPU parallel computing methods can markedly accelerate photoacoustic image reconstruction. This acceleration has the potential to facilitate the broader adoption of photoacoustic imaging in applications such as hemodynamic monitoring, clinical disease diagnosis, and drug development.

GPU-Based Parallel Computing Methods for Medical Photoacoustic Image Reconstruction

TL;DR

This paper demonstrates that GPU-based parallel computing, particularly through CUDA, substantially accelerates iterative photoacoustic image reconstruction without compromising accuracy. By profiling the reconstruction pipeline, the authors identify matrix multiplication as the dominant bottleneck and implement GPU-accelerated tiling, shared-memory strategies, and a tree-based accumulation to boost throughput. Experimental results show that GPU reconstruction of select frames achieves about a 5.9× speedup over CPU-based processing, enabling closer to real-time performance for photoacoustic imaging workflows. The work highlights practical pathways for integrating GPUs into medical imaging pipelines, with implications for hemodynamic monitoring and disease diagnostics.

Abstract

Recent years have witnessed a rapid advancement in GPU technology, establishing it as a formidable high-performance parallel computing technology with superior floating-point computational capabilities compared to traditional CPUs. This paper explores the application of this technology in the field of photoacoustic imaging, an emerging non-destructive testing technique in biomedical engineering characterized by its high contrast, resolution, and penetration depth. We conduct a data parallelism analysis targeting the computationally intensive image reconstruction segment of photoacoustic imaging. By parallelizing the serial code for iterative reconstruction and optimizing memory access, we achieve significant improvements in processing speed. Our experiments compare the imaging speeds of vascular images reconstructed using CPUs and GPUs, with the results visualized using Matlab. The findings demonstrate that, while maintaining data accuracy, GPU parallel computing methods can markedly accelerate photoacoustic image reconstruction. This acceleration has the potential to facilitate the broader adoption of photoacoustic imaging in applications such as hemodynamic monitoring, clinical disease diagnosis, and drug development.
Paper Structure (25 sections, 8 equations, 12 figures, 5 tables)

This paper contains 25 sections, 8 equations, 12 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Parallel Computing on GPU
  3. Parallel Computing on GPU
  4. Emergence and Development of GPU Technology
  5. Computational Advantages of GPUs
  6. GPU+CPU Heterogeneous Parallel Computing Model
  7. CUDA
  8. Programming Model
  9. Memory Model
  10. Integration of CUDA with MATLAB for Enhanced Parallel Computing
  11. Photoacoustic Imaging
  12. Introduction to Medical Photoacoustic Imaging
  13. Advancements and Applications of Medical Photoacoustic Imaging
  14. Principle of Photoacoustic Computed Tomography (PACT)
  15. The Principle of Iterative Reconstruction for Photoacoustic Imaging
  16. ...and 10 more sections

Figures (12)

  • Figure 1: CPU and GPU Structures
  • Figure 2: Peak performance of CPU and GPU (measured in billions of floating-point operations per second, or gigaflops)
  • Figure 3: CUDA Programming Model
  • Figure 4: GPU Hydrogenous Memory Architecture
  • Figure 5: Compilation process of kernel function with MATLAB
  • ...and 7 more figures