用并行积分图像加速生物图像聚类分析，处理超大图快10万倍。
Accelerating Biological Spatial Cluster Analysis with the Parallel Integral Image Technique
- 用并行积分图像技术优化滑动窗口分析，大幅降低计算开销。
- 在小图上提速13万倍，大图上稳定超过1万倍，支持7万×8.5万像素图像。
- 开源工具包已发布，适合高分辨率显微图像分析研究者使用。
空间聚类分析（SCA）为生物图像提供重要洞察，常用方法是滑动窗口分析（SWA）。然而，SWA计算成本高，难以处理大尺寸图像，限制其在小规模图像上的应用。随着高分辨率显微技术发展，图像尺寸已达70,000×85,000像素，超出以往SWA方法的处理能力。本文提出并行积分图像方法改进SWA，实现显著加速：在小规模图像上达到131,806倍提速，在多种大规模显微图像上保持超过10,000倍的速度提升。通过分析计算复杂度优势，并验证积分图像方法的性能优越性。相关代码以开源Python包形式发布于https://github.com/OckermanSethGVSU/BioPII。
原文摘要 · Abstract (English)
Spatial cluster analysis (SCA) offers valuable insights into biological images; a common SCA technique is sliding window analysis (SWA). Unfortunately, SWA's computational cost hinders its application to larger images, limiting its use to small-scale images. With advancements in high-resolution microscopy, images now exceed the capabilities of previous SWA approaches, reaching sizes up to 70,000 by 85,000 pixels. To overcome these limitations, this paper introduces the parallel integral image approach to SWA, surpassing previous methods. We achieve a remarkable speedup of 131,806x on small-scale images and consistent speedups of over 10,000x on a variety of large-scale microscopy images. We analyze the computational complexity advantages of the parallel integral image approach and present experimental results that validate the superior performance of integral-image-based methods. Our approach is made available as an open-source Python PIP package available at https://github.com/OckermanSethGVSU/BioPII.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。