eess.IV - 2023-12-07

Probabilistic volumetric speckle suppression in OCT using deep learning

  • paper_url: http://arxiv.org/abs/2312.04460
  • repo_url: https://github.com/bhaskarachintada/dltnode
  • paper_authors: Bhaskara Rao Chintada, Sebastián Ruiz-Lopera, René Restrepo, Brett E. Bouma, Martin Villiger, Néstor Uribe-Patarroyo
  • for: This paper aims to develop a deep learning framework for volumetric speckle reduction in optical coherence tomography (OCT) using a conditional generative adversarial network (cGAN).
  • methods: The proposed method takes partial OCT volumes as input and leverages the volumetric nature of OCT data to generate artifact-free despeckled volumes with excellent speckle reduction and resolution preservation in all three dimensions.
  • results: The proposed method demonstrates fast, effective, and high-quality despeckling of different tissue types acquired with three different OCT systems, outperforming existing deep learning methods. Additionally, the method addresses the challenge of generating high-quality, speckle-free training data by using volumetric non-local means despeckling-TNode.
    Abstract We present a deep learning framework for volumetric speckle reduction in optical coherence tomography (OCT) based on a conditional generative adversarial network (cGAN) that leverages the volumetric nature of OCT data. In order to utilize the volumetric nature of OCT data, our network takes partial OCT volumes as input, resulting in artifact-free despeckled volumes that exhibit excellent speckle reduction and resolution preservation in all three dimensions. Furthermore, we address the ongoing challenge of generating ground truth data for supervised speckle suppression deep learning frameworks by using volumetric non-local means despeckling-TNode to generate training data. We show that, while TNode processing is computationally demanding, it serves as a convenient, accessible gold-standard source for training data; our cGAN replicates efficient suppression of speckle while preserving tissue structures with dimensions approaching the system resolution of non-local means despeckling while being two orders of magnitude faster than TNode. We demonstrate fast, effective, and high-quality despeckling of the proposed network in different tissue types acquired with three different OCT systems compared to existing deep learning methods. The open-source nature of our work facilitates re-training and deployment in any OCT system with an all-software implementation, working around the challenge of generating high-quality, speckle-free training data.
    摘要 我团队提出了一种基于conditioned generative adversarial network(cGAN)的深度学习框架,用于对optical coherence tomography(OCT)数据进行三维斑点减少。为了利用OCT数据的三维性,我们的网络接受部分OCT卷积数据作为输入,从而生成了无残余的斑点减少后的高质量数据。此外,我们解决了生成深度学习框架的检测数据的挑战,通过使用volumetric non-local means despeckling-TNode生成训练数据。我们发现,虚拟节点处理是计算昂贵的,但它成为了训练数据的便利、可 accessible的黄金标准;我们的cGAN可以高效地减少斑点,同时保留组织结构,与非本地 means despeckling的系统分辨率相近,且两个数量级更快。我们展示了我们提议的网络在不同的组织类型和三个不同的OCT系统上的快速、高质量的斑点减少。我们的开源实现方便了重训练和部署,并且可以绕过生成高质量、斑点减少后的训练数据的挑战。

Analysis of Coding Gain Due to In-Loop Reshaping

  • paper_url: http://arxiv.org/abs/2312.04022
  • repo_url: None
  • paper_authors: Chau-Wai Wong, Chang-Hong Fu, Mengting Xu, Guan-Ming Su
  • for: 这 paper 是关于视频编码方面的研究,旨在提高编码率。
  • methods: 这 paper 使用了点操作,Directly modify the input video signal to improve the compression ratio。
  • results: 这 paper 通过 teorically 分析和实验验证,显示了在非优化 entropy coder 的情况下,Point reshaping 可以提高编码率。并且可以获得closed form 中的 PSNR 增加。
    Abstract Reshaping, a point operation that alters the characteristics of signals, has been shown capable of improving the compression ratio in video coding practices. Out-of-loop reshaping that directly modifies the input video signal was first adopted as the supplemental enhancement information~(SEI) for the HEVC/H.265 without the need of altering the core design of the video codec. VVC/H.266 further improves the coding efficiency by adopting in-loop reshaping that modifies the residual signal being processed in the hybrid coding loop. In this paper, we theoretically analyze the rate-distortion performance of the in-loop reshaping and use experiments to verify the theoretical result. We prove that the in-loop reshaping can improve coding efficiency when the entropy coder adopted in the coding pipeline is suboptimal, which is in line with the practical scenarios that video codecs operate in. We derive the PSNR gain in a closed form and show that the theoretically predicted gain is consistent with that measured from experiments using standard testing video sequences.
    摘要 rezhi,一种点操作,可以改变信号特性,已经证明可以提高视频编码中的压缩比率。在HEVC/H.265中,直接修改输入视频信号的out-of-loop rezhi首先被采用为supplemental enhancement information(SEI),无需修改视频编码的核心设计。VVC/H.266进一步提高了编码效率,通过在混合编码循环中修改剩余信号。在这篇论文中,我们 theoretically 分析了rezhi在循环中的Rate-Distortion性能,并通过实验验证我们的理论结果。我们证明,rezhi可以在编码ipeline中使用的 entropy 编码器不是最佳的情况下提高编码效率,这与实际的视频编码场景相符。我们 derive PSNR 增加的closed form 和实验结果相符。

Ricci-Notation Tensor Framework for Model-Based Approaches to Imaging

  • paper_url: http://arxiv.org/abs/2312.04018
  • repo_url: None
  • paper_authors: Dileepan Joseph
  • for: 这篇论文主要针对的是用tensor代数和编程技术进行图像增强的研究。
  • methods: 该论文提出了一种基于Ricci符号notation的tensor框架(RT框架),包括扩展的Ricci符号notation和 codesigned的对象对象编程框架RTToolbox。
  • results: 对比 numeric tensor 前置者,RT框架具有更高的计算和编程效率,可以更好地模型图像问题并开发解决方案。
    Abstract Model-based approaches to imaging, like specialized image enhancements in astronomy, favour physics-based models which facilitate explanations of relationships between observed inputs and computed outputs. While this paper features a tutorial example, inspired by exoplanet imaging, that reveals embedded 2D fast Fourier transforms in an image enhancement model, the work is actually about the tensor algebra and software, or tensor frameworks, available for model-based imaging. The paper proposes a Ricci-notation tensor (RT) framework, comprising an extended Ricci notation, which aligns well with the symbolic dual-index algebra of non-Euclidean geometry, and codesigned object-oriented software, called the RTToolbox for MATLAB. Extensions offer novel representations for entrywise, pagewise, and broadcasting operations popular in extended matrix-vector (EMV) frameworks for imaging. Complementing the EMV algebra computable with MATLAB, the RTToolbox demonstrates programmatic and computational efficiency thanks to careful design of tensor and dual-index classes. Compared to a numeric tensor predecessor, the RT framework enables superior ways to model imaging problems and, thereby, to develop solutions.
    摘要 模型基于方法,如天文学专门的图像提高技术,偏好基于物理模型,以便解释观测输入和计算输出之间的关系。本文介绍了一个教程例子, Draw inspiration from exoplanet imaging, revela了图像提高模型中嵌入的2D快速傅立做 transforms。然而,这篇文章实际上是关于矩阵代数和软件,或矩阵框架,用于模型基于图像的。文章提出了一种基于征 Ricci notation tensor(RT)框架,包括一个扩展的征 Ricci notation,与非欧几何的Symbolic dual-index algebraaligns well,以及codesigned object-oriented软件,称为RTToolbox for MATLAB。扩展提供了novel representations for entrywise、pagewise和广播操作,广泛用于扩展矩阵-向量(EMV)框架。与EMV算法可计算的MATLAB相比,RTToolbox表现出了优秀的程序和计算效率,感谢tensor和 dual-index类的优化设计。与 numeric tensor前代的RT框架相比,RT框架允许更好地模型图像问题,并因此开发解决方案。