A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy

📄 arXiv: 2310.08143v1 📥 PDF

作者: Léo Milecki, Jonathan Porée, Hatim Belgharbi, Chloé Bourquin, Rafat Damseh, Patrick Delafontaine-Martel, Frédéric Lesage, Maxime Gasse, Jean Provost

分类: cs.CV

发布日期: 2023-10-12

备注: Copyright 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

期刊: IEEE Transactions on Medical Imaging (Volume: 40, Issue: 5, May 2021)

DOI: 10.1109/TMI.2021.3056951

💡 一句话要点

提出深度学习框架以解决超声定位显微镜中的微血管重建问题

🎯 匹配领域: 支柱八：物理动画 (Physics-based Animation)

📋 核心要点

  1. 现有超声定位显微镜方法在处理高浓度微泡时面临干扰问题，导致重建精度不足。
  2. 论文提出了一种基于深度学习的三维卷积神经网络，通过模拟数据训练以提高微血管网络的重建能力。
  3. 实验结果表明，所提方法在体外和体内均显著提高了微血管的重建精度和分辨率，优于传统方法。

📝 摘要（中文）

超声定位显微镜能够将微血管床分辨至几微米。为了实现这一性能，微泡对比剂必须充分灌注整个微血管网络。微泡被单独定位并随时间跟踪，以采样单个血管，通常需要数十万张图像。现有处理流程无法有效处理多个相邻微泡的干扰，进一步降低了可实现的浓度。本文提出了一种深度学习方法，通过高浓度微泡的超声采集恢复密集的血管网络。使用从双光子显微镜分割的真实小鼠脑微血管网络训练了基于V-net架构的三维卷积神经网络。模拟了多个微泡流经微血管网络的超声数据集，并作为真实数据训练3D CNN以跟踪微泡。该方法在体内外验证，结果显示其在重建精度和分辨率上均优于传统方法。

🔬 方法详解

问题定义：本文旨在解决超声定位显微镜中高浓度微泡干扰导致的微血管重建精度不足的问题。现有方法在处理多个相邻微泡时，无法有效分离和跟踪，限制了微血管网络的重建能力。

核心思路：论文提出了一种基于深度学习的三维卷积神经网络（3D CNN），通过模拟微泡流动的超声数据进行训练，以提高对微血管网络的重建精度。该方法利用深度学习的特性，能够更好地处理复杂的干扰情况。

技术框架：整体架构包括数据模拟、网络训练和结果验证三个主要阶段。首先，通过双光子显微镜获取真实的微血管网络数据，然后生成多个微泡流动的超声数据集作为训练基础，最后使用训练好的3D CNN进行微血管重建。

关键创新：最重要的技术创新在于使用深度学习方法来处理高浓度微泡的干扰问题，显著提高了微血管重建的精度和分辨率。这一方法与传统的超声定位显微镜框架相比，能够更有效地分离和跟踪微泡。

关键设计：在网络结构上，采用了V-net架构，设计了适合三维数据处理的卷积层和池化层。损失函数的选择也经过优化，以确保在训练过程中能够有效地捕捉微血管的细节特征。

📄 摘要（原文）

Ultrasound Localization Microscopy can resolve the microvascular bed down to a few micrometers. To achieve such performance microbubble contrast agents must perfuse the entire microvascular network. Microbubbles are then located individually and tracked over time to sample individual vessels, typically over hundreds of thousands of images. To overcome the fundamental limit of diffraction and achieve a dense reconstruction of the network, low microbubble concentrations must be used, which lead to acquisitions lasting several minutes. Conventional processing pipelines are currently unable to deal with interference from multiple nearby microbubbles, further reducing achievable concentrations. This work overcomes this problem by proposing a Deep Learning approach to recover dense vascular networks from ultrasound acquisitions with high microbubble concentrations. A realistic mouse brain microvascular network, segmented from 2-photon microscopy, was used to train a three-dimensional convolutional neural network based on a V-net architecture. Ultrasound data sets from multiple microbubbles flowing through the microvascular network were simulated and used as ground truth to train the 3D CNN to track microbubbles. The 3D-CNN approach was validated in silico using a subset of the data and in vivo on a rat brain acquisition. In silico, the CNN reconstructed vascular networks with higher precision (81%) than a conventional ULM framework (70%). In vivo, the CNN could resolve micro vessels as small as 10 $μ$m with an increase in resolution when compared against a conventional approach.