Department of Medical and Bioinformatics, School of Informatics, Communications and Media, University of Applied Sciences Upper Austria, Hagenberg i. M., Austria.
Ludwig Boltzmann Institute for Experimental and Clinical Traumatology in the AUVA trauma research center, Austrian Cluster for Tissue Regeneration, Vienna, Austria.
PLoS One. 2023 Oct 12;18(10):e0291946. doi: 10.1371/journal.pone.0291946. eCollection 2023.
Identification and quantitative segmentation of individual blood vessels in mice visualized with preclinical imaging techniques is a tedious, manual or semiautomated task that can require weeks of reviewing hundreds of levels of individual data sets. Preclinical imaging, such as micro-magnetic resonance imaging (μMRI) can produce tomographic datasets of murine vasculature across length scales and organs, which is of outmost importance to study tumor progression, angiogenesis, or vascular risk factors for diseases such as Alzheimer's. Training a neural network capable of accurate segmentation results requires a sufficiently large amount of labelled data, which takes a long time to compile. Recently, several reasonably automated approaches have emerged in the preclinical context but still require significant manual input and are less accurate than the deep learning approach presented in this paper-quantified by the Dice score. In this work, the implementation of a shallow, three-dimensional U-Net architecture for the segmentation of vessels in murine brains is presented, which is (1) open-source, (2) can be achieved with a small dataset (in this work only 8 μMRI imaging stacks of mouse brains were available), and (3) requires only a small subset of labelled training data. The presented model is evaluated together with two post-processing methodologies using a cross-validation, which results in an average Dice score of 61.34% in its best setup. The results show, that the methodology is able to detect blood vessels faster and more reliably compared to state-of-the-art vesselness filters with an average Dice score of 43.88% for the used dataset.
使用临床前成像技术对小鼠的个体血管进行识别和定量分割是一项繁琐的手动或半自动任务，可能需要数周时间来检查数百个个体数据集的层面。临床前成像，如微磁共振成像 (μMRI)，可以在长度尺度和器官上产生小鼠血管的断层数据集，这对于研究肿瘤进展、血管生成或阿尔茨海默病等疾病的血管风险因素至关重要。训练能够产生准确分割结果的神经网络需要足够大量的标记数据，这需要很长时间才能编译。最近，在临床前环境中出现了几种相当自动化的方法，但仍然需要大量的手动输入，并且不如本文提出的深度学习方法准确——通过 Dice 分数进行量化。在这项工作中，提出了一种用于分割小鼠大脑血管的浅层三维 U-Net 架构的实现，该架构 (1) 是开源的，(2) 可以使用小数据集（在这项工作中，仅可用 8 个 μMRI 成像堆叠的小鼠大脑），并且 (3) 仅需要一小部分标记的训练数据。该模型与两种后处理方法一起使用交叉验证进行评估，在最佳设置下平均 Dice 分数为 61.34%。结果表明，与血管检测方法相比，该方法能够更快、更可靠地检测血管，血管检测方法的平均 Dice 分数为 43.88%。
