德国组织工程和再生医学研究所Ali Ertrk和慕尼黑工业大学Bjoern Menze课题组合作，对小鼠全脑血管进行了机器学习分析。论文于3月11日在线发表在《自然-方法学》。

在本研究中，研究人员开发了一个基于深度学习的网络来量化和分析脑血管，称为血管分割和分析管道（VesSAP）。该方法使用带转移学习方法对卷积神经网络（CNN）进行分割，并达到了人类水平的准确性。

通过使用VesSAP，研究人员将整个C57BL / 6J、CD1和BALB / c小鼠脑载入到Allen小鼠脑图集后，在微米级分析了它们的血管特征。

研究人员揭示了CD1小鼠继发性颅内侧血管生成的证据，并发现与大脑相比脑干的血管生成减少。因此，VesSAP可以对清除的小鼠大脑血管结构进行无偏倚且可扩展的量化，并提供对大脑血管功能的生物学见解。

据了解，利用组织清除方法可以实现无需切片而对生物样本进行成像。然而，在三维水平对大型成像数据集进行可靠且可扩展的分析仍然是一个挑战。

附：英文原文

Title: Machine learning analysis of whole mouse brain vasculature

Author: Mihail Ivilinov Todorov, Johannes Christian Paetzold, Oliver Schoppe, Giles Tetteh, Suprosanna Shit, Velizar Efremov, Katalin Todorov-Vlgyi, Marco Dring, Martin Dichgans, Marie Piraud, Bjoern Menze, Ali Ertrk

Issue&Volume: 2020-03-11

Abstract: Tissue clearing methods enable the imaging of biological specimens without sectioning. However, reliable and scalable analysis of large imaging datasets in three dimensions remains a challenge. Here we developed a deep learning-based framework to quantify and analyze brain vasculature, named Vessel Segmentation & Analysis Pipeline (VesSAP). Our pipeline uses a convolutional neural network (CNN) with a transfer learning approach for segmentation and achieves human-level accuracy. By using VesSAP, we analyzed the vascular features of whole C57BL/6J, CD1 and BALB/c mouse brains at the micrometer scale after registering them to the Allen mouse brain atlas. We report evidence of secondary intracranial collateral vascularization in CD1 mice and find reduced vascularization of the brainstem in comparison to the cerebrum. Thus, VesSAP enables unbiased and scalable quantifications of the angioarchitecture of cleared mouse brains and yields biological insights into the vascular function of the brain.

DOI: 10.1038/s41592-020-0792-1

Source: https://www.nature.com/articles/s41592-020-0792-1