Logo Logo
Hilfe
Hilfe
Switch Language to English

Todorov, Mihail Ivilinov; Paetzold, Johannes Christian; Schoppe, Oliver; Tetteh, Giles; Shit, Suprosanna; Efremov, Velizar; Todorov-Völgyi, Katalin; Duering, Marco; Dichgans, Martin ORCID logoORCID: https://orcid.org/0000-0002-0654-387X; Piraud, Marie; Menze, Björn und Ertürk, Ali (2020): Machine learning analysis of whole mouse brain vasculature. In: Nature Methods, Bd. 17, Nr. 4: S. 442-449 [PDF, 3MB]

[thumbnail of nihms-1628795.pdf]
Vorschau

Eingereichte Version
Download (3MB)

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. VesSAP is a tissue clearing- and deep learning-based pipeline for comprehensively analyzing mouse vasculature, from large vessels to small capillaries.

Dokument bearbeiten Dokument bearbeiten