Your browser doesn't support javascript.
loading
Machine learning analysis of whole mouse brain vasculature.
Todorov, Mihail Ivilinov; Paetzold, Johannes Christian; Schoppe, Oliver; Tetteh, Giles; Shit, Suprosanna; Efremov, Velizar; Todorov-Völgyi, Katalin; Düring, Marco; Dichgans, Martin; Piraud, Marie; Menze, Bjoern; Ertürk, Ali.
Afiliação
  • Todorov MI; Institute for Tissue Engineering and Regenerative Medicine (iTERM), Helmholtz Zentrum München, Neuherberg, Germany.
  • Paetzold JC; Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität (LMU), Munich, Germany.
  • Schoppe O; Graduate School of Neuroscience (GSN), Munich, Germany.
  • Tetteh G; Department of Computer Science, Technical University of Munich (TUM), Munich, Germany.
  • Shit S; Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany.
  • Efremov V; Munich School of Bioengineering, Technical University of Munich (TUM), Munich, Germany.
  • Todorov-Völgyi K; Department of Computer Science, Technical University of Munich (TUM), Munich, Germany.
  • Düring M; Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany.
  • Dichgans M; Department of Computer Science, Technical University of Munich (TUM), Munich, Germany.
  • Piraud M; Department of Computer Science, Technical University of Munich (TUM), Munich, Germany.
  • Menze B; Center for Translational Cancer Research of the TUM (TranslaTUM), Munich, Germany.
  • Ertürk A; Munich School of Bioengineering, Technical University of Munich (TUM), Munich, Germany.
Nat Methods ; 17(4): 442-449, 2020 04.
Article em En | MEDLINE | ID: mdl-32161395
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.
Assuntos

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Encéfalo / Aprendizado de Máquina Idioma: En Ano de publicação: 2020 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Encéfalo / Aprendizado de Máquina Idioma: En Ano de publicação: 2020 Tipo de documento: Article