虚拟现实
深度学习
计算机科学
计算生物学
人机交互
人工智能
神经科学
生物
作者
Doris Kaltenecker,Rami Al-Maskari,Moritz Negwer,Luciano Hoeher,Benedikt Wiestler,S. J. Zhao,Mihail Ivilinov Todorov,Zhouyi Rong,Johannes C. Paetzold,Benedikt Wiestler,Marie Piraud,Daniel Rueckert,Julia Geppert,Pauline Morigny,Maria Rohm,Bjoern Menze,Stephan Herzig,Mauricio Berriel Díaz,Ali Ertürk
标识
DOI:10.1038/s41592-024-02245-2
摘要
Abstract Automated detection of specific cells in three-dimensional datasets such as whole-brain light-sheet image stacks is challenging. Here, we present DELiVR, a virtual reality-trained deep-learning pipeline for detecting c-Fos + cells as markers for neuronal activity in cleared mouse brains. Virtual reality annotation substantially accelerated training data generation, enabling DELiVR to outperform state-of-the-art cell-segmenting approaches. Our pipeline is available in a user-friendly Docker container that runs with a standalone Fiji plugin. DELiVR features a comprehensive toolkit for data visualization and can be customized to other cell types of interest, as we did here for microglia somata, using Fiji for dataset-specific training. We applied DELiVR to investigate cancer-related brain activity, unveiling an activation pattern that distinguishes weight-stable cancer from cancers associated with weight loss. Overall, DELiVR is a robust deep-learning tool that does not require advanced coding skills to analyze whole-brain imaging data in health and disease.
科研通智能强力驱动
Strongly Powered by AbleSci AI