Abstract
AbstractBrainstem nuclei are hard to distinguish due to very few distinctive features which makes detecting them with high accuracy extremely difficult. We introduce StARQ that builds on SeBRe, a deep learning-based framework to segment regions of interest. StARQ provides new functionalities for automated segmentation of brainstem nuclei at high granularity, and quantification of underlying neural features such as axonal tracings, and synaptic punctae. StARQ will serve as a toolbox for generalized brainstem analysis, enabling reliable high-throughput computational analysis with open-source models.
Publisher
Cold Spring Harbor Laboratory
Reference23 articles.
1. Developing a brain atlas through deep learning;Nature Machine Intelligence,2019
2. Zhongyu Li , Zengyi Shang , Jingyi Liu , Haotian Zhen , Entao Zhu , Shilin Zhong , Robyn N Sturgess , Yitian Zhou , Xuemeng Hu , Xingyue Zhao , et al. D-lmbmap: a fully automated deep-learning pipeline for whole-brain profiling of neural circuitry. Nature Methods, pages 1–12, 2023.
3. Mouse brain mr super-resolution using a deep learning network trained with optical imaging data;Frontiers in Radiology,2023
4. Spineracks and spinalj for efficient analysis of neurons in a 3d reference atlas of the mouse spinal cord;STAR protocols,2021
5. Denerd: high-throughput detection of neurons for brain-wide analysis with deep learning;Scientific reports,2019