当前位置: X-MOL 学术Front. Neural Circuits › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools.
Frontiers in Neural Circuits ( IF 3.4 ) Pub Date : 2020-07-15 , DOI: 10.3389/fncir.2020.00042
Lina M Tran 1, 2, 3 , Andrew J Mocle 1, 2 , Adam I Ramsaran 1, 4 , Alexander D Jacob 1, 4 , Paul W Frankland 1, 2, 4, 5, 6 , Sheena A Josselyn 1, 2, 4, 5, 7
Affiliation  

In vivo 1-photon (1p) calcium imaging is an increasingly prevalent method in behavioral neuroscience. Numerous analysis pipelines have been developed to improve the reliability and scalability of pre-processing and ROI extraction for these large calcium imaging datasets. Despite these advancements in pre-processing methods, manual curation of the extracted spatial footprints and calcium traces of neurons remains important for quality control. Here, we propose an additional semi-automated curation step for sorting spatial footprints and calcium traces from putative neurons extracted using the popular constrained non-negative matrixfactorization for microendoscopic data (CNMF-E) algorithm. We used the automated machine learning (AutoML) tools TPOT and AutoSklearn to generate classifiers to curate the extracted ROIs trained on a subset of human-labeled data. AutoSklearn produced the best performing classifier, achieving an F1 score >92% on the ground truth test dataset. This automated approach is a useful strategy for filtering ROIs with relatively few labeled data points and can be easily added to pre-existing pipelines currently using CNMF-E for ROI extraction.

中文翻译:


使用开源 AutoML 工具自动管理 CNMF-E 提取的 ROI 空间足迹和钙痕迹。



体内 1 光子 (1p​​) 钙成像是行为神经科学中越来越流行的方法。人们开发了许多分析流程来提高这些大型钙成像数据集的预处理和 ROI 提取的可靠性和可扩展性。尽管预处理方法取得了这些进步,但手动管理提取的神经元空间足迹和钙痕迹对于质量控制仍然很重要。在这里,我们提出了一个额外的半自动管理步骤,用于对使用流行的显微内窥镜数据约束非负矩阵分解(CNMF-E)算法提取的假定神经元的空间足迹和钙痕迹进行排序。我们使用自动化机器学习 (AutoML) 工具 TPOT 和 AutoSklearn 来生成分类器,以管理在人类标记数据子集上训练的提取的 ROI。 AutoSklearn 生成了性能最佳的分类器,在地面真实测试数据集上取得了 F1 分数 >92%。这种自动化方法是一种有用的策略,可用于过滤具有相对较少标记数据点的 ROI,并且可以轻松添加到当前使用 CNMF-E 进行 ROI 提取的现有管道中。
更新日期:2020-07-15
down
wechat
bug