Intellicount: High-Throughput Quantification of Fluorescent Synaptic Protein Puncta by Machine Learning
Intellicount: High-Throughput Quantification of Fluorescent Synaptic Protein Puncta by Machine Learning
复制标题
DOI：
10.1523/eneuro.0219-17.2017
复制
发表时间：
2017-11-01
期刊：
影响因子：
3.4
通讯作者：
Pang, Z. P.
中科院分区：
文献类型：
--
作者：
Fantuzzo, J. A.;Mirabella, V. R.;Pang, Z. P.
突触形成分析可以通过成像和量化突触标记物的荧光信号来进行。传统上，这些分析是使用简单或多个阈值和分割方法或通过人工观察者的劳动密集型手动分析来完成的。在这里，我们描述了Intellicount，一个高通量，全自动突触量化程序，它应用了一种新的基于机器学习（ML）的图像处理算法，系统地提高了简单阈值技术的感兴趣区域（ROI）识别。通过处理来自人类和小鼠神经元的大型数据集，我们证明了这种方法允许图像处理独立于仔细设置的阈值进行，从而减少了对人为干预的需求。因此，该方法可以有效和准确地处理大型图像数据集，实验者的交互最少，使其不容易出现偏差，也不容易出现人为错误。此外，Intellicount集成到一个直观的图形用户界面（GUI）中，提供了一系列有价值的功能，包括自动化和多功能图形生成，常规统计分析以及通过嵌套文件夹运行完整数据集的能力，大大加快了数据分析过程。
Synapse formation analyses can be performed by imaging and quantifying fluorescent signals of synaptic markers. Traditionally, these analyses are done using simple or multiple thresholding and segmentation approaches or by labor-intensive manual analysis by a human observer. Here, we describe Intellicount, a high-throughput, fully-automated synapse quantification program which applies a novel machine learning (ML)-based image processing algorithm to systematically improve region of interest (ROI) identification over simple thresholding techniques. Through processing large datasets from both human and mouse neurons, we demonstrate that this approach allows image processing to proceed independently of carefully set thresholds, thus reducing the need for human intervention. As a result, this method can efficiently and accurately process large image datasets with minimal interaction by the experimenter, making it less prone to bias and less liable to human error. Furthermore, Intellicount is integrated into an intuitive graphical user interface (GUI) that provides a set of valuable features, including automated and multifunctional figure generation, routine statistical analyses, and the ability to run full datasets through nested folders, greatly expediting the data analysis process.