Title: Machine Learning to Quantify Brain Activity from Astrocyte Imaging Data

Speaker: Guoqiang Yu, Associate Professor, Bradley Department of Electrical & Computer Engineering, Virginia Tech

Time: 10:00-11:30, March 12, 2019

Location: Room 1113, Wang Kezhen Building, Peking University

Abstract:

Recent studies have suggested that astrocytes exert proactive regulatory effects on brain information processing and that they are deeply involved in normal brain development and disease pathology. Recording astrocyte activity is now technically feasible, due to recent advances in modern microscopy and ultrasensitive cell-type specific genetically encoded Ca2+ indicators for long-time imaging. However, there is a big gap between generating the data and extracting information from the data. Indeed, partially because of the challenges imposed by the complex patterns in astrocyte activity data, the development of sophisticated modeling and analysis tools lags much behind, and the current practice is essentially manual. This practice not only limits analysis throughput but also risks introducing bias and missing important information latent in complex, dynamic big data. In this talk, I will discuss our recent work on applying machine learning theory and techniques to flexibly and accurately quantify the astrocyte activity from the time-lapse fluorescent imaging data. For those who are interested in biology, I will demonstrate how our work can be used to assist your study of decoding the functional roles of astrocyte in brain. For those who are interested in the algorithm and tool development, I will show you how the astrocyte activity analysis is a booming research area and how the problem can serve as a motivating example for generic algorithm development.

Host: Dr. Yulong Li