Statistically unbiased prediction enables accurate denoising of voltage imaging data
Minho Eom, Seungjae Han, Gyuri Kim, Eun-Seo Cho, Jueun Sim, Pojeong Park, Kang-Han Lee, Seonghoon Kim, Marton Rozsa, Karel Svoboda, Myunghwan Choi, Cheol-Hee Kim, Adam Cohen, Jae-Byum Chang, Young-Gyu Yoon
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/NICALab/SUPPORTOfficialpytorch★ 101
Abstract
Here we report SUPPORT (Statistically Unbiased Prediction utilizing sPatiOtempoRal information in imaging daTa), a self-supervised learning method for removing Poisson-Gaussian noise in voltage imaging data. SUPPORT is based on the insight that a pixel value in voltage imaging data is highly dependent on its spatially neighboring pixels in the same time frame, even when its temporally adjacent frames do not provide useful information for statistical prediction. Such spatiotemporal dependency is captured and utilized to accurately denoise voltage imaging data in which the existence of the action potential in a time frame cannot be inferred by the information in other frames. Through simulation and experiments, we show that SUPPORT enables precise denoising of voltage imaging data while preserving the underlying dynamics in the scene.