![]() ![]() For commonly available functional imaging setups such as point-scanning or spinning disk confocal systems, tradeoffs exist between SNR in images and microscopy parameters such as imaging speed (exposure time), field-of-view (FOV), image resolution, length of recording etc. The persistent goal is to image wider (more cells and larger areas), deeper, and faster, while enhancing signal-to-noise ratio (SNR). We envision that the framework will enable faster and long-term imaging experiments necessary to study neuronal mechanisms of many behaviors.įluorescent functional imaging is ubiquitous in neuroscience research in model systems. Our framework has 30× smaller memory footprint, and is fast in training and inference (50–70 ms) it is highly accurate and generalizable, and further, trained with only small, non-temporally-sequential, independently-acquired training datasets ( ∼500 pairs of images). Here, we demonstrate a supervised deep-denoising method to circumvent these tradeoffs for several applications, including whole-brain imaging, large-field-of-view imaging in freely moving animals, and recovering complex neurite structures in C. Further, these methods require temporally-sequential pre-registered data acquired at ultrafast rates. ![]() While deep-learning methods have recently been applied to denoise images, their applications to downstream analyses, such as recovering high-SNR calcium traces, have been limited. Volumetric functional imaging is widely used for recording neuron activities in vivo, but there exist tradeoffs between the quality of the extracted calcium traces, imaging speed, and laser power. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |