Deep learning approach to Fourier ptychographic microscopy
Our recent work addresses the pressing need for high-throughput label-free microscopy and demonstrates gigapixel phase reconstruction in less than 30 seconds by a novel learning strategy that exploits in-variance in space and time. Read more here.
We have demonstrated a deep learning framework for Fourier ptychography video reconstruction. The proposed CNN architecture fully exploits the unique high-SBP imaging capability of FPM so that it can be trained using a single frame and then be generalized to a full time-series experiment.
We trained on Hela cells to predict the phase reconstruction of two other cell types (MCF10A, U2OS) with or without staining
FPM_Floss.aviHela cells video reconstruction in 4 hours
Digital Holographic Microscopy (DHM) based on deep learning
A novel method that combines a supervised deep learning technique with convolutional neural network (CNN) and Zernike polynomial fitting (ZPF). The deep learning CNN is implemented to perform automatic background region detection that allows for ZPF to compute the self-conjugated phase to compensate for most aberrations. Read more here.
ThreeHoursCellDefault.avi