公开(公告)号：US20220020115A1

公开(公告)日：2022-01-20

申请号：US17309027

申请日：2019-06-10

Applicant: Purdue Research Foundation

Inventor： Peiyi ZHANG ,  Fang HUANG ,  Sheng LIU

IPC: G06T3/40 ,  G06N3/08 ,  G01J3/443 ,  G01J3/28 ,  G01N21/64

Abstract: A fluorescent single molecule emitter simultaneously transmits its identity, location, and cellular context through its emission patterns. A deep neural network (DNN) performs multiplexed single-molecule analysis to enable retrieving such information with high accuracy. The DNN can extract three-dimensional molecule location, orientation, and wavefront distortion with precision approaching the theoretical limit of information content of the image which will allow multiplexed measurements through the emission patterns of a single molecule.