公开(公告)号：US10593039B2

公开(公告)日：2020-03-17

申请号：US15928992

申请日：2018-03-22

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Bahram Jalali ,  Ata Mahjoubfar ,  Lifan Chen

IPC: G06K9/00 ,  G06T7/00 ,  G16B40/00 ,  G06N3/08 ,  G01N15/14 ,  G06K9/46 ,  G06N3/04 ,  G01N15/10

Abstract: A method and apparatus for using deep learning in label-free cell classification and machine vision extraction of particles. A time stretch quantitative phase imaging (TS-QPI) system is described which provides high-throughput quantitative imaging, and utilizing photonic time stretching. In at least one embodiment, TS-QPI is integrated with deep learning to achieve record high accuracies in label-free cell classification. The system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. The system is particularly well suited for data-driven phenotypic diagnosis and improved understanding of heterogeneous gene expression in cells.

公开(公告)号：US20180286038A1

公开(公告)日：2018-10-04

申请号：US15928992

申请日：2018-03-22

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Bahram Jalali ,  Ata Mahjoubfar ,  Lifan Chen

IPC: G06T7/00 ,  G06F19/24 ,  G06N3/08 ,  G01N15/14 ,  G06N3/04

CPC classification number: G06T7/0012 ,  G01N15/1429 ,  G01N15/1434 ,  G01N15/147 ,  G01N15/1475 ,  G01N2015/1006 ,  G01N2015/144 ,  G01N2015/1445 ,  G01N2015/1454 ,  G01N2015/149 ,  G06K9/00127 ,  G06K9/0014 ,  G06K9/00147 ,  G06K9/4628 ,  G06N3/04 ,  G06N3/086 ,  G16B40/00

Abstract: A method and apparatus for using deep learning in label-free cell classification and machine vision extraction of particles. A time stretch quantitative phase imaging (TS-QPI) system is described which provides high-throughput quantitative imaging, and utilizing photonic time stretching. In at least one embodiment, TS-QPI is integrated with deep learning to achieve record high accuracies in label-free cell classification. The system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. The system is particularly well suited for data-driven phenotypic diagnosis and improved understanding of heterogeneous gene expression in cells.