公开(公告)号：US12190572B2

公开(公告)日：2025-01-07

申请号：US17266447

申请日：2019-08-06

Applicant: Sphere Fluidics Limited

Inventor： Nicholas Dayrell-Armes ,  David Holmes ,  Frank F Craig ,  Marian Rehak ,  Dimitris Josephides ,  Robert Salter ,  William Whitley ,  Sinan Gokkaya ,  Raphael Ruis

IPC: G06V10/82 ,  B01L3/00 ,  G01N15/14 ,  G01N15/1433 ,  G06F18/2431 ,  G06T7/70 ,  G06V10/44 ,  G06V10/764 ,  G06V20/69 ,  G01N15/10

Abstract: A method of processing droplets in a microfluidic system. The method may comprise capturing a time sequence of images of a droplet as it passes through a channel in a microfluidic system. The method may further comprise processing each image of the sequence of images using a convolutional neural network to count a number of cells or other entities visible in each image the droplet. The method may further comprise processing the count of the number of cells or other entities visible in each image of the droplet to determine an estimated number of cells or other entities in the droplet. The method/system may further comprise controlling a microfluidic process performed on the droplet responsive to the estimated number of cells or other entities in the droplet. Implementations of the method use the changing orientation and disposition of droplet contents in combination with machine learning to improve monoclonality assurance.

公开(公告)号：US20210293691A1

公开(公告)日：2021-09-23

申请号：US17266447

申请日：2019-08-06

Applicant: Sphere Fluidics Limited

Inventor： Nicholas Dayrell-Armes ,  David Holmes ,  Frank F Craig ,  Marian Rehak ,  Dimitris Josephides ,  Robert Salter ,  William Whitley ,  Sinan Gokkaya ,  Raphael Ruis

IPC: G01N15/14 ,  B01L3/00 ,  G06K9/00 ,  G06K9/62 ,  G06T7/70

Abstract: A method of processing droplets in a microfluidic system. The method may comprise capturing a time sequence of images of a droplet as it passes through a channel in a microfluidic system. The method may further comprise processing each image of the sequence of images using a convolutional neural network to count a number of cells or other entities visible in each image the droplet. The method may further comprise processing the count of the number of cells or other entities visible in each image of the droplet to determine an estimated number of cells or other entities in the droplet. The method/system may further comprise controlling a microfluidic process performed on the droplet responsive to the estimated number of cells or other entities in the droplet. Implementations of the method use the changing orientation and disposition of droplet contents in combination with machine learning to improve monoclonality assurance.