Systems and methods for counting particles

Inventors

Vidal, ReneHAEFFELE, Benjamin D.YELLIN, Florence

Assignees

MiDiagnostics NVJohns Hopkins University

Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Publication Number

US-11846577-B2

Patent

Publication Date

2023-12-19

Expiration Date


Abstract

Systems and methods are provided for counting particles in a fluid flow. In an aspect, coordinates of particles are obtained from video data of particles in a fluid, the video data made up of a sequence of image frames. The particle positions are linked in each pair of consecutive image frames of the video data. The linked particle positions are used to calculate particle trajectories through sequential image frames of the video data, and the particles are counted based on the particle trajectory. In another aspect, the particle positons within each image frame are transformed to estimated positions within a common coordinate frame. The estimated particle positions of a particle are grouped into a cluster center, and the particle count is calculated based on the cluster centers.

Core Innovation

The disclosed invention relates to particle counting in a fluid using video data comprising a sequence of image frames. A set of (x, y) coordinates corresponding to particle centers is obtained for particles within the fluid, with each set of (x, y) coordinates corresponding to an image frame. The approach transforms the coordinates of each particle center of each image frame to expected coordinates of a respective expected particle center in a common image frame.

After mapping particle-center coordinates into the common image frame, the expected coordinates of the expected particle centers are grouped into cluster centers. A particle count is then calculated based on the number of cluster centers, so that grouping across the common frame provides a particle counting basis from the video data.

In an exemplary implementation, a system includes a flow cell with a fluid passage and a lens-free image sensor that obtains holographic images of the fluid in the fluid passage. The processor captures video data of particles within the fluid using the lens-free image sensor, obtains the (x, y) coordinates of particle centers, performs the coordinate transforming to expected coordinates in a common image frame, groups the expected coordinates into cluster centers, and calculates a particle count based on the number of cluster centers.

Claims Coverage

The independent claims cover a method, a system, and a non-transitory computer-readable medium that perform a shared core pipeline. Across the independent claims, the main inventive features are coordinate transformation of particle centers into expected coordinates in a common image frame, clustering of expected coordinates into cluster centers, and calculating a particle count based on the number of cluster centers.

Transforming particle-center coordinates into expected coordinates in a common image frame

Transforming coordinates of each particle center of each image frame to expected coordinates of a respective expected particle center in a common image frame.

Grouping expected coordinates into cluster centers

Grouping the expected coordinates of the expected particle centers into cluster centers.

Calculating particle count based on number of cluster centers

Calculating a particle count based on the number of cluster centers.

Acquiring (x, y) coordinates corresponding to particle centers from video frames

Obtaining a set of (x, y) coordinates corresponding to particle centers in video data of a set of particles within a fluid, the video data comprising a sequence of image frames, and each set of (x, y) coordinates corresponding to an image frame of the sequence of image frames.

Using a flow cell and lens-free image sensor for holographic video capture

A flow cell including a fluid passage; a lens-free image sensor for obtaining a holographic image of a fluid in the fluid passage.

Computing a particle count from transformed and clustered expected coordinates in a processor

A processor in communication with the image sensor, the processor programmed to capture video data of particles within the fluid using the image sensor, obtain a set of (x, y) coordinates corresponding to particle centers in the video data, transform coordinates of each particle center of each image frame to expected coordinates of a respective expected particle center in a common image frame, group the expected coordinates of the expected particle centers into cluster centers, and calculate a particle count based on the number of cluster centers.

Storing the coordinate-transforming and clustering particle-counting program in a non-transitory medium

A non-transitory computer-readable medium having stored thereon a computer program for instructing a computer to obtain (x, y) coordinates corresponding to particle centers in video data, transform coordinates of each particle center of each image frame to expected coordinates in a common image frame, group the expected coordinates into cluster centers, and calculate a particle count based on the number of cluster centers.

The independent claims jointly cover obtaining (x, y) coordinates for particle centers from video frames, transforming each particle-center coordinate set to expected coordinates in a common image frame, grouping the expected coordinates into cluster centers, and calculating a particle count based on the number of cluster centers; the system claim further specifies a flow cell with a lens-free image sensor for holographic image acquisition, and the medium claim specifies a stored computer program.

Stated Advantages

Not explicitly described in patent.

Documented Applications

Not explicitly described in patent.

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.