Systems and methods for counting particles

Inventors

Vidal, Rene • HAEFFELE, Benjamin D. • YELLIN, Florence

Assignees

MiDiagnostics NV • Johns Hopkins University

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 positions 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 invention relates to particle counting in a fluid using video data that includes a sequence of image frames. A set of (x, y) coordinates corresponding to particle centers is obtained, where each set of (x, y) coordinates corresponds to an image frame of the sequence. The particle centers are linked between each pair of consecutive image frames by fitting the coordinates to a statistical model of particle displacements.

After linking, for each particle of the set of particles a trajectory is tracked through links in each sequential image frame until that particle is not linked in a next image frame. For each particle, a length of the tracked particle trajectory is calculated, and particle count is calculated based on the length of the tracked particle trajectory of each particle of the set of particles.

In addition, a coordinate transformation approach is described in the document. Particle centers are transformed into a common coordinate frame using a non-linear transform, and transformed centers are clustered such that the cluster centers count equals distinct particles.

Claims Coverage

The partial content provides three independent claims (method, system, and non-transitory computer-readable medium). Across these independent claims, the document consistently ties together inventive elements: obtaining (x,y) coordinates of particle centers from video frames, linking consecutive-frame coordinates using a statistical model of particle displacements, tracking per-particle trajectories until a non-linked event, computing trajectory length, and calculating particle count based on the trajectory length.

Across the independent claims, the core claim scope centers on particle counting by linking particle-center coordinates across consecutive image frames using a statistical model of particle displacements, tracking per-particle trajectories until a non-linked event occurs, computing each trajectory length, and calculating particle count based on the trajectory lengths. The system claim further specifies a flow cell and a lens-free image sensor for obtaining holographic images, and the medium claim specifies execution of the same tracking and counting operations as a computer program.

Stated Advantages

Documented Applications