Cell counting
Inventors
CORREIA DE MATOS NOLASCO LAMAS, Francisco • MANUEL DE OLIVEIRA GARCIA DA FONSECA, João • DO ROSÁRIO MAGALHÃES, André • PEDRO SANTOS MANSO CÔRTE-REAL, José • CABECA, Ricardo Manuel Marquest Caleiro
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10684207-B2
Publication Date
2020-06-16
Expiration Date
Abstract
Systems and methods for classifying blood cells in a blood sample are disclosed. A series of frames of the blood sample as it flows through a field of view of an image capture device are captured and analysed. Advantageously, the disclosed systems and methods combine the availability of morphological cell data with the convenience of a flow-through arrangement. The classification results can be used for estimating cell counts in a blood sample.
Core Innovation
The invention provides a method and system for estimating a cell count in a blood sample. The approach captures a sequence of frames of the sample with an image capture device as the sample flows through a field of view, identifies cells in each frame, and determines a frame cell count in each selected frame.
A plurality of frames is selected based on an estimate of cell velocity, where each selected frame is selected based on an estimate of the number of frames needed for all cells identified in the previous selected frame to leave the field of view. The method combines the determined frame cell counts to compute an estimated cell count in a volume corresponding to the field of view.
In some implementations, combining the frame cell counts includes fitting a distribution function to the determined frame cell counts and computing the estimated cell count from the fitted distribution, including using a Gamma distribution. In other implementations, the selection and/or combining is refined by selecting a subset based on frame positions in the sequence and a goodness of fit measure for how well the distribution function fits.
For volume determination used to convert to count per volume, an obstructed area can be detected in the field of view due to a flow obstruction, and the flow volume is determined by correcting an unobstructed volume for a volume associated with the obstructed area. Detecting an obstructed area can include partitioning the field of view into candidate areas and marking a candidate area as obstructed if less than a threshold amount of cells have been identified over the sequence of frames in that candidate area.
Claims Coverage
The provided independent claims are clm-00001, clm-00008, and clm-00009. They define three inventive features covering cell-count estimation from captured frames, obstruction detection, and a system configured to perform the same frame-selection and combining operations.
Velocity-based frame selection for estimating a cell count
Capturing a sequence of frames of the sample as the sample flows through a field of view, identifying cells in each frame, selecting a plurality of frames based on an estimate of cell velocity where each frame is selected based on an estimate of the number of frames needed for all cells identified in the previous selected frame to leave the field of view, determining a frame cell count of identified cells in each selected frame, and combining the determined frame cell counts to compute an estimated cell count.
Obstructed-area detection by thresholded candidate areas
Detecting an obstructed area by partitioning the field of view into candidate areas and marking a candidate area as obstructed if less than a threshold amount of cells have been identified over the sequence of frames in that candidate area.
System configured to combine selected-frame counts to compute an estimated cell count in field-of-view volume
An image capture device with a field of view and an image processor configured to capture a sequence of frames as the sample flows through the field of view, identify cells in each frame, select a plurality of frames based on an estimate of cell velocity where each frame is selected based on an estimate of the number of frames needed for all cells identified in the previous selected frame to leave the field of view, determine a frame cell count of identified cells in each selected frame, and combine the determined frame cell counts to compute an estimated cell count in a volume corresponding to the field of view.
Across the independent claims, the core coverage is the velocity-based selection of captured frames to count, followed by combining selected-frame counts to estimate a cell count, with an obstruction-detection option using partitioned candidate areas and a threshold condition.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?