Plaque detection method for imaging of cells

Patent metadata

Field	Value
Publication number	US-12482098-B2
Application number	US-202218275171-A
Country	US
Kind code	B2
Filing date	Feb 1, 2022
Priority date	Feb 1, 2021
Publication date	Nov 25, 2025
Grant date	Nov 25, 2025

Abstract

A plaque detection method and apparatus wherein at least one processor is programmed to receive above focus images to detect the presence of live cells without detecting the lysed cell materials, receive below focus images wherein virtual dark regions exist which are similar to cell shadows as seeds in a segmentation process and use contours around each resulting shape to obtain a subset that are more likely to be part of the cell population to define a cell map. A distance map is created in which each pixel value is the distance of that pixel from the nearest pixel of the cell map and the distance map is thresholded to create a first image of the places which are relatively far from the cells a second image with a smaller distance threshold to get an image that mimics the edges of the cells.

First claim

What is claimed is:

1 . A plaque detection method, comprising the steps of:
using above focus images to detect the presence of live cells without detecting the lysed cell materials; using below focus images wherein virtual dark regions exist which are similar to cell shadows as seeds in a segmentation process; using contours around each resulting shape to obtain a subset that are more likely to be part of the cell population to define a cell map; creating a distance map in which each pixel value is the distance of that pixel from the nearest pixel of the cell map; thresholding the distance map to create a first image of the places which are relatively far from the cells; and creating a second image with a smaller distance threshold to get an image that mimics the edges of the cells.

2 . The method according to claim 1 , further comprising applying a localized adaptive threshold process to the above focus images to produce a map of spots where intensity has concentrated.

3 . The method according to claim 1 , further comprising using parameters of shape and size to filter these contours to a subset that are more likely to be part of the cell population.

4 . The method according to claim 1 , further comprising rendering the contours that remain onto an image and detect regions that are empty.

5 . The method according to claim 1 , further comprising using the first image as a set of seeds for an additional application of a watershed algorithm and using the second image as the topography.

6 . A plaque detection apparatus, comprising the at least one processor programmed to receive above focus images to detect the presence of live cells without detecting the lysed cell materials; receiving below focus images wherein virtual dark regions exist which are similar to cell shadows as seeds in a segmentation process; using contours around each resulting shape to obtain a subset that are more likely to be part of the cell population to define a cell map; creating a distance map in which each pixel value is the distance of that pixel from the nearest pixel of the cell map; thresholding the distance map to create a first image of the places which are relatively far from the cells; and creating a second image with a smaller distance threshold to get an image that mimics the edges of the cells.

7 . The apparatus according to claim 6 , wherein the at least one processor applies a localized adaptive threshold process to the above focus images to produce a map of spots where intensity has concentrated.

8 . The apparatus according to claim 6 , wherein the at least one processor uses parameters of shape and size to filter these contours to a subset that are more likely to be part of the cell population.

9 . The apparatus according to claim 6 , wherein the at least one processor renders the contours that remain onto an image and detect regions that are empty.

10 . The apparatus according to claim 6 , wherein the at least one processor uses the first image as a set of seeds for an additional application of a watershed algorithm and uses the second image as the topography.

11 . A plaque detection method, comprising the steps of:
using above focus images to detect the presence of live cells without detecting the lysed cell materials; applying a localized adaptive threshold process to the images to produce a map of spots where intensity has concentrated; using below focus images wherein virtual dark regions exist which are similar to cell shadows; using bright spots in the below focus images as seeds in a segmentation process; defining contours around each resulting shape; using parameters of shape and size to filter these contours to a subset that are more likely to be part of the cell population; rendering the contours that remain onto an image and detect regions that are empty; creating a distance map in which each pixel value is the distance of that pixel from the nearest pixel of the cell map; thresholding the distance map to create a first image of the places which are relatively far from the cells; creating a second image with a smaller distance threshold to get an image that mimics the edges of the cells; using the first image as a set of seeds for an additional application of a watershed algorithm; and using the second image as the topography.

Assignees

• Thrive Bioscience Inc

Inventors

• Chapman Kenneth
• Evans Frank

Classifications

• G06V20/69

  Microscopic objects, e.g. biological cells or cellular parts · CPC title

• G06T2207/30024

  Cell structures in vitro; Tissue sections in vitro · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G01N15/149

  specially adapted for sorting particles, e.g. by their size or optical properties · CPC title

• G01N15/1433

  using image recognition · CPC title