US 2019/0163956 A1Published application

A Method To Combine Brightfield And Fluorescent Channels For Cell Image Segmentation And Morphological Analysis Using Images Obtained From Imaging Flow Cytometer (IFC)

AssigneeLuminex Corporation

InventorsAlan Li, Shobana Vaidyanathan

Life of this patent

Estimating the term…

Loading patent…

Abstract

A classifier engine provides cell morphology identification and cell classification in computer-automated systems, methods and diagnostic tools. The classifier engine performs multispectral segmentation of thousands of cellular images acquired by a multispectral imaging flow cytometer. As a function of imaging mode, different ones of the images provide different segmentation masks for cells and subcellular parts. Using the segmentation masks, the classifier engine iteratively optimizes model fitting of different cellular parts. The resulting improved image data has increased accuracy of location of cell parts in an image and enables detection of complex cell morphologies in the image. The classifier engine provides automated ranking and selection of most discriminative shape based features for classifying cell types.

Claims19

Dependent claims

A computer-automated cell classification system comprising:

an imaging flow cytometer acquiring a multispectral plurality of images of a sample cell, the plurality of images being simultaneously acquired across multiple imaging modes, and each of the images of the plurality being spatially well aligned with each other;
a classifier engine executed by a computer processor and coupled to receive the acquired multispectral plurality of images, the classifier engine:
(A) segmenting one of the images of the acquired plurality into components, the one image providing morphology of the sample cell, and the components being formed of image subcomponents representing parts of the sample cell;
(B) improving accuracy of location of cell parts in the one image by:
(i) segmenting other images of the acquired plurality into components corresponding to components segmented from the one image, the other images being of different imaging modes than the one image and each other, and the components segmented from the other images serving as masks of image subcomponents of the one image, (ii) spatially correlating the subcomponent masks generated by the segmented other images to the one image, and using the subcomponent masks as foreground object markers of respective cell parts for the one image, and (iii) applying a graphic cut segmentation to the one image in a manner that generates improved image data of the one image having increased accuracy of location of cell parts;
and
(C) reprocessing the one image resulting from (B) and having the generated improved image data including component masks with relative positions, the reprocessing identifying cell morphology from the one image and thereby classifying cell type of the sample cell;
and
an output unit rendering indications of the identified cell morphology and/or cell type classification from the classifier engine.

6 more elements

A computer-based diagnostic tool for identifying cell morphology and classifying cell type, comprising:

an input assembly providing access to a source of plural multispectral images of a sample cell, the plural images simultaneously acquired by an imaging flow cytometer, and the plural images being spatially well aligned amongst each other;
and
a classifier engine communicatively coupled to the input assembly and receiving the plural multispectral images, the classifier engine being executed by a computer processor and processing the received images by:
(A) segmenting one of the received images into components, the one image providing morphology of the sample cell, and the components being formed of image subcomponents representing parts of the sample cell;
(B) improving accuracy of location of cell parts in the one image by:
(i) segmenting other ones of the received images into components corresponding to components segmented from the one image, the other received images being of different imaging modes than the one image and each other, and the components segmented from the other received images serving as masks of image subcomponents of the one image, (ii) spatially correlating the subcomponent masks generated by the segmented other received images to the one image, and using the subcomponent masks as foreground object markers of respective cell parts for the one image, and (iii) applying a graphic cut segmentation to the one image in a manner that generates improved image data of the one image having increased accuracy of location of cell parts;
and
(C) reprocessing the one image resulting from (B) and having the generated improved image data including component masks with relative positions, the reprocessing identifying cell morphology from the one image and thereby classifying cell type of the sample cell, the classifier engine providing an output indication of the identified cell morphology and/or cell type classification.

5 more elements

A computer-implemented method of identifying cell morphology and classifying cell types, comprising:

using an imaging flow cytometer, acquiring a multispectral plurality of images of a sample cell, the plurality of images being simultaneously acquired across multiple imaging modes, and each of the images of the plurality being spatially well aligned with each other;
in a digital processor, responsively processing the acquired multispectral plurality of images by:
(A) segmenting one of the images of the acquired plurality into components, the one image providing morphology of the sample cell, and the components being formed of image subcomponents representing parts of the sample cell;
(B) improving accuracy of location of cell parts in the one image by:
(i) segmenting other images of the acquired plurality into components corresponding to components segmented from the one image, the other images being of different imaging modes than the one image and each other, and the components segmented from the other images serving as masks of image subcomponents of the one image, (ii) spatially correlating the subcomponent masks generated by the segmented other images to the one image, and using the subcomponent masks as foreground object markers of respective cell parts for the one image, and (iii) applying a graphic cut segmentation to the one image in a manner that generates improved image data of the one image having increased accuracy of location of cell parts;
and
(C) reprocessing the one image resulting from (B) and having the generated improved image data including component masks with relative positions, the reprocessing identifying cell morphology from the one image and thereby classifying cell type of the sample cell;
and
outputting an indication of the identified cell morphology and/or cell type classification.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/097,568Filed 5 Jun 2017
Priority: 10 Jun 2016
Published: 30 May 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G06V 20/698
Microscopic objects, e.g. biological cells or cellular parts: matching; Classification
G01N 15/1433
Signal processing: using image recognition
G06T 7/0012
Inspection of images, e.g. flaw detection: biomedical image inspection
G06T 7/11
Segmentation; Edge detection: region-based segmentation