Method to combine brightfield and fluorescent channels for cell image segmentation and morphological analysis using images obtained from imaging flow cytometer (IFC)

Patent metadata

Field	Value
Publication number	US-10846509-B2
Application number	US-201716097568-A
Country	US
Kind code	B2
Filing date	Jun 5, 2017
Priority date	Jun 10, 2016
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

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.

First claim

What is claimed is:

1. 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 computer processor, which executes a classifier engine 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 graph cut segmentation to the one image in a manner that generates improved image data of the one image, wherein the improved image data is improved by 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

a display screen rendering indications of the identified cell morphology and/or cell type classification from the classifier engine.

2. The cell classification system of claim 1 wherein the one image is a brightfield image and the other images are fluorescent images of different fluorescent channels.

3. The cell classification system of claim 2 wherein the step (B) of improving accuracy of location of cell parts in the brightfield image iteratively applies (i) through (iii) to each of the different fluorescent images.

4. The cell classification system of claim 1 wherein the classifier engine classifies cell types including any one or more of: sperm cells having disorders, sickle cells, cancer cells, and other cells indicative of disease or health disorder.

5. The cell classification system of claim 1 wherein the display screen is a computer display monitor.

6. The cell classification system of claim 1 wherein the classifier engine classifies defective sperm cells, and the display screen renders an indication of infertility.

7. The cell classifier of claim 6 wherein the classification engine classifies a defective sperm cell by automatically identifying one or more of: presence of cytoplasmic droplets, occurrence of Distal Midpiece Reflex (DMR), and shape of sperm head.

8. 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 graph cut segmentation to the one image in a manner that generates improved image data of the one image, wherein the improved image data is improved by 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.

9. The method of claim 8 wherein the one image is a brightfield image and the other images are fluorescent images of different fluorescent channels.

10. The method of claim 9 wherein the step (B) of improving accuracy of location of cell parts in the brightfield image iteratively applies (i) through (iii) to each of the different fluorescent images.

11. The method of claim 8 wherein the reprocessing classifies cell types including one or more of: sperm cells having disorders, sickle cells, cancer cells, and other cells indicative of disease or health disorder.

12. The method of claim 8 wherein the output indication is a diagnostic test result indicator.

13. The method of claim 8 wherein the responsively processing includes classifying defective sperm cells; and
the outputting renders an indication of infertility.

14. The method of claim 13 wherein the classifying a defective sperm cell includes the digital processor automating identification of one or more of: presence of cytoplasmic droplets, occurrence of Distal Midpiece Reflex (DMR), and shape of sperm head.

Assignees

• Luminex Corp

Inventors

• Li Alan
• Vaidyanathan Shobana

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06V2201/03

  Recognition of patterns in medical or anatomical images · CPC title

• G06V20/695

  Preprocessing, e.g. image segmentation · CPC title

• G06V20/693

  Acquisition · CPC title

• G06V20/698 Primary

  Matching; Classification · CPC title