Image analysis systems and related methods

Patent metadata

Field	Value
Publication number	US-9836839-B2
Application number	US-201615154824-A
Country	US
Kind code	B2
Filing date	May 13, 2016
Priority date	May 28, 2015
Publication date	Dec 5, 2017
Grant date	Dec 5, 2017

Abstract

Embodiments disclosed herein are directed to systems and methods for determining a presence and an amount of an analyte in a biological sample. The systems and methods for determining the presence of an analyte utilize a plurality of images of a sample slide including multiple fields-of-view having multiple focal planes therein. The systems and methods utilize algorithms configured to color and grayscale intensity balance the plurality of images and based thereon determine if the plurality of images contain the analyte therein.

First claim

What is claimed is:

1. A system for determining a presence of an analyte in blood, the system comprising:
at least one memory storage medium configured to store a plurality of images of a sample slide, the plurality of images including,
a plurality of fields-of-view, each including a unique x and y coordinate of the sample slide; and
a plurality of focal planes, each having a unique z coordinate of the sample slide;

at least one processor operably coupled to the at least one memory storage medium, the at least one processor being configured to,
determine and apply a white balance transform to each of the plurality of images effective to produce a plurality of color-corrected images;
determine and apply an adaptive grayscale transform to each of the plurality of images to provide an adaptive grayscale intensity image for each of the plurality of images;
detect and identify one or more candidate objects in the plurality of color-corrected images and the adaptive grayscale intensity images;
extract and score the one or more candidate objects based at least in part on one or more characteristics of the one or more candidate objects, filter the one or more candidate objects based at least in part on the score, and output one or more color-corrected image patches and one or more adaptive grayscale intensity image patches for each filtered candidate object;
extract one or more feature vectors from the color-corrected image patches and the adaptive grayscale intensity image patches and output the one or more feature vectors;
classify each of the one or more feature vectors as corresponding to an artifact or an analyte; and
determine if the feature vectors classified as analytes are above or below a threshold level associated with a positive diagnosis.

2. The system of claim 1 , wherein the at least one memory storage medium includes an image preprocessing module, a candidate object detection module, a feature extraction module, a classification module, and a diagnosis module stored therein as computer readable programs that are executable by the at least one processor.

3. The system of claim 1 , wherein the at least one processor is configured to determine and apply a white balance transform to the plurality of images based at least partially upon a plurality of brightest pixels in the plurality of images.

4. The system of claim 3 , wherein at least one processor is configured to determine the white balance transform from:
a plurality of brightest pixels from a subset of the plurality of images randomly selected such that a probability of a presence of a clear pixel therein is substantially 1;
a calculated standard grayscale intensity of each pixel of the subset of the plurality of images to determine the plurality of brightest pixels in each of the subset of the plurality of images;
a red value R, a green value G, and a blue value B of each of the plurality of brightest pixels;
an average color vector defined by an average color of the plurality of brightest pixels;
a white color vector;
an axis vector that is perpendicular to, and calculated from a cross-product of, both the average color vector and the white color vector; and
an affine transform matrix calculated from the axis vector and an angle between the average color vector and the white color vector.

5. The system of claim 4 , wherein the at least one processor is configured to apply the white balance transform to a color vector of each of the pixels of the plurality of images defined by the R, G, and B value therein, and output the color-corrected images based thereon.

6. The system of claim 1 , wherein the at least one processor is configured to determine and apply an adaptive grayscale transform to the plurality of images and output a plurality of adaptive grayscale intensity images.

7. The system of claim 1 , wherein at least one processor is configured to:
receive as input a plurality of color-corrected images and standard grayscale intensity images;
threshold the standard grayscale intensity images at a dark threshold to detect blobs;
filter at least one of color, area, or shape of one or more detected blobs to locate and identify white blood cell nuclei at high sensitivity and specificity;
output as white blood cell vector data to the memory storage medium, a red value R, a green value G, and a blue value B of one or more pixels from the color-corrected images that contain a white blood cell nuclei therein; and
output as background vector data, to the memory storage medium, a red value R, a green value G, and a blue value B of a plurality of qualified background pixels as determined from a random sampling of pixels that are brighter in grayscale intensity than the dark threshold in the color-corrected images; and
supply the white blood cell vector data and background vector data to a machine learning module stored in the at least one memory storage medium and executed by the at least one processor, the machine learning module configured to determine an adaptive grayscale projection vector.

8. The system of claim 7 , wherein the at least one processor is configured to determine:
the adaptive grayscale transform based upon an adaptive grayscale projection vector, which is based at least in part on a plurality of white blood cell pixels and a plurality of qualified background pixels; and
the adaptive grayscale projection vector using a regression.

9. The system of claim 8 , wherein the at least one processor is configured to calculate and apply an adaptive grayscale intensity to each of the plurality of images effective to provide a plurality of adaptive grayscale intensity images.

10. The system of claim 1 , wherein the at least one processor is configured to determine one or more potential analyte locations based upon one or more of a plurality of color-corrected images or a plurality of adaptive grayscale intensity images.

11. The system of claim 10 , wherein the at least one processor is configured to:
determine which fields-of-view of the plurality of fields-of-view include one or more candidate objects therein;
cluster candidate objects based at least in part on a distance between one or more adjacent candidate objects of the one or more candidate objects in a field-of-view to provide a candidate object cluster defined by one or more adjacent candidate objects therein;
determine a focal plane having a best focus score for each of the one or more candidate objects;
output a score for each of the one or more candidate object based at least in part on one or more characteristics of each of the one or more candidate objects, the one or more characteristics including at least one of area, grayscale intensity, shape, or color; and
filter the one or more candidate objects based at least in part on the score of the one or more characteristics.

12. The system of claim 11 , wherein the at least one processor is configured to filter the one or more candidate objects by comparing the score of one or more characteristics of the one or more candidate objects to a threshold score for each of the one or more characteristics, output the one or more candidate objects with a score above the threshold score as potential analyte locations, and reject the one or more candidate objects with a score below the threshold score.

13. The system of claim 12 wherein the at least one processor is configured to determine a threshold score based upon attributes of ground truth objects trained into the at least one memory storage medium and accessed by the at least one processor.

14. The system of claim 1 , wherein the at least one processor is configured to receive as i

Assignees

• Tokitae Llc

Inventors

• Champlin Cary Richard
• Delahunt Charles
• Horning Matthew P
• Hu Liming
• Mcguire Shawn Keith
• Mehanian Courosh
• Thompson Clay Matthew
• Wilson Benjamin K

Classifications

• G06V10/56

  relating to colour · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06K9/4652

  Physics · mapped topic

• G06K9/00147

  Physics · mapped topic

• G06T2207/30004

  Biomedical image processing · CPC title