# US 2021/0279870 A1 · Methods, Systems, and Apparatuses for Quantitative Analysis of Heterogeneous Biomarker Distribution

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279870 A1
- Document ID: US20210279870A1
- Status: Published application
- Kind: A1
- Application number: 17/329,966
- Filed: 2021-05-25
- Published: 2021-09-09
- Earliest claimed: 2014-12-03
- Assignees: Ventana Medical Systems, Inc.; Oregon Health & Science University
- Applicants: Ventana Medical Systems, Inc.; Oregon Health & Science University
- Inventors: Michael Barnes; David Chafin; Karl Garsha; Thomas M. Grogan; Esteban Roberts; Benjamin Stevens; Franklin Ventura; Christophe Chefd'hotel; Kandavel Shanmugam; Joe Gray; Damien Ramunno-Johnson; Tothu Tania Vu; Brian J. Druker; Thomas Jacob
- Web page: https://patentgrep.com/patent/US20210279870A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 7/11: Region-based segmentation
- G06T 7/90: Determination of colour characteristics
- G06V 20/698: {Matching; Classification}
- G06F 18/2321: using statistics or function optimisation, e.g. modelling of probability density functions
- G06F 18/23211: with adaptive number of clusters
- G06T 2207/10036: Multispectral image; Hyperspectral image
- G06T 2207/10056: Microscopic image
- G06T 2207/10064: Fluorescence image
- G06T 2207/20032: Median filtering
- G06T 2207/20104: Interactive definition of region of interest [ROI]
- G06T 2207/20152: Watershed segmentation
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06T 2207/30096: Tumor; Lesion
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/56: relating to colour
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Methods, systems, and apparatuses for detecting and describing heterogeneity in a cell sample are disclosed herein. A plurality of fields of view (FOV) are generated for one or more areas of interest (AOI) within an image of the cell sample are generated. Hyperspectral or multispectral data from each FOV is organized into an image stack containing one or more z-layers, with each z-layer containing intensity data for a single marker at each pixel in the FOV. A cluster analysis is applied to the image stacks, wherein the clustering algorithm groups pixels having a similar ratio of detectable marker intensity across layers of the z-axis, thereby generating a plurality of clusters having similar expression patterns.

## Claims

### Claim 1

A system for generating a dataset for use in a cluster analysis, the system comprising one or more processors; and one or more memories coupled to the processor, the one or more memories to store computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
(a) computing a field of view (FOV) sampling grid for each of a plurality of areas of interest (AOI) within obtained image data;
(b) acquiring multi-spectral data and/or hyper-spectral data at single or multiple z-planes for each computed FOV;
(c) unmixing signal data corresponding to one or more detectable markers from the collected multi-spectral data and/or hyper-spectral data for each computed FOV;
(d) identifying FOVs to be compared as a group in the cluster analysis; and
(e) storing selected features of interest of the identified FOVs in the dataset, wherein the features of interested are selected by automatically segmenting the unmixed signals corresponding to the one or more detectable marker signals in each of the selected FOVs.