# US 10,768,403 B2 · Auto-focus methods and systems for multi-spectral imaging

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

- Number: US 10,768,403 B2
- Document ID: US10768403B2
- Status: Granted
- Kind: B2
- Application number: 16/199,286
- Filed: 2018-11-26
- Published: 2019-05-02
- Granted: 2020-09-08
- Earliest claimed: 2013-07-18
- Assignees: Ventana Medical Systems, Inc.
- Applicants: Ventana Medical Systems, Inc.
- Inventors: Joerg Bredno; Jim F. Martin; Anindya Sarkar
- Web page: https://patentgrep.com/patent/US10768403B2

## CPC

- G02B 21/244: {using image analysis techniques}
- G02B 21/006: {focusing arrangements; selection of the plane to be imaged}
- G02B 21/0072: {details concerning resolution or correction, including general design of CSOM objectives}
- G02B 21/008: {Details of detection or image processing, including general computer control}
- G02B 21/367: {providing an output produced by processing a plurality of individual source images, e.g. image tiling, montage, composite images, depth sectioning, image comparison}
- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts
- H04N 23/10: for generating image signals from different wavelengths
- H04N 23/67: Focus control based on electronic image sensor signals
- G02B 21/16: adapted for ultraviolet illumination {; Fluorescence microscopes (G02B21/0076 takes precedence)}
- G06T 2207/10056: Microscopic image
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Techniques for acquiring focused images of a microscope slide are disclosed. During a calibration phase, a “base” focal plane is determined using non-synthetic and/or synthetic auto-focus techniques. Furthermore, offset planes are determined for color channels (or filter bands) and used to generate an auto-focus model. During subsequent scans, the auto-focus model can be used to quickly estimate the focal plane of interest for each color channel (or filter band) rather than re-employing the non-synthetic and/or synthetic auto-focus techniques.

## Claims

### Claim 1

A system for enhancing a focus of an image of a biological specimen, the system comprising (i) one or more processors, and (ii) one or more memories coupled to the one or more processors, the one or more memories to store computer-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
determining an in-focus base focus plane for a first slide position of a microscope slide, wherein the in-focus base plane is determined by running an auto-focus routine on at least one of a gray scale or a color channel slide image of the first slide position;
deriving offset values that provide a best focus plane for each of a plurality of color channels or filter bands for the first slide position, wherein the offset values are derived from a pre-computed auto-focus model;
generating an image for each of the plurality of color channels or filter bands based on the identified offset values and the determined in-focus base focus plane for the first slide position; and
computing a composite image for the first slide position by combining each of the obtained images for each of the plurality of color channels or filter bands.

### Claim 2 (depends on 1)

The system of claim 1, wherein the pre-computed auto-focus model is derived from images acquired from a series of training slides.

### Claim 3 (depends on 2)

The system of claim 2, wherein the pre-computed auto-focus model is generated by deriving training base focus planes and training offset values from the series of training slides.

### Claim 4 (depends on 3)

The system of claim 3, wherein training offset values are derived for each of a plurality of slide positions for each slide in the series of training slides.

### Claim 5 (depends on 4)

The system of claim 4, wherein training offset values are derived for a plurality of color channels or band filters for each of the plurality of slide positions.

### Claim 6 (depends on 2)

The system of claim 2, wherein the pre-computed training model includes information pertaining to a type of biological specimen present on the series of training slides.

### Claim 7 (depends on 6)

The system of claim 6, wherein the offset values that provide the best focus plane for each of a plurality of color channels are derived based on a type of tissue on the microscope slide.

### Claim 8 (depends on 1)

The system of claim 1, wherein the composite image is a combination of a focused red channel image, a focused green channel image, and a focused blue channel image.