# US 2026/0305912 A1 · Medical optical system, data processing system, computer program, and non-volatile computer-readable storage medium

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

- Number: US 2026/0305912 A1
- Document ID: US20260305912A1
- Status: Published application
- Kind: A1
- Application number: 19/708,807
- Filed: 2026-06-15
- Published: 2026-10-08
- Earliest claimed: 2020-04-27
- Assignees: Carl Zeiss Meditec AG
- Applicants: Carl Zeiss Meditec AG
- Inventors: Christoph Hauger; Stefan Saur; Gerald Panitz
- Web page: https://patentgrep.com/patent/US20260305912A1

## CPC

- A61B 1/000094: {extracting biological structures}
- A61B 1/000096: {using artificial intelligence}
- A61B 1/043: {for fluorescence imaging}
- A61B 1/0653: {with wavelength conversion}
- G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A method for determining a position of a tumor in a macroscopic tissue region includes receiving histological images, each representing a different microscopic tissue section of the macroscopic tissue region. An artificial intelligence comprising a trained neural network classifies each microscopic tissue section as representing tumor tissue or healthy tissue, producing a classification result for each section. The method includes generating a macroscopic classification image based on the classification results, wherein an edge of an area in the macroscopic classification image taken up by image regions representing the classification results represents a boundary of the tumor. The method further includes producing an overview image of the macroscopic tissue region and overlaying the macroscopic classification image on the overview image to mark the boundary of the tumor in the overview image.

## Claims

### Claim 1

A method for determining a position of a tumor in a macroscopic tissue region, the method comprising:
receiving, at data processing hardware, histological images, each histological image representing a different microscopic tissue section of the macroscopic tissue region;
classifying, by an artificial intelligence comprising a trained neural network, each microscopic tissue section represented in the histological images as a tissue section representing the tumor or a tissue section representing healthy tissue, resulting in a classification result for each classified microscopic tissue section;
generating, by the data processing hardware, a macroscopic classification image based on the classification results, wherein an edge of an area taken up in the macroscopic classification image by image regions representing the classification results represents a boundary of the tumor;
producing, by the data processing hardware, an overview image of the macroscopic tissue region; and
overlaying, by the data processing hardware, the macroscopic classification image on the overview image to mark the boundary of the tumor in the overview image.

### Claim 2 (depends on 1)

The method of claim 1, wherein classifying each microscopic tissue section is based on at least one of:
a morphology of the microscopic tissue section represented in the respective histological image;
an intensity of fluorescence radiation emitted by the microscopic tissue section represented in the respective histological image;
a decay behavior of the fluorescence radiation emitted by the microscopic tissue section represented in the respective histological image; or
spectral reflection properties of the microscopic tissue section represented in the respective histological image.

### Claim 3 (depends on 1)

The method of claim 1, wherein classifying each microscopic tissue section comprises classifying each microscopic tissue section into one of a plurality of classes, and wherein one class of the plurality of classes represents healthy tissue and remaining classes of the plurality of classes represent different types of tumor tissue.

### Claim 4 (depends on 1)

The method of claim 1, further comprising recording, by an endomicroscope, the histological images, wherein each histological image shows a tissue section having an edge length of 0.5 mm or less and a spatial resolution of 20 μm or better.

### Claim 5 (depends on 4)

The method of claim 4, further comprising scanning, by a scanning device, the macroscopic tissue region with the endomicroscope by displacing a distal end of the endomicroscope along a scanning path.

### Claim 6 (depends on 5)

The method of claim 5, further comprising registering coordinates of sites of the macroscopic tissue region at which the histological images are recorded, wherein generating the macroscopic classification image comprises arranging the image regions representing the classification results based on the registered coordinates.

### Claim 7 (depends on 1)

The method of claim 1, further comprising registering the macroscopic classification image and the overview image to one another by aligning features identifiable in both images.

### Claim 8 (depends on 1)

The method of claim 1, further comprising positioning a treatment system for treating the tumor based on the boundary of the tumor marked in the overview image.

### Claim 9 (depends on 8)

The method of claim 8, wherein positioning the treatment system comprises aligning an irradiation system with a site of the macroscopic tissue region classified as representing the tumor.

### Claim 10 (depends on 8)

The method of claim 8, wherein positioning the treatment system comprises guiding an applicator for local application of therapeutic radiation to a site of the macroscopic tissue region classified as representing the tumor.

### Claim 11

A system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
receiving histological images, each histological image representing a different microscopic tissue section of the macroscopic tissue region;
classifying, by an artificial intelligence comprising a trained neural network, each microscopic tissue section represented in the histological images as a tissue section representing the tumor or a tissue section representing healthy tissue, resulting in a classification result for each classified microscopic tissue section;
generating a macroscopic classification image based on the classification results, wherein an edge of an area taken up in the macroscopic classification image by image regions representing the classification results represents a boundary of the tumor;
producing an overview image of the macroscopic tissue region; and
overlaying the macroscopic classification image on the overview image to mark the boundary of the tumor in the overview image.

### Claim 12 (depends on 11)

The system of claim 11, wherein classifying each microscopic tissue section is based on at least one of:
a morphology of the microscopic tissue section represented in the respective histological image;
an intensity of fluorescence radiation emitted by the microscopic tissue section represented in the respective histological image;
a decay behavior of the fluorescence radiation emitted by the microscopic tissue section represented in the respective histological image; or spectral reflection properties of the microscopic tissue section represented in the respective histological image.

### Claim 13 (depends on 11)

The system of claim 11, wherein classifying each microscopic tissue section comprises classifying each microscopic tissue section into one of a plurality of classes, and wherein one class of the plurality of classes represents healthy tissue and remaining classes of the plurality of classes represent different types of tumor tissue.

### Claim 14 (depends on 11)

The system of claim 11, wherein the operations further comprise recording the histological images, wherein each histological image shows a tissue section having an edge length of 0.5 mm or less and a spatial resolution of 20 μm or better.

### Claim 15 (depends on 14)

The system of claim 14, wherein the operations further comprise scanning the macroscopic tissue region with the endomicroscope by displacing a distal end of the endomicroscope along a scanning path.

### Claim 16 (depends on 15)

The system of claim 15, wherein the operations further comprise registering coordinates of sites of the macroscopic tissue region at which the histological images are recorded, wherein generating the macroscopic classification image comprises arranging the image regions representing the classification results based on the registered coordinates.

### Claim 17 (depends on 11)

The system of claim 11, wherein the operations further comprise registering the macroscopic classification image and the overview image to one another by aligning features identifiable in both images.

### Claim 18 (depends on 11)

The system of claim 11, wherein the operations further comprise causing positioning a treatment system for treating the tumor based on the boundary of the tumor marked in the overview image.

### Claim 19 (depends on 18)

The system of claim 18, wherein positioning the treatment system comprises aligning an irradiation system with a site of the macroscopic tissue region classified as representing the tumor.

### Claim 20 (depends on 18)

The system of claim 18, wherein positioning the treatment system comprises guiding an applicator for local application of therapeutic radiation to a site of the macroscopic tissue region classified as representing the tumor.
