# US 2023/0410293 A1 · Quality maps for optical coherence tomography angiography

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

- Number: US 2023/0410293 A1
- Document ID: US20230410293A1
- Status: Published application
- Kind: A1
- Application number: 18/035,492
- Filed: 2021-11-29
- Published: 2023-12-21
- Earliest claimed: 2020-11-30
- Assignees: Carl Zeiss Meditec AG
- Applicants: Carl Zeiss Meditec, Inc.; Carl Zeiss Meditec AG
- Inventors: LUIS DE SISTERNES
- Web page: https://patentgrep.com/patent/US20230410293A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 7/40: Analysis of texture (depth or shape recovery from texture G06T7/529)
- G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30041: Eye; Retina; Ophthalmic
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- G06T 2207/30168: Image quality inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system, method, and/or device for determinizing a quality measure of OCT structural data and/or OCTA functional data uses a machine learning model trained to provide a single overall quality measure, or a quality map distribution for the OCT/OCTA data based on the generation of multiple features maps extracted from one or more slab views of the OCT/OCTA data. The extracted feature maps may be different texture-type maps, and the machine model is trained to determine the quality measure based on the texture maps.

## Claims

### Claim 1

A method for generating a quality measure of optical coherence tomography (OCT) data, comprising:
acquiring a volume of OCT data;
defining one or more slab views from the volume OCT data;
generating a plurality of feature maps from each slab view;
determining the quality measure based on image properties of the plurality of feature maps;
displaying the quality measure or storing the quality measure for further processing.

### Claim 2 (depends on 1)

The method of claim 1, wherein a plurality of said slab views are defined.

### Claim 3 (depends on 1)

The method of claim 1, wherein each slab view is a frontal, planar view of a sub-volume of the volume of OCT data.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining the quality measure includes submitting the plurality of feature maps to a machine model trained using a plurality of pre-graded OCT data volume samples, one or more training slab view defined per OCT data volume sample, and a plurality of training feature maps generated from each training slab view.

### Claim 5 (depends on 4)

The method of claim 4, wherein the machine model is a deep learning model.

### Claim 6 (depends on 4)

The method of claim 4, wherein the machine model is a neural network model.

### Claim 7 (depends on 1)

The method of claim 1, wherein the image properties of the feature maps include image texture features.

### Claim 8 (depends on 1)

The method of claim 1, wherein the image properties of the feature maps include Haralick features.

### Claim 9 (depends on 1)

The method of claim 1, wherein the OCT data is OCT angiography data.

### Claim 10 (depends on 1)

The method of claim 1, wherein the quality measure is a two-dimensional (2D) quality map identifying a quality measure for different regions of its corresponding slab view.

### Claim 11 (depends on 10)

The method of claim 10, wherein acquiring a volume of OCT data includes:
a) collecting a plurality of different OCT volume samples of the same retinal tissue region;
b) applying to each of the OCT volume samples the steps of defining one or more slab views, generating the plurality of feature maps, and determining the quality measure based on the plurality of feature maps, whereby a plurality of 2D quality map samples corresponding to the plurality of different OCT volume samples are defined; and
the method further comprises:
defining composite OCT data based on the higher quality regions of the plurality of different OCT volume samples based on their respective 2D quality map samples.

### Claim 12 (depends on 10)

The method of claim 10, wherein:
determining the quality measure includes submitting the plurality of feature maps to a machine model trained to determine the quality maps based on the plurality of feature maps; and
the machine model is further trained to identify one or more causes of a quality region within the quality map having a lower quality measure than a predefined threshold, and identifying one or more corrective actions to improve the lower quality measure in a subsequent OCT acquisition.

### Claim 13 (depends on 12)

The method of claim 12 wherein the one or more causes are selected from a predefined list of error-sources including one or more of incorrect focusing, opacities, illumination below a predefined threshold, light penetration less than a predefined threshold, tracking or motion artifacts, and noise above a predefined threshold.

### Claim 14 (depends on 12)

The method of claim 12, wherein the one or more corrective actions include a focus adjustment, a recommendation for pupil dilation, identifying an alternate imaging angle, or identifying possible cause of loss of eye tracking.

### Claim 15 (depends on 12)

The method of claim 12, wherein the corrective action is output to an electronic display.

### Claim 16 (depends on 12)

The method of claim 12, wherein the corrective action is transferred to an automated sub-system that automatically implements the corrective action prior to the subsequent acquisition.

### Claim 17 (depends on 10)

The method of claim 10, further including defining an overall quality score for the acquisition based at least in part on the average of the individual quality measure distribution of the quality map.

### Claim 18 (depends on 10)

The method of claim 10, wherein the acquisition is an OCTA acquisition defined from a plurality of OCT scans of the same region of the retina, and the method further includes defining an overall quality score for the OCTA acquisition based at least in part on the average of the individual quality measure distribution of the quality maps of the plurality of OCT scans from which the OCTA acquisition is defined.

### Claim 19 (depends on 10)

The method of claim 10, further including, identifying a target region within the acquisition, and designating the entire acquisition as good or bad based on the quality map measures corresponding to the target region.