# US 8,275,186 B2 · Method and apparatus for setting a detection threshold in processing medical images

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

- Number: US 8,275,186 B2
- Document ID: US8275186B2
- Status: Granted
- Kind: B2
- Application number: 11/344,838
- Filed: 2006-01-31
- Published: 2007-08-02
- Granted: 2012-09-25
- Earliest claimed: 2006-01-31
- Assignees: Hologic, Inc.
- Inventors: Philippe Raffy
- Web page: https://patentgrep.com/patent/US8275186B2

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- G16H 40/63: for local operation
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/10072: Tomographic images
- G06T 2207/10116: X-ray image
- G06T 2207/30064: Lung nodule
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

An intuitive user interface is provided that allows for selection of an abnormality level in features in a medical image on the basis of graphical depictions of the abnormalities themselves. In one embodiment, the user interface displays realistic images of actual abnormalities in a series ranging from least severe to most severe and the medical practitioner selects the abnormality level by mouse-clicking on one of the images. The user interface then displays an annotated map of suspected abnormalities with annotations only on those suspected abnormalities that are at least as severe as the selected abnormality. In alternative embodiments, the user interface displays stylized images of the abnormalities plotted by the display using mathematical functions. In yet another alternative, the images are hand-drawn images.

## Claims

### Claim 1

A method for determining a threshold for display of regions of interest, the threshold used by a computer aided detection device for analysis of medical images and the method operating on a computer having a display for displaying the medical images, the method comprising:
displaying a plurality of images on the display, each of the images having a different
abnormality selected from a range of different abnormalities that may be observed in an anatomical image on the display,
receiving, from a user interface, a selection of one of the images and an associated selected abnormality, and
displaying, in response to said selected image and associated selected abnormality, an anatomical image in which abnormalities less severe than the selected abnormality are not annotated.

### Claim 2 (depends on 1)

The method of claim 1 wherein the abnormalities in the anatomical image are scored to produce a set of scores, said method further comprising:
establishing a threshold having a value that depends on the abnormality of the selected image; and
comparing each score of the set of scores with the threshold to determine which abnormalities to annotate.

### Claim 3 (depends on 1)

The method of claim 1 wherein the images are images of actual abnormalities.

### Claim 4 (depends on 1)

The method of claim 1 wherein the images are images of actual abnormalities in lung nodules.

### Claim 5 (depends on 1)

The method of claim 1 wherein the images are representative of abnormalities.

### Claim 6 (depends on 5)

The method of claim 5 wherein the images are generated mathematically.

### Claim 7 (depends on 5)

The method of claim 5 wherein the images are hand-drawn.

### Claim 8

In a system for displaying medical images in which certain abnormalities are annotated, a method comprising:
displaying a plurality of images, each image of the plurality having an abnormality selected from a range of different abnormalities that may be observed in an anatomical image,
receiving, from a user interface, a selection of one of the images having an associated selected abnormality, and
displaying, in response to the selection of the one of the images having the associated selected abnormality, an anatomical image in which abnormalities less severe than the selected abnormality of the selected image are not annotated.

### Claim 9 (depends on 8)

The method of claim 8 further comprising:
scoring the abnormalities in the anatomical image to produce a set of scores;
establishing a threshold having a value that depends on which image is selected; and
comparing each score of the set of scores with the threshold to determine which abnormalities to annotate.

### Claim 10 (depends on 8)

The method of claim 8 wherein the images are images of actual abnormalities.

### Claim 11 (depends on 8)

The method of claim 8 wherein the images are images of actual abnormalities in lung nodules.

### Claim 12 (depends on 8)

The method of claim 8 wherein the images are representative of abnormalities.

### Claim 13 (depends on 12)

The method of claim 12 wherein the images are generated mathematically.

### Claim 14 (depends on 12)

The method of claim 12 wherein the images are hand-drawn.