# US 2013/0259345 A1 · Computer aided diagnostic system incorporating shape analysis for diagnosing malignant lung nodules

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

- Number: US 2013/0259345 A1
- Document ID: US20130259345A1
- Status: Published application
- Kind: A1
- Application number: 13/833,333
- Filed: 2013-03-15
- Published: 2013-10-03
- Earliest claimed: 2012-03-30
- Assignees: University of Louisville Research Foundation, Inc.
- Applicants: University of Louisville Research Foundation, Inc.
- Inventors: Ayman S. El-Baz; Matthew Nitzken
- Web page: https://patentgrep.com/patent/US20130259345A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20081: Training; Learning
- G06T 2207/30064: Lung nodule
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A computer aided diagnostic system and automated method diagnose lung cancer through modeling and analyzing the shape of pulmonary nodules. A model used in such analysis describes the shape of pulmonary nodules in terms of spherical harmonics required to delineate a unit sphere corresponding to the pulmonary nodule to a model of the pulmonary nodule.

## Claims

### Claim 1

A method of classifying a pulmonary nodule, the method comprising:
receiving image data associated with a chest scan;
segmenting image data associated with lung tissue from the image data associated with the chest scan;
equalizing the segmented image data;
segmenting image data associated with a pulmonary nodule from the equalized and segmented image data;
generating a three dimensional (3D) mesh model of the segmented pulmonary nodule;
mapping the 3D mesh model to a corresponding unit sphere;
computing a number of spherical harmonics required to delineate the unit sphere to the 3D mesh model; and
classifying the pulmonary nodule as malignant or benign using a learned shape model based at least in part on the computed number of spherical harmonics required to delineate the unit sphere to the 3D mesh model.

### Claim 2 (depends on 1)

The method of claim 1, wherein mapping the 3D mesh model to the corresponding unit sphere includes rearranging a plurality of mesh nodes of the 3D mesh model such that each mesh node of the plurality is a substantially equal distance from a center point of the 3D mesh model.

### Claim 3 (depends on 2)

The method of claim 2, wherein mapping the 3D mesh model to the corresponding unit sphere includes rearranging the plurality of mesh nodes such that all mesh nodes are substantially equally distant from each neighboring mesh node.

### Claim 4 (depends on 1)

The method of claim 1, further comprising determining an error value between the delineated unit sphere and the 3D mesh model for each spherical harmonic, wherein classifying the pulmonary nodule is based at least in part on the determined error value for each spherical harmonic.

### Claim 5

A method for classifying an anatomical structure, the method comprising:
processing image data including image data associated with an anatomical structure to generate segmented image data for the anatomical structure;
generating a three dimensional (3D) model of the anatomical structure based on the segmented image data;
using at least one processor, performing shape analysis of the three dimensional model; and
classifying the anatomical structure based on the shape analysis of the three dimensional model.

### Claim 6 (depends on 5)

The method of claim 5, wherein the anatomical structure is a nodule, and wherein performing shape analysis classifies the nodule as malignant or benign.

### Claim 7 (depends on 6)

The method of claim 6, wherein the nodule is a pulmonary nodule, and wherein the image data comprises a low dose computed tomography (LDCT) chest scan.

### Claim 8 (depends on 7)

The method of claim 7, wherein processing the image data includes segmenting image data associated with lung tissue from image data associated with the chest scan.

### Claim 9 (depends on 8)

The method of claim 8, wherein processing the image data further comprises equalizing the segmented image data associated with the lung tissue.

### Claim 10 (depends on 9)

The method of claim 9, wherein processing the image data further comprises segmenting image data associated with a pulmonary nodule from the equalized and segmented image data associated with the lung tissue.

### Claim 11 (depends on 5)

The method of claim 5, wherein performing shape analysis of the 3D model includes performing spherical harmonic shape analysis of the 3D model.

### Claim 12 (depends on 11)

The method of claim 11, wherein performing spherical harmonic shape analysis includes computing a number of spherical harmonics required to delineate a unit sphere to the 3D model.

### Claim 13 (depends on 12)

The method of claim 12, wherein performing spherical harmonic shape analysis includes mapping the 3D model to the unit sphere prior to computing the number of spherical harmonics.

### Claim 14 (depends on 13)

The method of claim 13, wherein mapping the 3D model to the unit sphere includes modifying positions of a plurality of nodes in the 3D model such that each node is a substantially determined unit distance from a center of the anatomic structure and each node is a substantially equal distance from each neighboring node.

### Claim 15 (depends on 14)

The method of claim 14, wherein mapping the 3D model to the unit sphere includes performing an iterative attraction-repulsion algorithm including an attraction step that centers each node with respect to neighboring nodes and a repulsion step that pushes all nodes outward to become evenly spaced after a back-projection onto the unit sphere.

### Claim 16 (depends on 12)

The method of claim 12, wherein the anatomical structure comprises a nodule, and wherein classifying the anatomical structure includes classifying the nodule as malignant or benign based upon the number of spherical harmonics required to delineate the unit sphere to the 3D model.

### Claim 17 (depends on 16)

The method of claim 16, wherein classifying the nodule as malignant or benign uses a learned shape model.

### Claim 18 (depends on 12)

The method of claim 12, wherein computing the number of spherical harmonics includes approximating the 3D model by the unit sphere and a linear combination of spherical harmonics.

### Claim 19 (depends on 12)

The method of claim 12, further comprising determining an error value between the delineated unit sphere and the 3D model for each spherical harmonic, wherein classifying the anatomic structure nodule is based at least in part on the determined error value for each spherical harmonic.

### Claim 20 (depends on 5)

The method of claim 5, wherein the 3D model comprises a 3D mesh model of a surface of the anatomical structure.

### Claim 21

An apparatus, comprising:
at least one processor; and
program code configured upon execution by the at least one processor to classify an anatomical structure by:
processing image data including image data associated with an anatomical structure to generate segmented image data for the anatomical structure;
generating a three dimensional (3D) model of the anatomical structure based on the segmented image data;
performing shape analysis of the three dimensional model; and
classifying the anatomical structure based on the shape analysis of the three dimensional model.

### Claim 22

A program product, comprising:
a computer readable medium; and
program code stored on the computer readable medium and configured upon execution by at least one processor to classify an anatomical structure by:
processing image data including image data associated with an anatomical structure to generate segmented image data for the anatomical structure;
generating a three dimensional (3D) model of the anatomical structure based on the segmented image data;
performing shape analysis of the three dimensional model; and
classifying the anatomical structure based on the shape analysis of the three dimensional model.
