# US 2019/0318197 A1 · Method and system for abnormal tissue detection using z-scores in a joint histogram

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

- Number: US 2019/0318197 A1
- Document ID: US20190318197A1
- Status: Published application
- Kind: A1
- Application number: 15/952,278
- Filed: 2018-04-13
- Published: 2019-10-17
- Earliest claimed: 2018-04-13
- Assignees: Siemens Healthcare GmbH
- Applicants: Siemens Healthcare GmbH
- Inventors: TOM HILBERT; TOBIAS KOBER; GIAN FRANCO PIREDDA
- Web page: https://patentgrep.com/patent/US20190318197A1

## CPC

- G06T 7/0014: {using an image reference approach}
- G06T 7/11: Region-based segmentation
- G06T 7/174: involving the use of two or more images
- G06V 10/758: {Involving statistics of pixels or of feature values, e.g. histogram matching}
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/20128: Atlas-based segmentation
- G06T 2207/30016: Brain
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Organ tissue properties of a patient are automatically compared with organ tissue properties of a healthy subject group. A population norm for the organ tissue properties is determined by: selecting at least two different tissue properties of the organ; determining for each tissue property previously selected and for each subject of said group a quantitative tissue property map; for each subject of the group, calculating a joint histogram from all the quantitative tissue property maps obtained for said subject; and determining an averaged joint histogram from all subjects of the healthy group, thus defining the population norm. A comparison is automatically performed of the averaged joint histogram with a patient joint histogram obtained for the organ tissue properties of the patient, by calculating a statistical deviation of values of a patient joint histogram relative to values of the averaged joint histogram, and mapping the statistical deviation to the patient organ.

## Claims

### Claim 1

A method for automatically comparing organ tissue properties of a patient with corresponding organ tissue properties of a group of healthy subjects, the method comprising the following steps:
determining a population norm for the organ tissue properties by:
a) selecting at least two different tissue properties of the organ to be investigated;
b) determining for each tissue property previously selected and for each subject of said group a quantitative tissue property map;
c) for each subject of the group, calculating a joint histogram from all the quantitative tissue property maps obtained for said subject;
d) normalizing each previously calculated joint histogram;
e) determining an averaged joint histogram by averaging the normalized joint histograms across all subjects of the healthy group, wherein said averaged joint histogram defines said population norm;
automatically performing a comparison of the averaged joint histogram with a patient joint histogram obtained for the organ tissue properties of the patient, wherein the patient joint histogram is obtained through the following steps:
b1) determining for each tissue property selected in step a) a quantitative tissue property map for the patient organ; and
c1) calculating a joint histogram from all the quantitative tissue property maps obtained for the organ of said patient;
d1) normalizing the previously calculated joint histogram; and
wherein the comparison is obtained by calculating a statistical deviation of values of the patient joint histogram with respect to values of the averaged joint histogram and mapping the statistical deviation to the patient organ.

### Claim 2 (depends on 1)

The method according to claim 1, wherein calculating the joint histogram comprises:
determining for each subject of said group and for each quantitative tissue property map obtained for said subject a total volume of said organ;
dividing said total volume into voxels wherein each voxel is associated to a quantitative value for the tissue property of the quantitative tissue property map;
dividing the quantitative values of each of the quantitative tissue property maps into bins;
for each bin, counting the number of voxels lying within said bin in order to create the joint histogram.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the step of normalizing each previously calculated joint histogram comprises dividing each bin of the joint histogram by the total number of voxels comprised within the total volume of said organ.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the step of normalizing each previously calculated joint histogram comprises dividing each bin of the joint histogram by the total number of voxels comprised within the total volume of said organ.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the calculated statistical deviation is a z-score calculated from the averaged joint histogram and the patient joint histogram, and the method comprises mapping the z-score to the patient organ.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the step of mapping the z-score to the patient organ comprises:
pairing all voxels in the image domain of the patient organ with a corresponding bin in the patient joint histogram domain according to voxel intensity; and
assigning to each voxel the z-score from the bin it belongs to in order to build a z-score map in the image domain.

### Claim 7

An imaging system configured for automatically comparing organ tissue properties of a patient with corresponding organ tissue properties of a group of healthy subjects, the imaging system comprising:
a processor and an accessible memory, the imaging system being configured to:
determine a population norm for said organ tissue properties by:
a) selecting at least two different tissue properties of the organ to be investigated;
b) determining for each tissue property previously selected and for each subject of said group a quantitative tissue property map;
c) for each subject of the group, calculating a joint histogram from all the quantitative tissue property maps obtained for said subject;
d) normalizing each previously calculated joint histogram; and
e) determining an averaged joint histogram by averaging the normalized joint histograms across all subjects of the healthy group, wherein said averaged joint histogram defines said population norm;
automatically perform a comparison of the averaged joint histogram with a patient joint histogram obtained for the organ tissue properties of the patient, wherein, for determining the patient joint histogram, the imaging system is configured for:
b1) determining for each tissue property selected in step a) a quantitative tissue property map for the patient organ; and
c1) calculating a joint histogram from all the quantitative tissue property maps obtained for the organ of said patient;
d1) normalizing the previously calculated joint histogram; and
and wherein the comparison is obtained by calculating a statistical deviation of values of the patient joint histogram with respect to values of the averaged joint histogram and mapping said statistical deviation to the patient organ.

### Claim 8 (depends on 7)

The imaging system of claim 7, configured for calculating the joint histogram by:
determining for each subject of said group and for each quantitative tissue property map obtained for said subject a total volume of said organ;
dividing said total volume into voxels wherein each voxel is associated to a quantitative value for the tissue property of the quantitative tissue property map;
dividing the quantitative values of each of the quantitative tissue property maps into bins;
for each bin, counting the number of voxels lying within said bin in order to create the joint histogram.

### Claim 9 (depends on 7)

The imaging system of claim 7, configured for dividing each bin of the joint histogram by a total number of voxels comprised within the total volume of said organ in order to normalize each previously calculated joint histogram.

### Claim 10 (depends on 7)

The imaging system of claim 7, configured for calculating a z-score from the averaged joint histogram and the patient joint histogram, and mapping the z-score to the patient organ.

### Claim 11 (depends on 1)

A non-transitory computer-readable medium encoded with executable instructions that, when executed, cause one or more imaging systems to perform the method according to claim 1.