Breast mapping and abnormality localization

Patent metadata

Field	Value
Publication number	US-12236582-B2
Application number	US-201917279002-A
Country	US
Kind code	B2
Filing date	Sep 24, 2019
Priority date	Sep 24, 2018
Publication date	Feb 25, 2025
Grant date	Feb 25, 2025

Abstract

Systems and methods for locating abnormalities within a breast and generating mappings of structures, such as ducts, within the breast. First imaging data may be acquired for a breast from a first imaging modality and second imaging data for the breast from a second imaging modality. The first imaging data is co-registered with the second imaging data, such that the first imaging data and the second imaging data share a common coordinate space. Based on the second imaging data, a plurality of structures within the breast are mapped to generate a mapping of the plurality of structures. From at least one of the first imaging data or the second imaging data, the abnormality in the breast is located. The mapping of the plurality of structures and the located abnormality in the breast may be concurrently displayed. A statistical analysis of the mapping of the breast structures may also be performed.

First claim

What is claimed is:

1. A method for imaging a breast, the method comprising:
receiving ultrasound image data for a breast scanned with an ultrasound probe;
executing an artificial intelligence image analysis technique to identify one or more anatomical structures of the breast within the ultrasound image data;
removing tissue other than the identified one or more anatomical structures from the ultrasound image data;
generating, from the identified one or more anatomical structures, a model of the one or more structures of the breast, wherein the model comprises one of:
a 3D mapping of the anatomical structures; and
a plurality 2D mapping of the anatomical structures;

analyzing the model of the one or more anatomical structures to determine a statistical correlation between the model of the one or more anatomical structures and data for an aggregation of model of the one or more anatomical structures for other breasts, wherein the analysis of the model of the one or more anatomical structures to determine the statistical correlation comprises:
extracting at least one feature associated with a type of the anatomical structure;
determining whether the extracted at least one feature indicates a likelihood of an abnormality; and
based on the determined statistical correlation, generating a risk assessment for the breast.

2. The method of claim 1 , further comprising:
scanning the breast with the ultrasound probe to generate the ultrasound data;
tracking the location of the ultrasound probe during scanning of the breast; and
providing visual feedback regarding progress of the scanning.

3. The method of claim 1 , wherein the risk assessment indicates whether additional diagnostic procedures should be performed for the breast.

4. The method of claim 1 , the method further comprising training the artificial intelligence image analysis technique using a dataset of image data wherein structures have been previously identified.

5. The method of claim 1 , wherein the one or more anatomical structures are breast ducts.

6. The method of claim 5 , further comprising:
extracting from the generated model, quantitative values at least one of the number of ducts, a regularity pattern for the ducts, or a termination regularity for the ducts; and
wherein the statistical correlation is based on the extracted quantitative values.

7. The method of claim 1 , wherein the one or more anatomical structures are at least one of breast ducts, lobules, lymph nodes, vascular structures, or Cooper's ligaments.

8. The method of claim 1 , wherein the ultrasound data is 3D ultrasound data for the whole breast.

9. The method of claim 1 , further comprising:
executing a second artificial intelligence image analysis technique to identify one or more second anatomical structures of the breast within the ultrasound image data, wherein the second anatomical structures are of a different type than the one or more anatomical structures;
removing tissue other than the identified one or more second anatomical structures from the ultrasound image data;
generating, from the identified one or more second anatomical structures, a second model of the one or more second structures of the breast, wherein the second model comprises one of:
a 3D mapping of the anatomical second structures; and
a plurality 2D mapping of the anatomical second structures.

10. A system for imaging ducts of a breast, the system comprising:
at least one processor; and
memory, operatively connected to the at least one processor, storing instructions that when executed by the at least one processor cause the system to perform a set of operations comprising:
receiving ultrasound image data for a breast scanned with an ultrasound probe;
executing an artificial intelligence image analysis technique to identify one or more anatomical structures of the breast within the ultrasound image data;
removing tissue other than the identified one or more anatomical structures from the ultrasound image data;
generating, from the identified one or more anatomical structures, a model of the one or more structures of the breast, wherein the model comprises one of:
a 3D mapping of the anatomical structures; and
a plurality 2D mapping of the anatomical structures;
comparing the extracted at least one feature to a threshold value, wherein the threshold value is determined based on data for an aggregation of models of the one or more anatomical structures for other breasts; and
based on the comparison of the extracted at least one feature to the threshold value, generating a risk assessment for the breast.

11. The system of claim 10 , wherein the one or more anatomical structures are at least one of breast ducts, lobules, lymph nodes, vascular structures, or Cooper's ligaments.

12. The system of claim 10 , wherein the extracted at least one feature is represented by a quantitative value.

Assignees

• Hologic Inc

Inventors

• St Pierre Shawn
• Harvey Susan

Classifications

• G06T2207/30068

  Mammography; Breast · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/10132

  Ultrasound image · CPC title

• G06T2207/10116

  X-ray image · CPC title

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title