Granted Patent B2

US 12,505,645 · App. 17/910,162 · Granted Dec 23, 2025

Inventors: Shawn St. Pierre (Marlborough, MA); Christophe Fraschini (Aix-en-Provence, FR)

Assignee: Hologic, Inc.

G06V10/759G06T7/0014G06T2207/30068G06T2207/30096G06V2201/032

Abstract

Claims (71)

1 . A method of locating of a lesion within a breast, the method comprising:

receiving, at a computing system an indication of a location of a target lesion within the breast on a first image of the breast obtained by a first imaging modality;

recording a first set of location coordinates of the target lesion indicated on the first image;

receiving, at the computing system, a second image of the breast obtained by a second imaging modality;

analyzing, at an artificial intelligence engine operating on the computing system, the first image including the target lesion and the second image to generate a virtual deformable model;

co-registering the first image and the second image into the virtual deformable model;

based on the analysis of the first image and of the second image, determining a probability that the target lesion corresponds to each location of the breast;

generating a probability mapping comprising visual indication of a probability of each location on the breast corresponding to the target lesion;

outputting an indicator of probability for display on a graphical user interface, the indicator comprising the probability mapping;

receiving transmissions in real time from an ultrasound probe indicating its position at the breast;

navigating to a location of the breast based at least in part on the received transmissions and the probability mapping;

receiving a third image associated with the location of the breast, wherein the third image is an ultrasound image; and

analyzing, using the artificial intelligence engine, the third image to generate a confidence score indicating a likelihood that a potential lesion in the third image matches the target lesion in the first image, wherein analyzing the third image comprises:

converting the first set of location coordinates into a second set of location coordinates for use in ultrasound imaging modality;

identifying the potential lesion within the area of the breast corresponding to the second set of location coordinates of the target lesion; and

analyzing, with the artificial intelligence engine, the first image including the target lesion and the third image including the potential lesion to correlate the first image and the third image.

2 . The method of claim 1 , further comprising recording location coordinates of the potential lesion, and wherein analyzing the first image and the second image comprises comparing location coordinates of the target lesion and location coordinates of the potential lesion.

3 . The method of claim 2 , wherein the second set of location coordinates comprise a clock position relative to a nipple of the breast, a depth from a surface of the breast, and a distance from the nipple.

4 . The method of claim 1 , wherein the target lesion and the potential lesion are indicated by receiving a selection on an image of the breast presented on a display of the computing device.

5 . The method of claim 1 , wherein the first imaging modality is digital breast tomosynthesis.

6 . The method of claim 1 , wherein the first imaging modality is magnetic resonance imaging (MRI).

7 . The method of claim 1 , wherein the second imaging modality comprises stereo optical imagery.

8 . The method of claim 1 , wherein analyzing the first image and the third image is performed using an artificial intelligence system trained using a library of digital breast tomosynthesis cases and corresponding diagnostic ultrasound cases.

9 . The method of claim 1 , wherein analyzing the third image comprises comparing form factors of breast tissue surrounding the target lesion and the potential lesion.

10 . The method of claim 1 , wherein the indicator comprises displaying at least one of a shape, a color, a numerical value, and a reference on the second image.

11 . A lesion identification system comprising:

a processing device; and

a memory storing instructions that, when executed by the processing device, facilitate performance of operations, comprising:

accessing an x-ray image of a breast, the x-ray image including an identified lesion indicated with a visual marker;

recording a first set of location coordinates of the identified lesion indicated on the x-ray image;

receiving an optical image of the breast;

analyzing, at an artificial intelligence engine, the x-ray image including the identified lesion and the optical image to generate a virtual deformable model;

co-registering the x-ray image and the optical image into the virtual deformable model;

based on the analysis of the x-ray image and of the optical image, determining a probability that the identified lesion corresponds to each location of the breast;

generating a probability mapping comprising visual indication of a probability of each location on the breast corresponding to the indicated lesion;

outputting an indicator of probability for display on a graphical user interface, the indicator comprising the probability mapping;

receiving transmissions in real time from an ultrasound probe indicating its position at the breast;

navigating to a location of the breast based at least in part on the received transmissions and the probability mapping;

receiving an ultrasound image associated with the location of the breast; and

analyzing, using the artificial intelligence engine, the ultrasound image to generate a confidence score indicating a likelihood that a potential lesion in the ultrasound image matches the identified lesion in the x-ray image, wherein analyzing the ultrasound image comprises:

converting the first set of location coordinates into a second set of location coordinates for use in ultrasound imaging modality;

identifying the potential lesion within the area of the breast corresponding to the second set of location coordinates of the identified lesion;

analyzing, with the artificial intelligence engine, the x-ray image including the identified lesion and the ultrasound image including the potential lesion to correlate the x-ray image and the ultrasound image;

generating the confidence score; and

displaying an output associated with the confidence score on a graphical user interface.

12 . The system of claim 11 , wherein the first set of location coordinates identifies a location of the target lesion while the breast is under compression; wherein the second set of location coordinates identifies a location of the potential lesion while the breast is not under compression.

13 . The system of claim 12 , where the operations further comprise analyzing form factors of the breast tissue surrounding the identified lesion and the potential lesion to generate the confidence score.

14 . The system of claim 11 , wherein the ultrasound image is analyzed using an artificial intelligence lesion classifier of the artificial intelligence engine, the artificial intelligence lesion classifier being trained on digital breast tomosynthesis images and corresponding ultrasound images.

15 . The system of claim 14 , wherein the artificial intelligence lesion classifier analyzes lesions for correlations in one or more of density, stiffness, shape, margins, orientation, texture, pattern, size, and depth within the breast.

16 . The system of claim 11 , wherein the ultrasound image is received from an ultrasound system, the confidence score is communicated to a display in communication with the ultrasound system, and a visual indication of the confidence score is displayed on the display in communication with the ultrasound system as a visual indicator on the ultrasound image.

17 . A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

obtaining data for a target lesion from a data store, wherein the data was obtained with x-ray imaging and includes at least an x-ray image of the target lesion and a first set of location coordinates for a location of the target lesion within a breast;

receiving, at the computing system, an optical image of the breast;

analyzing, at an artificial intelligence engine operating on the computing system, the x-ray image including the target lesion and the optical image to generate a virtual deformable model;

co-registering the x-ray image and the optical image into the virtual deformable model;

based on the analysis of the x-ray image and of the optical image, determining a probability that the target lesion corresponds to each location of the breast;

generating a probability mapping comprising visual indication of a probability of each location on the breast corresponding to the target lesion;

outputting an indicator of probability for display on a graphical user interface, the indicator comprising the probability mapping;

receiving transmissions in real time from an ultrasound probe indicating its position at the breast;

navigating to a location of the breast based at least in part on the received transmissions and the probability mapping;

recording an ultrasound image of the breast associated with the location;

analyzing, using the artificial intelligence engine, the ultrasound image to generate a confidence score indicating a likelihood that a potential lesion in the ultrasound image matches the target lesion in the x-ray image, wherein analyzing the ultrasound image comprises:

converting the first set of location coordinates into a second set of location coordinates for use in ultrasound imaging modality;

identifying a potential lesion within the area of the breast corresponding to the second set of location coordinates of the target lesion;

analyzing, with the artificial intelligence engine, potential lesion to compare the potential lesion to the target lesion and determine a level of confidence that the potential lesion corresponds to the target lesion; and

outputting an indicator of the level of confidence on a graphical user interface.

18 . The non-transitory machine-readable storage medium of claim 17 , wherein the operations further comprise:

recording an image of breast tissue using digital breast tomosynthesis;

receiving an indication on the image of a target lesion within the breast;

determining the first set of location coordinates for the location of the target lesion within the breast; and

saving the indication and the first set of location coordinates of the target lesion in the data store.

Assignments (5)

Continuity (2)

References Cited (400)