Methods and systems for determining breast density

• US 10,123,758 B2
• Filed: 02/19/2018
• Issued: 11/13/2018
• Est. Priority Date: 08/20/2013
• Status: Active Grant

• Current Assignee: Densitas Incorporated
• Original Assignee: Densitas Incorporated
• Inventors: Abdolell, Mohamed, Hope, Tyna, Zaboli, Shiva, Tsuruda, Kaitlyn
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US15/898,829
• Publication Number:
  US 20180168531A1
• Time in Patent Office: 267 Days
• Field of Search: 382128, 382129, 382130, 382131, 382132, 382133, 382134, 378 4, 378 8, 378 21- 27, 378 37, 378901, 604 74, 604346, 623 7
• CPC Class Codes: A61B 6/502 for diagnosis of breast, i.e. mammography
• CPC Class Codes: A61B 6/5211 involving processing of medical diagnostic data
• CPC Class Codes: A61B 6/5252 removing objects from field of view, e.g. removing patient table from a CT image
• CPC Class Codes: A61B 6/5258 involving detection or reduction of artifacts or noise
• CPC Class Codes: A61B 6/5294 involving using additional data, e.g. patient information, image labeling, acquisition parameters
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20061 Hough transform
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Various embodiments are described herein for methods, devices and systems that can be used to determine a breast density value from an input image of patient'"'"'s breast. In one example embodiment, the breast density value is calculated by receiving an input image corresponding to the digital mammogram, removing metadata information from the input image to generate an intermediate image, generating a region of interest (ROI) image based on the intermediate image, extracting values for predictor variables based on the metadata information, the intermediate image and the ROI image, and calculating breast density based on the values of the predictor variables. The breast density value is calculated based on a breast density model.

Claims

1. A system for determining a breast density value from a mammogram image of a breast, the system comprising:

a memory unit;

a processing unit that is coupled to the memory unit and controls operation of the system;

an input module that interacts with the memory unit and is configured to receive an input image corresponding to the digital mammogram and remove metadata information from the input image to generate an intermediate image;

a region of interest (ROI) generation module that is configured to generate an ROI image based on the intermediate image;

a breast density model that is developed using a statistical learning algorithm, a machine learning algorithm or regression analysis modelling; and

a breast density measurement module that is configured to extract values for predictor variables from the metadata information, the intermediate image and the ROI image; and

calculate the breast density measurement by providing the values of the predictor variables as inputs to the breast density model.

2. The system of claim 1, wherein the breast density model is trained using measures of breast density values from expert assessment of breast density on a set of training mammogram images comprising at least one of processed raw digital mammogram images and ‘

for presentation’

digital mammogram images that are raw digital mammogram images that have been enhanced for viewing by a human observer.

3. The system of claim 2, wherein the statistical learning algorithm or the machine learning algorithm include one of linear regression, parametric regression models, non-parametric regression models, semi-parametric regression models, multivariate adaptive regression splines, artificial neural networks, classification and regression trees, random forests, support vector machines, random forests, ensemble models and ensemble learning algorithms.

4. The system of claim 2, wherein the system further comprises a display that is coupled to the processing unit and is configured to display a user interface that shows the input image, the intermediate image and the breast density measurement.

5. The system of claim 2, the processing unit is configured to generate a report that contains the breast density measurement and has a format according to one of a DICOM Structured Report (SR), DICOM Secondary Capture (SC), or DICOM Greyscale Softcopy Presentation State (GSPS) and sends the report to one of a (Picture Archiving and Communication System) PACS, an Electronic Medical Record (EMR) system, a mammogram review station, a Hospital Information Technology (HIT) system, a personal computer, and communication devices.

6. The system of claim 2, wherein the intermediate image is processed to generate a pre-ROI image by removing noise from the intermediate image and the ROI image is generated by processing the pre-ROI image by optionally resizing the intermediate image.

7. The system of claim 2, wherein the metadata information that is removed from the input image comprises DICOM header information, and the predictor variables from the metadata information comprise at least one of patient specific parameters, image acquisition device parameters and image acquisition parameters.

8. The system of claim 7, wherein the image acquisition parameters comprise at least one of relative x-ray exposure, exposure duration, laterality, patient orientation and peak kilo-voltage;

the patient specific parameters comprise at least one of age of the patient, gender of the patient, patient date of birth, and patient identification information; and

the image acquisition device parameters comprise at least one of name and model of the device used to obtain the digital mammogram.

9. The system of claim 2, wherein the predictor variables comprise histogram features including at least one of skewness, entropy, maximum between class variance, ninety nine percent index and fifty percent index.

10. The system of claim 2, wherein the predictor variables comprise texture features including at least one of average gradient magnitude value of the intermediate image within the region defined by the non-zero values of the ROI image, an average gradient magnitude value of the intermediate image within a subset of the region defined by the non-zero values of the ROI image, an edge ratio of the intermediate image in the region defined by the non-zero values of ROI image, and an edge ratio of the intermediate image within a subset of the region defined by the non-zero values of ROI image.

11. A method of determining a breast density measurement from a digital mammogram, the method being performed by a processing unit, the method comprising:

receiving an input image corresponding to the digital mammogram;

removing metadata information from the input image to generate an intermediate image;

generating a region of interest (ROI) image based on the intermediate image;

extracting values for predictor variables from the metadata information, the intermediate image and the ROI image; and

calculating the breast density measurement based by providing the values of the predictor variables to a breast density model that is developed using a statistical learning algorithm, a machine learning algorithm or regression analysis modelling.

12. The method of claim 11, wherein the method comprises training the breast density model using measures of breast density values from expert assessment of breast density on a set of training mammogram images comprising at least one of processed raw digital mammogram images and ‘

for presentation’

digital mammogram images that are a raw digital mammogram images that have been enhanced for viewing by a human observer.

13. The method of claim 12, wherein the statistical learning algorithm or the machine learning algorithm include one of linear regression, parametric regression models, non-parametric regression models, semi-parametric regression models, multivariate adaptive regression splines, artificial neural networks, classification and regression trees, random forests, support vector machines, random forests, ensemble models and ensemble learning algorithms.

14. The method of claim 12, wherein the method comprises displaying a user interface that shows the input image, the intermediate image and the breast density measurement.

15. The method of claim 12, wherein the method further comprises generating a report that contains the breast density measurement and has a format according to one of a DICOM Structured Report (SR), DICOM Secondary Capture (SC), or DICOM Greyscale Softcopy Presentation State (GSPS) and sending the report to one of a (Picture Archiving and Communication System) PACS, an Electronic Medical Record (EMR) system, a mammogram review station, a Hospital Information Technology (HIT) system, a personal computer, and communication devices.

16. The method of claim 12, wherein the method comprises processing the intermediate image to generate a pre-ROI image by removing noise from the intermediate image and the ROI image is generated by processing the pre-ROI image by optionally resizing the intermediate image.

17. The method of claim 12, wherein the method comprises removing DICOM header information from the input image and obtaining the values for the predictor variables from the metadata information from at least one of patient specific parameters, image acquisition device parameters and image acquisition parameters.

18. The method of claim 17, wherein the image acquisition parameters comprise at least one of relative x-ray exposure, exposure duration, laterality, patient orientation and peak kilo-voltage;

the patient specific parameters comprise at least one of age of the patient, gender of the patient, patient date of birth, and patient identification information; and

the image acquisition device parameters comprise at least one of name and model of the device used to obtain the digital mammogram.

19. The method of claim 12, wherein the method comprises obtaining the values for the predictor variables from histogram features including at least one of skewness, entropy, maximum between class variance, ninety nine percent index and fifty percent index.

20. The method of claim 12, wherein the method comprises obtaining the values for the predictor variables from texture features including at least one of average gradient magnitude value of the intermediate image within the region defined by the non-zero values of the ROI image, an average gradient magnitude value of the intermediate image within a subset of the region defined by the non-zero values of the ROI image, an edge ratio of the intermediate image in the region defined by the non-zero values of ROI image, and an edge ratio of the intermediate image within a subset of the region defined by the non-zero values of ROI image.