Image analysis for assessing image data

• US 10,282,838 B2
• Filed: 01/09/2017
• Issued: 05/07/2019
• Est. Priority Date: 01/09/2017
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Nunes, Camila Patricia Bazilio, Magalhaes, Marina Lundgren de Almeida, Ribeiro, Marcelo Blois, Oliveira, Dario Augusto Borges, Silva, Eudemberg Fonseca, De Andrade, Felipe Santos, Blumenthal, Marco, Palma, Giovanni John Jacques, Mueller, Serge Louis Wilfrid
• Primary Examiner(s): Woldemariam, Aklilu K
• Application Number:
  US15/401,884
• Publication Number:
  US 20180197288A1
• Time in Patent Office: 848 Days
• Field of Search: 382128, 382131, 382132, 382276, 382155, 382157, 382168, 382170, 382181, 382203, 382224, 382260
• CPC Class Codes: A61B 6/4405 the apparatus being movable or portable, e.g. handheld or mounted on a trolley
• CPC Class Codes: A61B 6/502 for diagnosis of breast, i.e. mammography
• CPC Class Codes: A61B 6/5258 involving detection or reduction of artifacts or noise
• CPC Class Codes: A61B 6/563 involving image data transmission via a network
• CPC Class Codes: A61B 6/586 Detection of faults or malfunction of the device
• CPC Class Codes: G01T 7/00 Details of radiation-measuring instruments
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS

Abstract

The present approach relates to providing image quality feedback to personnel (e.g., a technician) acquiring non-invasive images in real-time or near real-time. By way of example, the proposed approach may automatically assess the quality of images in real-time by evaluating the images for the presence or absence of non-conformities using processor-implemented, rule-based algorithms running partly or completely in parallel to one another. The proposed approach improves the image analysis pipeline by efficiently providing notification of and/or discarding low-quality or unsuitable images or exams after they are taken, such as in within seconds or minutes.

Claims

1. An imaging system, comprising:

an X-ray source configured to emit X-rays;

a radiation detector configured to generate signals in response to the emitted X-rays incident on a surface of the radiation detector;

data acquisition circuitry configured to use the signals to generate one or more mammographic images that are transmitted directly or indirectly to a remote processing resource configured to execute a plurality of services which each evaluate the one or more images for a different type of non-conformity; and

an operator interface and display configured to execute an application that notifies a technician in real-time or near real-time to determine if a plurality of non-conformities of the one or more mammographic images identified by the remote processing resource includes a predetermined type of non-conformity, wherein the plurality of non-conformities include one or more of;

absence of a breast/chest angle in an MLO view, wherein the MLO is a mediolateral-oblique;

misalignment of a nipple and pectoral muscle in an MLO view, wherein the MLO is a mediolateral-oblique;

non-centered nipple in a CC view, wherein the CC is a center-caudal;

and absence of pectoral muscle in the CC view, wherein the CC is a center-caudal.

2. The imaging system of claim 1, wherein the imaging system comprises a mammography imaging system.

3. The imaging system of claim 1, wherein the remote processing resource comprises a cloud-based resource.

4. The imaging system of claim 1, wherein the one or more images are transmitted to the remote processing resource via a picture archiving and communication system intermediary.

5. The imaging system of claim 1, wherein the identified non-conformities are displayed in less than 1 minute from the time a respective image is acquired.

6. The imaging system of claim 1, wherein the identified non-conformities are displayed while a patient is still at a site of the imaging system.

7. An image analysis architecture, comprising:

an X-ray source configured to emit X-rays;

a radiation detector configured to generate signals in response to the emitted X-rays incident on a surface of the radiation detector;

a data acquisition circuitry configured to use the signals to generate one or more mammographic image files;

an application interface configured to be displayed at the site of an imaging system and to facilitate the transfer of die one or more mammographic image files to a remote processing resource; and

a plurality of services executable on the remote processing resource, wherein at least a portion of the services are configured to execute in parallel and wherein each service is configured to analyze the one or more mammographic image files for a respective type from a plurality of non-conformities and to provide a notification to a technician in real-time or near real-time via the application interface to determine based on a threshold if a pre-determined type of non-conformity is identified, wherein the plurality of non-conformities include one or more of;

absence of a breast/chest angle in an MLO view, wherein the MLO is a mediolateral-oblique;

misalignment of a nipple and pectoral muscle in an MLO view, wherein the MLO is a mediolateral-oblique;

non-centered nipple in a CC view, wherein the CC is a center-caudal;

and absence of pectoral muscle in the CC view, wherein the CC is a center-caudal.

8. The image analysis architecture of claim 7, wherein the remote processing resource comprises a cloud-based resource.

9. The image analysis architecture of claim 8, wherein the cloud-based resource comprises one or more application servers.

10. The image analysis architecture of claim 7, wherein the plurality of non-conformities include one or more of:

bad pixels, line artifacts, or components of the imaging system shown in the image.

11. A method for remotely assessing image quality, comprising:

emitting X-rays using an X-ray source;

generating signals using a radiation detector in response to the emitted X-rays incident on a surface of the radiation detector;

receiving an image of a patient or object using the signals generated at a site of an imaging system, wherein the image comprises mammographic images;

processing the image using a plurality of image quality analysis services, at least a portion of which execute in parallel, wherein the image quality service analytics are executed on a network-based architecture physical remote form the site of the imaging system;

transmitting one or more notifications of a plurality of non-conformities identified by the image quality analysis services to a technician in the site of the imaging system in less than a minute from the time the image was acquired to determine if the plurality of identified nonconformities includes a pre-determined type of non-conformity, wherein the plurality of nonconformities include one or more of;

absence of a breast/chest angle in an MLQ view, wherein the MLO is a mediolateral-oblique;

misalignment of a nipple and pectoral muscle in an MLO view, wherein the MLO is a mediolateral-oblique;

non-centered nipple in a CC view, wherein the CC is a center-caudal;

and absence of pectoral muscle in the CC view, wherein the CC is a center-caudal.

12. The method of claim 11, wherein the site is a mobile site presently occupied by a portable imaging system.

13. The method of claim 11, wherein the network-based architecture comprises a cloud-based architecture.

14. The method of claim 11, wherein the plurality of non-conformities include one or more of:

bad pixels, line artifacts, or components of the imaging system shown in the image.

15. The method of claim 11, wherein the plurality of non-conformities relate to clinical standards for the position and/or orientation of a body part being imaged.