MEDICAL IMAGE IDENTIFICATION AND INTERPRETATION

• US 20180137244A1
• Filed: 11/14/2017
• Published: 05/17/2018
• Est. Priority Date: 11/17/2016
• Status: Active Grant

• Current Assignee: TeraRecon Inc. (Fortive Corp.)
• Original Assignee: TeraRecon Inc. (Fortive Corp.)
• Inventors: Sorenson, Jeffrey L., MacCutcheon, David W., Zhao, Tiecheng, Kuhn, Gael
• Granted Patent: US 10,452,813 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 2576/00 Medical imaging apparatus involving image processing or analysis A61B1/00009, A61B6/52 and A61B8/52 take precedence; image processing per se G06T; details of algorithms for analysing medical images G06T7/0012
• CPC Class Codes: A61B 5/0013 Medical image data A61B1/00011, A61B6/56, A61B8/56 take precedence
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 8/565 involving data transmission via a network
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

An artificial intelligence findings system includes an artificial intelligence findings system. An image identification engine receives new image data pertaining to a patient and past reports and image data pertaining to the patient. The image identification engine uses the past image data pertaining to the patient to identify for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data. A findings engine receives new image data and processes the new image data to generate findings based on the new image data and based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data. A communication interface provides the findings to a diagnostic review system that presents the findings to a user. An adjustment engine receives notifications of changes to findings made by a user when using the medical image interpretation system.

Claims

1. A medical image interpretation system, comprising:

an artificial intelligence findings system that comprises;

an image identification engine that receives new image data pertaining to a patient and past reports and past image data pertaining to the patient, the image identification engine using the past image data pertaining to the patient to identify for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data;

a findings engine that receives new image data and processes the new image data to generate findings based on the new image data and based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data;

a diagnostic review system that presents the findings to a user, the findings as presented comprising data that includes images; and

,

an adjustment engine that receives notifications of changes to findings made by the user when using the medical image interpretation system.

2. A medical image interpretation system as in claim 1, wherein the image identification engine, based on the new image data and based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data, calls additional finding engines to produce findings, the additional findings engines being selected to be called by the image identification engine is based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data and based upon the expertise of each of the additional findings engines.

3. A medical image interpretation system as in claim 1, additionally comprising:

a tracking module that tracks findings and adjustments made to the findings by the user when using the diagnostic review system, the tracking module producing tracking information based on the findings and adjustments made to the findings by the user and usage patterns ascertainable based on other users; and

a machine learning engine that receives the tracking information and based on the tracking information adjusts categorization preferences that are used by the image identification engine when identifying study images for patients.

4. A medical image interpretation system as in claim 1, wherein the findings presented to the user by the diagnostic review system include past reports and image data for the patient that are prior information to the images patient anatomical structures, anatomical anomalies and anatomical features within the new image data that are identified for study

5. A medical image interpretation system as in claim 1, wherein the image identification engine extracts features from the new image data to match image data in an archive that includes image data with similar characteristic features.

6. A medical image interpretation system as in claim 1:

wherein the image identification engine extracts features from the new image data to match image data in an archive that includes image data with similar characteristic features; and

,

wherein the diagnostic review system builds a hanging protocol using the new image data and the images on a computer screen to display the new image data and image data from the archive displayed in an order with multiple images on multiple monitors as determined by the hanging protocol.

7. A medical image interpretation system as in claim 1, wherein the artificial intelligence findings system additionally comprises:

a tracking module that tracks findings and adjustments made to the findings by the user when using the diagnostic review system, the tracking module producing tracking information based on the findings and adjustments made to the findings by the user and usage patterns ascertainable based on other users.

8. A medical image interpretation system as in claim 7, wherein the diagnostic review system includes:

a viewer that displays the images incorporated into a physician interpretation workflow adapting itself based upon the tracking information;

wherein the diagnostic review system allows the user to view and confirm findings, with the tracking engine tracking whether the findings are unviewed, viewed, added, deleted, adjusted, unconfirmed, confirmed, reported or unreported;

wherein the diagnostic review system allows the user to modify the images to produce derived images;

wherein changes made to the report are reflected in the images displayed by the viewer; and

,

wherein changes made to the images displayed by the viewer are reflected in report.

9. A method for producing a report from medical image data, the method comprising:

receiving new image data pertaining to a patient and past reports and past image data pertaining to the patient;

using an image identification engine to identify for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data based on the past image data pertaining to the patient;

using a findings engine to process the new image data to generate findings based on the new image data and based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data;

using a diagnostic review system to presents the findings to a user, the findings as presented comprising data that includes images; and

,

providing, to an adjustment engine, notifications of changes to findings made by the user when using the medical image interpretation system.

10. A method as in claim 9, wherein using an image identification engine to identify for study images based on the new image data and based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data, includes calling additional finding engines to produce findings, the additional findings engines being selected to be called by the image identification engine based on the identified for study images of patient anatomical structures, anatomical anomalies and anatomical features within the new image data and based upon the expertise of each of the additional findings engines.

11. A method as in claim 9, additionally comprising:

using a tracking module to track findings and adjustments made to the findings by the user when using the diagnostic review system, the tracking module producing tracking information based on the findings and adjustments made to the findings by the user and usage patterns ascertainable based on other users; and

using a machine learning engine to receive the tracking information and based on the tracking information adjusting categorization preferences that are used by the image identification engine when identifying study images for patients.

12. A method as in claim 9, wherein the findings presented to the user by the diagnostic review system include past reports and image data for the patient that are prior information to the images patient anatomical structures, anatomical anomalies and anatomical features within the new image data that are identified for study

13. A method as in claim 9, wherein the image identification engine extracts features from the new image data to match image data in an archive that includes image data with similar characteristic features.

14. A method as in claim 9:

wherein the image identification engine extracts features from the new image data to match image data in an archive that includes image data with similar characteristic features; and

,

wherein the diagnostic review system builds a hanging protocol using the new image data and the images on a computer screen to display the new image data and image data from the archive displayed in an order with multiple images on multiple monitors as determined by the hanging protocol.

15. A method as in claim 9, additionally comprising:

using a tracking module to track findings and adjustments made to the findings by the user when using the diagnostic review system, including producing tracking information based on the findings and adjustments made to the findings by the user and usage patterns ascertainable based on other users.

16. A method as in claim 15, wherein the diagnostic review system includes:

a viewer that displays the images incorporated into a physician interpretation workflow adapting itself based upon the tracking information;

wherein the diagnostic review system allows the user to view and confirm findings, with the tracking engine tracking whether the findings are unviewed, viewed, added, deleted, adjusted, unconfirmed, confirmed, reported or unreported;

wherein the diagnostic review system allows the user to modify the images to produce derived images;

wherein changes made to the report are reflected in the images displayed by the viewer; and

,

wherein changes made to the images displayed by the viewer are reflected in report.