METHOD AND WORKSTATIONS FOR A DIAGNOSTIC SUPPORT SYSTEM

• US 20190392944A1
• Filed: 06/22/2018
• Published: 12/26/2019
• Est. Priority Date: 06/22/2018
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Samset, Eigil, Kohls, Mark
• Application Number:
  US16/016,291
• Publication Number:
  US 20190392944A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/54 Browsing; Visualisation therefor
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/10132 Ultrasound image
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Methods and systems are provided for automating analysis of diagnostic medical images. In one example, a method includes obtaining a set of medical images of a patient, automatically generating a set of clinical parameters from the set of medical images, automatically identifying a clinical finding of the patient based on at least one selected clinical parameter of the set of clinical parameters, outputting a graphical user interface for display on a display device, the graphical user interface including a visualization of the clinical finding and a link within the visualization of the clinical finding, and responsive to selection of the link, outputting, for display within the graphical user interface, a visualization of the at least one selected clinical parameter.

Claims

1. A method, comprising:

obtaining a set of medical images of a patient;

automatically generating a set of clinical parameters from the set of medical images;

automatically identifying a clinical finding of the patient based on at least one selected clinical parameter of the set of clinical parameters;

outputting a graphical user interface for display on a display device, the graphical user interface including a visualization of the clinical finding and a link within the visualization of the clinical finding; and

responsive to selection of the link, outputting, for display within the graphical user interface, a visualization of the at least one selected clinical parameter.

2. The method of claim 1, wherein the link is a first link, the visualization of the at least one selected clinical parameter includes a second link, and further comprising responsive to selection of the second link, outputting, for display within the graphical user interface, a selected image from the set of medical images, the selected image including a visualization of the at least one selected clinical parameter in relation to the selected image.

3. The method of claim 2, further comprising outputting, for display within the graphical user interface, a set of thumbnail images each representing a respective image of the set of medical images associated with the clinical finding.

4. The method of claim 1, wherein:

the set of clinical parameters comprises one or more of;

one or more quantitative measurements of anatomical and/or physiological features of the patient, one or more classifications of anatomical and/or physiological features of the patient, and one or more scores of anatomical and/or physiological features of the patient; and

automatically identifying the clinical finding of the patient comprises automatically identifying the clinical finding based on at least one selected clinical parameter of the set of clinical parameters and patient information received from one or more of a remote computing device and user input.

5. The method of claim 4, wherein the one or more quantitative measurements include one or more of:

one or more distance measurements, one or more area measurements, one or more volume measurements, one or more velocity measurements, and one or more time measurements.

6. The method of claim 5, wherein automatically generating the set of clinical parameters from the set of medical images comprises automatically identifying each anatomical feature and each physiological feature in each image of the set of medical images and generating the one or more quantitative measurements by measuring at least one identified anatomical feature and/or identified physiological feature.

7. The method of claim 1, wherein obtaining the set of medical images of the patient comprises obtaining a set of ultrasound images of the patient.

8. The method of claim 7, wherein obtaining the set of ultrasound images comprises obtaining a set of ultrasound images of a heart of the patient, and wherein automatically generating the set of clinical parameters from the set of medical images comprises automatically generating the set of clinical parameters from the set of ultrasound images of the heart according to an echocardiogram protocol.

9. The method of claim 1, wherein obtaining the set of medical images of the patient comprises obtaining a set of images of a heart of the patient, the set of images of the heart of the patient acquired from an ultrasound imaging system, a magnetic resonance imaging system, or a computed tomography imaging system.

10. The method of claim 9, wherein automatically identifying the clinical finding of the patient comprises automatically identifying the clinical finding based on at least one selected clinical parameter of the set of clinical parameters and further based on prior clinical findings of the patient identified from a previous exam.

11. The method of claim 1, further comprising:

identifying one or more clinical findings for each of a plurality of patients;

assigning a severity score to each patient based on the identified one or more clinical findings; and

outputting a second graphical user interface that presents a list of the plurality of patients sorted by respective severity scores.

12. A workstation, comprising:

a display; and

a processor configured to execute instructions stored in memory to;

output, to the display, a visualization of a clinical finding of a patient, the clinical finding automatically identified from a clinical parameter of a set of clinical parameters automatically determined from a set of medical images of the patient, the visualization of the clinical finding including a link; and

responsive to a user selecting the link, output to the display an image from the set of medical images, the image associated with the clinical finding and including a visualization of the clinical parameter.

13. The workstation of claim 12, wherein the processor is configured to execute instructions to output, to the display, a visualization of the clinical parameter along with the visualization of the clinical finding.

14. The workstation of claim 12, wherein the processor is configured to execute instructions to output, to the display, a visualization of the clinical parameter along with the image.

15. The workstation of claim 12, wherein the clinical parameter includes a quantitative measurement of an anatomical feature of the patient, wherein the clinical finding is identified based on the quantitative measurement having a value outside a normal range of values for the quantitative measurement, and wherein the image includes the anatomical feature annotated with a visualization of the quantitative measurement.

16. The workstation of claim 12, wherein the processor is configured to execute instructions to:

output, to the display, a first user interface control button and a second user interface control button;

responsive to the user selecting the first user interface control button, save the clinical finding in a report; and

responsive to the user selecting the second user interface control button, omit the clinical finding from the report, the report configured to be saved in a medical record of the patient.

17. A workstation, comprising:

a display; and

a processor configured to execute instructions stored in memory to;

output, to the display, a graphical user interface including a visualization of a clinical finding of a patient and a visualization of one or more clinical parameters, the clinical finding automatically identified from the one or more clinical parameters, the one or more clinical parameters automatically generated from a set of medical images of the patient; and

responsive to a user selecting a link associated with a selected clinical parameter of the one or more clinical parameters, output, to the display, an image from the set of medical images that includes an annotation of the selected clinical parameter.

18. The workstation of claim 17, wherein the link is a first link associated with a first selected clinical parameter, wherein the image is a first image, and wherein the processor is configured to execute instructions to, responsive to the user selecting a second link associated with a second selected clinical parameter of the one or more clinical parameters, output, to the display, a second image from the set of medical images that includes an annotation of the second selected clinical parameter.

19. The workstation of claim 17, wherein the one or more clinical parameters comprise a subset of a plurality of clinical parameters automatically generated from the set of medical images of the patient, and wherein the clinical finding is a first clinical finding of a plurality of clinical findings automatically identified from the plurality of clinical parameters.

20. The workstation of claim 19, wherein the first clinical finding comprises an abnormal finding, wherein at least one other clinical finding of the plurality of clinical findings comprises a normal finding, wherein the one or more clinical parameters includes a first quantitative measurement of an anatomical feature of the patient, wherein the first clinical finding is identified based on the first quantitative measurement having a value outside a normal range of values for the first quantitative measurement, wherein the image includes the anatomical feature annotated with a visualization of the first quantitative measurement, and wherein the normal finding is identified based on a second quantitative measurement of an anatomical feature of the patient having a value within a normal range of values for the second quantitative measurement.