Methods and systems for workflow management

Patent metadata

Field	Value
Publication number	US-11393579-B2
Application number	US-201916522554-A
Country	US
Kind code	B2
Filing date	Jul 25, 2019
Priority date	Jul 25, 2019
Publication date	Jul 19, 2022
Grant date	Jul 19, 2022

Abstract

Various methods and systems are provided for generating an optimized workflow and assisting in clinical decision making during analysis of a patient image by a user at a site. In an example, a method includes automatically identifying one or more exam parameters associated with a diagnostic exam that includes one or more medical images and automatically generating a workflow for analyzing the one or more medical images, the workflow including one or more of a diagnostic protocol, a toolset, a prior imaging scan, a prior finding, and a reference image, the workflow generated based on the one or more exam parameters.

First claim

The invention claimed is:

1. A method, comprising:
automatically identifying one or more exam parameters associated with a diagnostic exam that includes one or more medical images;
automatically generating a workflow for analyzing the one or more medical images, the workflow including one or more of a diagnostic protocol, a toolset, a prior imaging scan, a prior finding, and a reference image, wherein the workflow is generated based on the one or more exam parameters and wherein the toolset comprises at least one user interface menu option or at least one control button that, when selected, allows a task to be performed;
training an artificial intelligence-based model to predict which of one or more viewports of a user interface are to display the prior imaging scan, the toolset, or the reference image, wherein the training includes training the artificial intelligence-based model using the prior imaging scan, the toolset used by a clinician when making a diagnosis using the prior imaging scan, a relative positioning of one or more tools of the toolset when making the diagnosis, and corroboration of the diagnosis with expert usage data;
automatically executing the artificial intelligence-based model, based at least in part on an imaging modality used to acquire the reference image and without explicit user input, to predict which of the one or more viewports of the user interface are to display the prior imaging scan, the toolset, or the reference image;
displaying the workflow in the predicted one or more viewports of the user interface, wherein a size of the one or more viewports or a position of the one or more viewports is predicted based at least in part on the prior imaging scan, the toolset, the reference image, or a combination thereof; and
displaying the one or more medical images in the user interface that is formatted according to the workflow.

2. The method of claim 1 , wherein the one or more exam parameters comprise one or more of the imaging modality used to acquire the one or more medical images, a diagnostic goal of the diagnostic exam, anatomical features imaged in the one or more medical images, patient information of a patient imaged in the one or more medical images, and an identity of the clinician performing the diagnostic exam.

3. The method of claim 1 , further comprising collecting follow-up data after completion of the diagnostic exam confirming or not confirming one or more findings saved with the diagnostic exam, the follow-up data usable to determine a diagnostic accuracy of the generated workflow.

4. The method of claim 1 , wherein the diagnostic protocol includes a list of action items to be performed during the diagnostic exam.

5. The method of claim 1 , wherein the workflow further includes a format of a workflow interface via which the one or more medical images, the toolset, the prior imaging scan, the prior finding, and the reference image are displayed.

6. The method of claim 1 , wherein automatically generating the workflow comprises automatically generating the workflow according to a set of suggested workflow parameters output by one or more workflow models.

7. The method of claim 6 , wherein the one or more workflow models are trained to correlate the one or more exam parameters with the set of suggested workflow parameters based on training datasets that include, for each of a plurality of prior diagnostic exams associated with different respective patients, patient clinical data, prior reports, image data, and diagnostic exam workflow usage data.

8. The method of claim 7 , further comprising collecting user interaction data during execution of the diagnostic exam via the generated workflow, the user interaction data usable to retrain the one or more workflow models.

9. A system, comprising:
a storage system; and
a computing device storing instructions executable by a processor of the computing device to:
automatically identify one or more exam parameters associated with a diagnostic exam that includes one or more medical images, the diagnostic exam and the one or more medical images stored in the storage system;
automatically generate a workflow for analyzing the one or more medical images, the workflow including one or more of a diagnostic protocol, a toolset, a prior imaging scan, a prior finding, and a reference image, wherein the workflow is generated based on the one or more exam parameters and wherein the toolset comprises at least one user interface menu option or at least one control button that, when selected, allows a task to be performed;
train an artificial intelligence-based model to predict which of one or more viewports of a user interface are to display the prior imaging scan, the toolset, or the reference image, wherein the training includes training the artificial intelligence-based model using the prior imaging scan, the toolset used by a clinician when making a diagnosis using the prior imaging scan, a relative positioning of one or more tools of the toolset when making the diagnosis, and corroboration of the diagnosis with expert usage; automatically execute the artificial intelligence-based model, based at least in part on an imaging modality used to acquire the reference image and without explicit user input, to predict which of the one or more viewports of the user interface are to display the prior imaging scan, the toolset, or the reference image;
display the workflow in the predicted one or more viewports of the user interface, wherein a size of the one or more viewports or a position of the one or more viewports is predicted based at least in part on the prior imaging scan, the toolset, the reference image, or a combination thereof;
display the one or more medical images in the user interface that is formatted according to the workflow; and
send the workflow to the storage system for storage with the one or more medical images as part of the diagnostic exam.

10. The system of claim 9 , wherein the workflow comprises predicting a hanging protocol that indicates an order of presentation of the one or more medical images during the diagnostic exam.

11. The system of claim 9 , further comprising a viewer including a display device, and wherein the viewer is configured to send a request to the storage system to retrieve the diagnostic exam including the one or more medical images and the workflow, and display via the display device the one or more medical images according to the diagnostic protocol of the workflow and display the toolset, the prior imaging scan, the prior finding, and/or the reference image according to the workflow.

12. The system of claim 9 , wherein the one or more exam parameters comprise one or more of the imaging modality used to acquire the one or more medical images, a diagnostic goal of the diagnostic exam, anatomical features imaged in the one or more medical images, patient information of a patient imaged in the one or more medical images, and an identity of the clinician performing the diagnostic exam.

13. The system of claim 9 , wherein the diagnostic protocol includes a list of action items to be performed during the diagnostic exam and wherein the workflow further includes a format of a workflow interface via which the one or more medical images, the toolset, the prior imaging scan, the prior finding, and the reference image are displayed.

14. The system of claim 9 , wherein automatically generating the workflow comprises automatically generating the workflow according to a set of suggested workflow parameters output by one or more workflow models.

15. The system of claim 14 , wherein the one or more workflow models are

Assignees

• Ge Prec Healthcare Llc
• Ge Prec Healthcare

Inventors

• Kumar Shashi
• Jha Avinash
• Ramanatha Chiranjeevi

Classifications

• G16H40/20 Primary

  for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms · CPC title

• G16H30/20 Primary

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title

• G06Q10/0633

  Workflow analysis · CPC title

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title