Medical scan triaging system and methods for use therewith

Patent metadata

Field	Value
Publication number	US-11669792-B2
Application number	US-202117457050-A
Country	US
Kind code	B2
Filing date	Dec 1, 2021
Priority date	Nov 21, 2018
Publication date	Jun 6, 2023
Grant date	Jun 6, 2023

Abstract

A medical scan triaging system is operable to train a computer vision model and to generate abnormality data indicating abnormality probabilities for medical scans via the computer vision model. A first subset of medical scans is determined by identifying medical scans with abnormality probabilities greater than a first probability value of a triage probability threshold. A second subset of medical scans is determined by identifying medical scans with abnormality probabilities less than the first probability value. An updated first subset of medical scans is determined by identifying medical scans with abnormality probabilities greater than a second probability value of an updated triage probability threshold. An updated second subset of the plurality of medical scans is determined by identifying medical scans with a abnormality probabilities less than the second probability value. The updated first subset of medical scans is transmitted to client devices.

First claim

What is claimed is:

1. A method for execution by a medical scan triaging system, the method comprising:
training a computer vision model by performing a training step upon image data of a training set of medical scans, the computer vision model utilizing artificial intelligence;
generating abnormality data for each of a plurality of medical scans by utilizing the computer vision model to perform an inference function on image data of each of the plurality of medical scans via the artificial intelligence, wherein the abnormality data for the each of the plurality of medical scans indicates an abnormality probability indicating a probability that an abnormality is present in the each of the plurality of medical scans;
determining a first subset of the plurality of medical scans designated for human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability greater than a first probability value indicated by a triage probability threshold;
determining a second subset of the plurality of medical scans designated as normal and waived from the human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability less than the first probability value indicated by the triage probability threshold;
facilitating transmission of each of the first subset of the plurality of medical scans to at least one of a plurality of client devices;
determining an updated triage probability threshold with a second probability value that is less than the first probability value;
determining an updated first subset of the plurality of medical scans designated for the human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability greater than the second probability value of the updated triage probability threshold; and
determining an updated second subset of the plurality of medical scans designated as normal and waived from the human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability less than the second probability value of the updated triage probability threshold, wherein at least one of the plurality of medical scans has an abnormality probability that is less than the first probability value indicated by the triage probability threshold and that is greater than the second probability value indicated by the updated triage probability threshold, and wherein at least one of the plurality of medical scans in the second subset is removed to generate the updated second subset and is added to the first subset to generate the updated first subset.

2. The method of claim 1 , further comprising:
receiving the triage probability threshold and the updated triage probability threshold from a first client device that is distinct from the plurality of client devices.

3. The method of claim 1 , wherein the triage probability threshold determined at a first time, and wherein the updated triage probability threshold is determined at a second time after the first time.

4. The method of claim 1 wherein the at least one medical scan is transmitted to at least one of the plurality of client devices for review.

5. The method of claim 1 , wherein the triage probability threshold is determined based on an administrator setting the triage probability threshold, and wherein the updated triage probability threshold is determined based on the administrator changing the triage probability threshold to the updated triage probability threshold.

6. The method of claim 1 , wherein the abnormality data for at least one of the plurality of medical scans further includes a time-sensitivity value indicating a time-sensitivity of a detected abnormality in the abnormality data, and wherein the method further comprises:
determining a triage time-sensitivity threshold;
determining a third subset of the plurality of medical scans by identifying ones of the second subset of the plurality of medical scans with a corresponding time-sensitivity value that compares favorably to the triage time-sensitivity threshold;
designating the third subset of the plurality of medical scans for human review; and
facilitating transmission of the third subset of the plurality of medical scans to the plurality of client devices associated with a plurality of users, wherein the third subset of the plurality of medical scans are displayed to the plurality of users via a plurality of display devices associated with the plurality of client devices, wherein each of the third subset of the plurality of medical scans is transmitted to one of the plurality of client devices.

7. A medical scan triaging system, comprising:
at least one processor; and
a memory that stores operational instructions that, when executed by the at least one processor, cause the medical scan triaging system to:
train a computer vision model by performing a training step upon image data of a training set of medical scans, the computer vision model utilizing artificial intelligence;
generate abnormality data for each of a plurality of medical scans by utilizing the computer vision model to perform an inference function on image data of each of the plurality of medical scans via the artificial intelligence, wherein the abnormality data for the each of the plurality of medical scans indicates an abnormality probability indicating a probability that an abnormality is present in the each of the plurality of medical scans;
determine a first subset of the plurality of medical scans designated for human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability greater than a first probability value indicated by a triage probability threshold;
determine a second subset of the plurality of medical scans designated as normal and waived from the human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability less than the first probability value indicated by the triage probability threshold;
determine an updated triage probability threshold with a second probability value that is greater than the first probability value;
determine an updated first subset of the plurality of medical scans designated for the human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability greater than the second probability value of the updated triage probability threshold;
determine an updated second subset of the plurality of medical scans designated as normal and waived from the human review by identifying ones of the plurality of medical scans with a corresponding abnormality probability less than the second probability value of the updated triage probability threshold, wherein at least one of the plurality of medical scans has an abnormality probability that is greater than the first probability value indicated by the triage probability threshold and that is less than the second probability value indicated by the updated triage probability threshold, wherein the at least one of the plurality of medical scans in the first subset is removed to generate the updated first subset and is added to the second subset to generate the updated second subset; and
facilitate transmission of each of the updated first subset of the plurality of medical scans to at least one of a plurality of client devices.

8. The medical scan triaging system of claim 7 , wherein the operational instructions, when executed by, further cause the medical scan triaging system to:
receive the triage probability threshold and the updated triage probability threshold from a first client device that is distinct from the plurality of client devices.

9. The medical scan triag

Assignees

• Enlitic Inc

Inventors

• Lyman Kevin
• Yao Li
• Poblenz Eric C
• Prosky Jordan
• Covington Ben
• Upton Anthony

Classifications

• G06T12/20

  Inverse problem, i.e. transformations from projection space into object space · CPC title

• G06T11/26

  Drawing of charts or graphs · CPC title

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title