Systems and methods for preventing errors in medical imaging

Patent metadata

Field	Value
Publication number	US-11587232-B1
Application number	US-202217738932-A
Country	US
Kind code	B1
Filing date	May 6, 2022
Priority date	May 6, 2022
Publication date	Feb 21, 2023
Grant date	Feb 21, 2023

Abstract

A method for preventing wrong-patient errors includes receiving a selection of a current imaging subject. The current imaging subject is selected for a current image acquisition session comprising capturing one or more current images of the current imaging subject utilizing at least a first image sensor system of a first imaging modality. The method includes accessing one or more previous images of a previous imaging subject. The one or more previous images depict the previous imaging subject according to at least a second imaging modality that is different from the first imaging modality. The method includes presenting the one or more previous images on a display system and, in response to determining that the previous imaging subject matches the current imaging subject based upon the one or more previous images, performing the current image acquisition session.

First claim

What is claimed is:

1. A computer-implemented method for preventing wrong-patient errors, comprising:
receiving a selection of a current imaging subject, the current imaging subject being selected for a current image acquisition session comprising ci) capturing one or more current images of the current imaging subject utilizing at least a first image sensor system of a first imaging modality and (ii) capturing one or more additional current images of the current imaging subject utilizing at least a second image sensor system of a second imaging modality that is different from the first imaging modality, the second image sensor system being mounted to the first image sensor system;
accessing a set of one or more previous images of a previous imaging subject, the one or more previous images of the previous imaging subject being associated with one or more image capture timepoints that temporally precede the current image acquisition session, the one or more previous images depicting the previous imaging subject according to at least the second imaging modality that is different from the first imaging modality;
presenting the one or more previous images on a display system, the display system comprising a user interface associated with control of the second image sensor; and
in response to determining that the previous imaging subject matches the current imaging subject based upon the one or more previous images of the second imaging modality, performing the current image acquisition session by (i) capturing the one or more current images of the current imaging subject utilizing at least the first image sensor system of the first imaging modality and (ii) capturing one or more additional current images of the current imaging subject utilizing at least the second image sensor system mounted to the first image sensor system.

2. The computer-implemented method of claim 1 , wherein receiving the selection of the current imaging subject comprises receiving user input selecting the current imaging subject.

3. The computer-implemented method of claim 1 , wherein accessing the set of one or more previous images of the previous imaging subject comprises accessing a data repository of imaging subjects based upon the selection of the current imaging subject.

4. The computer-implemented method of claim 1 , wherein the one or more current images or the one or more previous images comprise one or more video frames.

5. The computer-implemented method of claim 1 , wherein the user interface of the display system is further associated with control of the first image sensor system of the first imaging modality.

6. The computer-implemented method of claim 1 , wherein the set of one or more previous images of the previous imaging subject further comprises at least one previous image depicting the previous imaging subject according to the first imaging modality.

7. The computer-implemented method of claim 1 , wherein determining that the previous imaging subject matches the current imaging subject based upon the one or more previous images of the second imaging modality comprises receiving user input indicating that the previous imaging subject matches the current imaging subject.

8. The computer-implemented method of claim 1 , wherein determining that the previous imaging subject matches the current imaging subject is further based upon one or more audio recordings of the current imaging subject.

9. The computer-implemented method of claim 1 , further comprising associating the one or more current images with the previous imaging subject within a subject data repository.

10. The computer-implemented method of claim 1 , wherein the first image sensor system is configured to be prevented from acquiring the one or more current images of the current imaging subject unless the previous imaging subject matches the current imaging subject.

11. The computer-implemented method of claim 1 , wherein the first imaging modality comprises a medical imaging modality, the second imaging modality comprises a visible spectrum imaging modality, and the current imaging subject comprises a medical patient.

12. A computer-implemented method for preventing laterality errors, comprising:
prior to performing a current image acquisition session of a structure using a first imaging modality, capturing one or more images of the structure using a second imaging modality that is different from the first imaging modality;
accessing an indication of one or more intended structure attributes, the one or more intended structure attributes being selected to be embodied by the structure for the current image acquisition session;
determining one or more imaged structure attributes by utilizing the one or more images of the structure of the second imaging modality as input to one or more artificial intelligence modules configured to determine structure attributes based upon input imagery, the one or more imaged structure attributes comprising output of the one or more artificial intelligence modules; and
in response to determining one or more discrepancies between the one or more imaged structure attributes and the one or more intended structure attributes (i) preventing performance of the current image acquisition session and (ii) presenting a notification on a user interface.

13. The computer-implemented method of claim 12 , wherein the one or more intended structure attributes comprise an intended laterality, and wherein the one or more imaged structure attributes comprise an imaged laterality.

14. The computer-implemented method of claim 12 , wherein the one or more artificial intelligence modules comprise a convolutional neural network.

15. The computer-implemented method of claim 12 , wherein performance of the current image acquisition session using the first imaging modality is conditioned on detecting no discrepancies between the one or more imaged structure attributes and the one or more intended structure attributes.

Assignees

• Camerad Tech
• Uab Res Found

Inventors

• Wick Carson Arthur
• Tridandapani Srini

Classifications

• G10L17/00

  Speaker identification or verification techniques · CPC title

• G06V2201/03

  Recognition of patterns in medical or anatomical images · CPC title

• G06V10/74

  Image or video pattern matching; Proximity measures in feature spaces · CPC title

• A61B5/0055

  by applying suction · CPC title

• A61B5/0035 Primary

  adapted for acquisition of images from more than one imaging mode, e.g. combining MRI and optical tomography · CPC title