System and method for providing AI-assisted checklist for interventional medical procedures

Patent metadata

Field	Value
Publication number	US-12536661-B2
Application number	US-202318374145-A
Country	US
Kind code	B2
Filing date	Sep 28, 2023
Priority date	Sep 28, 2023
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

An imaging system and method includes a display, a processor, and electronic memory storing processor-executable code that operates by receiving an image of a patient with a medical device disposed therein, detecting the medical device within the image, detecting one or more reference landmark(s) within the image, and generating a combined image by superimposing an overlay on the image to indicate a position of the medical device relative to the reference landmarks. The processor-executable code further causes the image processing system to generate a checklist for verification by a user of the position of the medical device for presentation with the combined image on the display to help the user to adhere to clinical guidelines for placement of the device. In addition, the processor-executable code can prefill the checklist using an artificial intelligence model, with checklist responses used to train or validate the AI model, or for quality assurance purposes.

First claim

We claim:

1 . A imaging processing system, comprising:
(a) a display; (b) a processor; and (c) a memory storing processor-executable code that when executed by the processor causes:
(i) receiving an image of a region of interest of a patient with a medical tube or line disposed within the region of interest;
(ii) detecting the medical tube or line within the image;
(iii) detecting one or more reference landmark(s) within the region of interest within the image, wherein the one or more reference landmarks are internal to the patient;
(iv) generating a combined image by superimposing an overlay on the image to indicate a position of the medical tube or line relative to the one or more reference landmarks;
(v) generating a checklist for verification of the position of the medical tube or line relative to the one or more reference landmarks; and
(vi) presenting the combined image and checklist on the display.

2 . The imaging processing system of claim 1 , wherein generating the checklist comprises:
(a) accessing a memory storing clinical guidelines regarding proper placement of the medical tube or line relative to the one or more reference landmarks; and (b) selecting a number of steps for the checklist from the clinical guidelines.

3 . The imaging processing system of claim 2 , wherein selecting the number of steps from the clinical guidelines comprises selecting less than all of the steps in the checklist.

4 . The imaging processing system of claim 2 , wherein selecting the number of steps from the clinical guidelines comprises providing user-selectable responses associated with each of the steps.

5 . The imaging processing system of claim 4 , wherein the user-selectable responses include confidence scores associated with each user-selectable response.

6 . The imaging processing system of claim 5 , wherein the processor-executable code when executed by the processor causes a calculation of a confidence score for the combined image from the confidence scores from the user-selectable responses in the checklist.

7 . The imaging processing system of claim 4 , wherein the user-selectable responses include a priority review response.

8 . The imaging processing system of claim 4 , wherein the processor-executable code when executed by the processor causes determining whether the medical tube or line is properly positioned relative to the one or more reference landmarks.

9 . The imaging processing system of claim 8 , wherein determining whether the medical tube or line is properly positioned within the image comprises employing an artificial intelligence to determine whether the medical tube or line is properly positioned within the image.

10 . The imaging processing system of claim 9 , wherein the processor-executable code when executed by the processor causes comparing the determination by the artificial intelligence of whether the medical tube or line is properly positioned within the image with the user-selectable responses in the checklist.

11 . The imaging processing system of claim 10 , wherein comparing the determination by the artificial intelligence of whether the medical tube or line is properly positioned within the image with the user-selectable responses comprises pre-selecting one or more of the user-selectable responses in the checklist by the artificial intelligence.

12 . The imaging processing system of claim 10 , further comprising training the artificial intelligence with results of the comparison of the determination by the artificial intelligence of whether the medical tube or line is properly positioned within the image with the user-selectable response in the checklists.

13 . The imaging processing system of claim 10 , wherein comparing the determination by the artificial intelligence of whether the medical tube or line is properly positioned within the image with the user-selectable responses comprises providing feedback on the user-selectable responses in the checklist.

14 . An imaging system comprising:
(a) a radiation source; (b) a detector capable of receiving radiation emitted from the radiation source to generate image data; (c) a display for presenting information to a user; and (d) a controller connected to the display and operable to control the operation of the radiation source and detector to generate an image from the image data, the controller including an image processing system comprising:
(a) a processor; and
(b) a memory storing processor-executable code that when executed by the processor causes:
(i) receiving an image of a region of interest of a patient with a medical catheter, tube or line disposed within the region of interest;
(ii) detecting the medical tube or line within the image;
(iii) detecting one or more reference landmark(s) within the region of interest within the image, wherein the one or more reference landmarks are internal to the patient;
(iv) generating a combined image by superimposing an overlay on the image to indicate a position of the medical tube or line relative to the one or more reference landmarks;
(v) selecting a number of steps to form a checklist for verification of the position of the medical tube or line relative to the one or more reference landmarks; and
(vi) displaying the combined image and checklist on the display.

15 . A method for medical image processing, comprising:
(a) receiving, via a processor, an image of a region of interest of a patient with a medical tube or line disposed within the region of interest; (b) detecting, via the processor, the medical tube or line within the image; (c) detecting, via the processor, a number of reference landmarks within the region of interest within the image, wherein the number of reference landmarks are each internal to the patient; (d) generating, via the processor, a combined image by superimposing an overlay on the image to indicate a position of the medical tube or line relative to the one or more reference landmarks; (e) generating, via the processor, a checklist for verification of the position of the medical tube or line relative to the one or more reference landmarks; and (f) causing, via the processor, presentation of the combined image and the checklist on a display.

16 . The method of claim 15 , wherein the step of generating the checklist comprises, via the processor:
(a) accessing a memory storing clinical guidelines regarding proper placement of a medical tube relative to the one or more reference landmarks; and (b) selecting the number of steps comprises selecting the number of steps from the clinical guidelines.

17 . The method of claim 16 , wherein the step of generating the checklist comprises, via the processor, providing user-selectable responses associated with each of the steps of the checklist.

18 . The method of claim 17 , comprising determining, via the processor, whether the medical tube or line is properly positioned relative to the one or more reference landmarks.

19 . The method of claim 18 , wherein determining whether the medical tube or line is properly positioned within the image comprises employing, via the processor, an artificial intelligence to determine whether the medical tube or line is properly positioned within the image.

20 . The method of claim 19 , comprising comparing, via the processor, the determination by the artificial intelligence of whether the medical tube or line is properly positioned within the image with the user-selectable responses in the checklist.

Assignees

• Ge Prec Healthcare Llc
• Ge Prec Healthcare

Inventors

• Tegzes Pál
• Herczeg Zita
• Yang Hongxu
• Kiss Zoltán
• Dalal Poonam
• Rao Gireesha
• Goswami Pulak
• Zhou Dennis

Classifications

• G06T2210/41

  Medical · CPC title

• G06T2207/30204

  Marker · CPC title

• G06T2207/30021

  Catheter; Guide wire · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title