CPC G06T 7/0012 (2013.01) [A61B 6/4057 (2013.01); A61B 6/4208 (2013.01); G06T 7/20 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20101 (2013.01); G06T 2207/30004 (2013.01)] | 20 Claims |
1. An imaging system comprising:
an imaging device comprising a gamma camera and a persistence scope, and structured to scan a subject during an image scan performed by an operator, the subject comprising an organ, a structure, or a region of interest (ROI) of the organ or the structure; and
a real-time, AI-enabled analysis device coupled to the imaging device and comprising an AI-enabled data processing system, an input apparatus, and a display, the real-time, AI-enabled analysis device configured to:
receive data corresponding to a plurality of image frames from the gamma camera and user input identifying the ROI using the persistence scope in a first image frame of the plurality of the image frames;
provide data corresponding to the first image frame, including the identified ROI and data corresponding to the remaining image frames to the AI-enabled data processing system, wherein the AI-enabled data processing system has been previously trained to automatically track the identified ROI during the image scan using training and test data representing a number of image datasets associated with the ROI obtained from a plurality of test subjects;
accept a plurality of valid image frames from the plurality of image frames based on a predefined set of computer vision rules and a minimum accepted frame threshold;
calculate, frame by frame, an ROI function value of the plurality of valid image frames;
automatically determine whether a predetermined ROI function value has been reached; and
alert the operator of the imaging device that at least one of the predetermined ROI function value or a predefined maximum scan duration has been reached.
|
11. A real-time, AI-enabled analysis device coupled to an imaging device for use during an image scan, comprising:
an input apparatus;
a display; and
an AI-enabled data processing system, wherein the real-time, AI-enabled analysis device is configured to:
receive data corresponding to a plurality of image frames from the imaging device and user input identifying an ROI in a first image frame of the plurality of the image frames;
provide data corresponding to the first image frame, including the identified ROI and data corresponding to the remaining image frames to the AI-enabled data processing system, wherein the AI-enabled data processing system has been previously trained to automatically identify the ROI during the image scan using training and test data representing a number of image datasets associated with the ROI obtained from a plurality of test subjects;
accept a plurality of valid image frames from the plurality of image frames based on a predefined set of computer vision rules and a minimum accepted frame threshold;
calculate, frame by frame, an ROI function value of the plurality of valid image frames; and
determine whether a predetermined ROI function value has been reached; and
alert an operator of the imaging device that the predetermined ROI function value has been reached.
|
12. A method of imaging using a real-time, AI-enabled analysis device coupled to an imaging device during an image scan of a subject, comprising:
receiving data corresponding to a plurality of image frames from the imaging device and user input identifying a region of interest (ROI) in a first image frame of the plurality of the image frames;
providing data corresponding to the first image frame, including the identified ROI and data corresponding to the remaining image frames to an AI-enabled data processing system of the real-time, AI-enabled analysis device, wherein the AI-enabled data processing system has been previously trained automatically to track the identified ROI during the image scan using training and test data representing a number of image datasets associated with the ROI obtained from a plurality of test subjects;
accepting a plurality of valid image frames from the plurality of image frames based on a predefined set of computer vision rules and a minimum accepted frame threshold;
calculating, frame by frame, an ROI function value of the plurality of valid image frames;
determining whether a predetermined ROI function value has been reached; and
alerting an operator of the imaging device that the predetermined ROI function value has been reached.
|