Endoscopy video feature enhancement platform
An endoscopy video feature enhancement platform (EVFEP) is connected to the output of any type endoscope system, and inputs and captures the output video. The video is visually augmented live with indicators of possible polyp detection and localization, polyp attributes, and procedure metrics, based on the collective learning of the output results of many different types of endoscopy systems on a large scale. An artificial intelligence model is trained on confirmed polyp detection previously determined by this and other EVFEP devices used with many different types of endoscope systems on a large scale. Augmented video, images and automatically generated short video clips of key procedure segments are passed to a reporting system, and supplemented with meta data.
1. A method of simplifying identification of a segment of interest in video output from an endoscopy system, comprising:
inputting an unaugmented mirrored monitor endoscopy video stream output from an output port of an endoscopy system;
detecting a picture-in-picture within the input unaugmented mirrored monitor endoscopy video stream;
generating a video clip from the input endoscopy video stream comprising image frames before and after the detected picture-in-picture in the input endoscopy video stream, the video clip spanning a given length of time;
triggering collection of critical information related to the detected picture-in-picture by generating in real-time an audible prompt requesting a verbal finding of the critical information;
speech-to-text converting a responsive verbal finding to meta data; and
associating the meta data with the video clip.
2. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , further comprising:
aggregating a plurality of the video clips together with the respective verbal findings; and
transmitting the aggregated plurality of the video clips to an EMR/reporting system in either push or pull mode.
3. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , wherein:
the verbal finding includes a reason, a location, and a description of an anomaly visible in the generated video clip.
4. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , wherein:
the given length of time of the video clip is configurably adjustable.
5. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , wherein:
the audible prompt is a verbal request.
6. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , wherein:
the output port of the endoscopy system is a mirrored output port.
7. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , wherein:
the output port of the endoscopy system is an output from a digital video splitter.
8. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , further comprising:
storing the meta data to an electronic medical record.
9. The method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 1 , further comprising:
storing a copy of the video clip; and
storing a link to the copy of the video clip, augmented with the meta data, to an electronic medical record.
10. A computer-readable medium storing instructions that, when executed by a computer, cause it to perform a method of simplifying identification of a segment of interest in video output from an endoscopy system, comprising steps of:
inputting an unaugmented mirrored monitor endoscopy video stream output from an output port of an endoscopy system;
detecting a picture-in-picture within the input unaugmented mirrored monitor endoscopy video stream;
generating a video clip from the input endoscopy video stream comprising image frames before and after the detected picture-in-picture in the input endoscopy video stream, the video clip spanning a given length of time;
triggering collection of critical information related to the detected picture-in-picture by generating in real-time an audible prompt requesting a verbal finding of the critical information;
speech-to-text converting a responsive verbal finding to meta data; and
associating the meta data with the video clip.
11. The computer-readable medium storing instructions that, when executed by a computer, cause it to perform the method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 10 , further comprising:
storing the meta data to an electronic medical record.
12. The computer-readable medium storing instructions that, when executed by a computer, cause it to perform a method of simplifying identification of a segment of interest in video output from an endoscopy system according to claim 10 , further comprising:
storing a copy of the video clip; and
storing a link to the copy of the video clip, augmented with the meta data, to an electronic medical record.