Video Tip: Using AI to Detect Neoplasia | June 2022-Using AI to Detect Neoplasia

Video Transcription

Because you can see that looks to me like the lesion at six o'clock. So come back more if you can come back back. So that's the squamous.  And you can see now there is no positive signal, there's no alarm. And if we go down slowly now towards the barracks.  And so far there is no AI signal for detection. And here we come you see the reverse L appears, and it transfers an image to the top right corner with the heat map showing a lesion at the bottom.  And so, the AI is detecting a lesion I, I also agree that there is likely to be a new plastic lesion here between about six to eight o'clock looks slightly depressed.  Almost to a resident it appeared to be a little bit more extensive than six to eight, I mean how about it's almost starting at the three o'clock.  Well, yesterday, that's where we will have to use the BLI, and I think you're probably right, there's a subtle extension at about three o'clock so it's almost three to nine o'clock.  Yeah, and this is a good example also is that a lot of these lesions is in Barrett says you will know, end up being a little bit more extensive than what you initially think it to be so this is a great.  Yeah, it is. What frame rate does the AI system, run your images in the room. Yes, I know is our research fellow. I don't know. Do you know the frame rate.  For the detection is about five milliseconds per image or frame. So it's incredibly fast.  So, it's, it's almost it is, that's why it's real time as you see it. It detects sometimes it certainly detects a lot faster than most of my fellows can detect the lesion.  So, as soon as it's within the endoscopy view. It detects the lesion. So that's the master most of the most just go down there. So you can see the sutures.  These are the surgical sutures that you can see the black sutures that the good thing is there is no nuisance value of the system. There is no false positive detection here you see a lot of time in our early phase we noticed that the top of the gastric  fold gets detected as a positive lesion because it's raised, but the beauty of this system is there's no detection of these gastric folds.  There's no noise there so you pull back slowly now.

Video Summary

In this video, a medical professional is using an AI system to detect lesions in a patient. They identify a squamous lesion at six o'clock and note that there is no positive signal or alarm. As they move downwards, they come across a reverse L image in the top right corner with a heat map showing a lesion at the bottom. They agree that there is likely a new plastic lesion between six and eight o'clock, which may actually extend from three to nine o'clock. They also discuss the fast frame rate of the AI system, which allows for real-time detection. Additionally, they note that the system does not have any false positive detections and does not detect gastric folds.

Keywords

AI system

lesion detection

squamous lesion

plastic lesion

fast frame rate