Video Tip: Using AI for Lesion and Dysplasia Detection | May 2022-Using AI for Lesion and Dysplasia Detection

Video Transcription

So, that's a patient with a Barrett's lesion, and you can see that the reverse green L is a sign of detection. As soon as it detects, it transfers the image to the top right corner,  and then the heat map shows the location of the lesion. So, as we come back now, the lesion is back in focus. You can see the heat map is detecting.  So, moving on to another case, which is a splat lesion. Again, you can see, as soon as they come into view, the reverse L finds the lesion,  and the heat map is showing you the location of the lesion. This last case is a very subtle lesion, only seen on retroflexion, and you can see that it's very difficult,  but even in retroflexion, you can, the system is detecting the lesion. Heat map is showing you the location. There, you can see slightly 2C depressed area.  This is, I feel, is the common blind spot for community endoscopists who do big-volume endoscopy, and lesions around this area get commonly missed.  So, this will be one of the big advantages of AI in the future when you have lesions like this, which can be picked up because they can be very easily missed.  This is just on top of the gastric fold, and you can see from the heat map that it extends only up to the lesion and not all the way down the gastric fold  because gastric fold is always a nuisance element, and AI can pick that up as a false positive signal all the time. So, these were four very quick snippets of what the system does.

Video Summary

This video showcases a system that uses AI to detect lesions in patients. The video highlights three different cases: a patient with a Barrett's lesion, a splat lesion, and a subtle lesion only visible on retroflexion. In each case, the AI system quickly detects the lesion and displays it in the top right corner, along with a heat map indicating its location. The video emphasizes the potential benefits of AI in detecting lesions that are easily missed, such as those around the gastric fold. The system is shown to be able to differentiate between real lesions and false positive signals caused by the gastric fold. (No credits were mentioned in the transcript)

Keywords

AI system

lesion detection

Barrett's lesion

splat lesion

retroflexion