Image search software helps detect cancer

Christopher Boone: Visuvi as I mentioned is a visual search engine with patent painting technology around content based image analysis. What that means is that unlike Google where you type in text to initiate a search query, we allow users to upload an image and we then analyze that image to determine the content to deliver relevant results, so in this example, what would you type in to Google to try and describe to be able to find the artist who painted this? James Gosling: Seurat. Christopher Boone: Well, that's cheating. James Gosling: Yeah, I happen to know the answer. Christopher Boone: But if you didn't know the answer, right, it becomes a little more challenging. James Gosling: That's right. Christopher Boone: Truly a situation where an image is worth a thousand words. James Gosling: Right. Christopher Boone: So, with Visuvi, you click to the next slide. You can see, you can take or capture the image through any means, a mobile phone, a PDA, a computer to initiate a search query our engine and analyzes the content of the image to deliver relevant results. The unique thing here is that there is no text, there's no meta-tags involved. It's entirely computer generated image analysis. So, we click to the next one. Something a little more practical and not to scare you, but being men, there is one in six chance that we could be diagnosed with prostate cancer. So, this is actually a prostate biopsy. We click to the next. One of the things that we are trying to do or where we are seeing use case in our technology is to improve the diagnoses for cancer and prostate cancer for example the most effective means of diagnosis is a $6,000 procedure. The majority of which is a human being, a pathologist that has to sit down and actually review this information, and so our technology can do a couple of things. One of which is improve the qualitative and quantitative information around that diagnosis, but more importantly is to reduce that cost. So, reducing that cost we can provide them the information, but also eventually improve patient care. James Gosling: So, the way this is build is you've got this Java application in the back end that essentially has a hatch table of a lot of images. Christopher Boone: Yeah, so right now we have about 150 million images. We are indexing at a rate of about 400 images per second, so roughly a billion a month. We are a young company. James Gosling: Yeah. Christopher Boone: Been around for less than a year. So, yeah, the index that we have is pretty substantial. James Gosling: Right and the front end that you built is that looks to me like an FX app. Christopher Boone: That's correct. This is a -- as a matter of fact this is a Java FX app that we've developed and I'm proud to say that again, this very talented team put this together in a week. So, what we are looking at here -- this is an actually biopsy slide, prostate biopsy and we can magnify this looking at the resolution here to get into some more granular detail and the use case is fairly -- seemingly fairly simple, right. So, a pathologist might see something that's unique and they want to be able to identify similar patient cases and then of course their respective diagnosis. So, with our technology, and again using Java, a pathologist could highlight that respective item, capture that with this Java FX app and then use that image to initiate a search query to find related patient cases. And again, this is live. This is all happening in real time. James Gosling: Right, so you just searched many millions of biopsies to find similar features. Christopher Boone: Ninety thousand images in this case in 0.3 seconds. James Gosling: Yeah and so what you end up with is images that are kind of similar with patient outcomes, patient histories. Christopher Boone: Yeah, so we can click on the patient outcome here and look at the diagnoses and in this case, this was cancer, unfortunately. James Gosling: Yeah, that's pretty cool. And I suspect that there are more than a few people in this room who will live an extra few years just because of you guys.

Music

==== Transcribed by Automatic Sync Technologies ====