Skip to main content
Milan Radovich

Milan Radovich

Higher education teacher

Sep 3, 2026

5:16
What does that mean in your world? And when you look at sequencing plus imaging plus clinical outcomes, what does that buy you in the real world?
5:26
You know, bias is quite a bit because it's really a genotype without a phenotype is, you know, just half the story.
5:32
Being able to just have molecular data itself helps us, for example, understand maybe the prevalence of a mutation, helps us understand what are all things that go on haywire in particular cancer that could potentially be targeted.
5:44
But it doesn't tell us in itself, okay, is that mutation associated with prognosis or is it associated with drug response? Or can we identify that mutation on a H&E image using digital path AI, which I want to touch on today, as well as a really burgeoning area.
5:59
So you really need the spectrum.
6:01
The most powerful application of being able to use H&E develop AI algorithms is having the merger of the genomics along with the clinical data to ask those really important clinical questions.
6:11
So a really great example of a large data set being leveraged for this is a tool we developed called GPS AI.
9:44
All of this data that you've got, where is it useful mainly for carers internally? Where is it useful for the practicing clinician who has to deal with the decision that they have to make for a patient versus actual research? Because there's still a lot of research that needs to go on.
5:19
What are some of the innovations happening from a screening perspective?
5:23
Yeah, absolutely.
5:24
Well, obviously, as you mentioned, the best way to bend the survival curve for this disease is to be able to catch cancer as early as stages.
5:32
We know that when cancer is caught as early as stages, it's much more manageable from a surgery perspective, from a treatment perspective.
5:39
And we know from survival curves these patients obviously have a chance at cure and obviously living longer.
5:46
In my opinion, I think the technology that is going to revolutionize how we do screening is something called multi-cancer early detection or what we call MSED.
5:56
And what these are are tests in particular that take a blood sample, use really sensitive sequencing techniques to identify the presence of a cancer signal.
9:52
And so if there's a positive signal, you can have further tests, right? And so what are some innovations in that realm of initial diagnosis? Are we still quite reliant on the basic that then triages to immunohistochemistry? What's the state of the art

We value your privacy

We use cookies to understand how you use our platform and to improve your experience. Click “Accept All” to consent, or “Decline non-essential” to opt out of non-essential cookies. Read our Privacy Policy.