For patients receiving medical care for cancer, a diagnosis marks the beginning of their journey. Prosciaa downtown-based company, is on a mission to change the way the world practices pathology – which is at the heart of establishing a diagnosis – through digitization and artificial intelligence.
“At Proscia, we work to help pathologists improve cancer diagnosis so they can speed up turnaround times and achieve the best patient outcomes,” said Sean Grullonsenior researcher in artificial intelligence at Proscia.
The company’s products include Concentric, its digital pathology platform and a variety of AI tools. In October 2021, Proscia released the results of a study that looked at the technology that powers its DermaAI.* Performed at Thomas Jefferson University and University of Floridathe study confirmed that Proscia’s AI identified melanoma, the deadliest form of skin cancer, with a high degree of accuracy.
Proscia’s AI team is split between its engineering team and its research team. Grullon leads the research team, developing the strategy that guides the engineers’ development of Proscia’s AI tools.
Grullon, who has 12 years of experience in particle physics research, joined Proscia in March 2021. What attracted him to this fast-growing, venture-backed company? He said one main thing came to mind – the mission.
Technically spoke with Grullon about his professional journey, current role and the implications of using artificial intelligence in healthcare. (Spoiler: he’s pro-AI.)
First of all, how did you start working in AI?
I fell into AI by accident. I first moved to Philadelphia to become a physics teacher. I have a doctorate. in particle physics, which is a pretty abstract view of physics that just tries to figure out what the universe is made of. Then I decided that I no longer wanted to be in academia for various reasons, but wanted to stay in Philadelphia. I was lucky because around that time the field of AI in life sciences and healthcare really started to take off.
How did you manage to move from physics to AI?
Much of the math behind AI and its algorithms is very similar to the math that drives many physical applications. The irony of particle physics is that to study things that are really small, you have to build things that are really big, and the really big things that you build collect a lot of data. So I gained some experience with machine learning and different data algorithms through my academic career in physics.
I read research papers for more background information, and also packed some of my physics papers so I could use them as an example for future employers when I first applied for jobs. jobs in this field.
Tell me more about Proscia’s AI research team.
Right now, I have four direct reports. We use the Agile working system and I like to give them space to complete their projects. We stay in touch with daily 15-minute team standups and bi-weekly one-on-ones.
As a manager, I believe in empowering my team. In the entrepreneurial spirit of Proscia, I want to encourage all team members to feel like they own the business and are in charge of the business. They don’t work for me, do they? We work collectively together to support this mission.
As someone who works in this space every day, what does AI in healthcare mean to you?
When you talk about AI in healthcare, you feel like robot doctors are replacing real doctors and you fear what happens in sci-fi movies. But the reality is that AI is there to help doctors. In fact, there is a shortage of doctors, and AI can allow them to focus their time where it matters most.
This is especially true when it comes to pathologists. Pathologists are really important because they are the ones who examine a biopsy to determine if it is cancerous or not, but the population has been steadily declining for years. AI can help them work more efficiently, and time is running out, especially when it comes to cancer.
It’s not a direct comparison, but it’s like how Google Maps makes you more efficient at finding directions to get from home to work. It’s more efficient than using a printed map, isn’t it? That’s what we do, but instead we help pathologists be more efficient in the interest of patient care. This is one of our main goals at Proscia.
*DermAI is for research use only.