OncoVision

Inspiration

We were inspired by the uses of AI in the medical field we had heard about before the hackathon, in addition to the various lectures that got us thinking about how we could leverage emerging technologies through e-med.

What it does

Provides a convenient interface where users can snap a picture and get a preliminary cancer analysis.

How we built it

We used Svelte, Tailwind, and shadcn-svelte for the frontend. We used TensorFlow for our machine learning and computer vision analysis on the backend.

Challenges we ran into

We had a big challenge with implementing multiple types of cancer analysis at the same time, along with connecting our frontend to the TensorFlow backend.

Accomplishments that we're proud of

We are proud of being able to implement an advanced ML model into a polished frontend UI in the limited amount of time we had.

What we learned

We learned a lot about training computer vision and prediction models, exchanging info between the frontend and backend, along with many new concepts on the frontend.

What's next for OncoVision

We look forward to expanding the scope of our app with additional medical datasets and types of cancer analysis. For example, datasets based off of hospital scans that are more oriented towards medical professionals.

Built With

• shadcn
• svelte
• tailwind
• tensorflow