Inspiration
42,000 women die annually (U.S) from Breast Cancer. 13% of women will be diagnosed with Breast Cancer at some point in their lives.
In the U.S., mammograms are a vital part of their healthcare, but due to a lack of resources, patients who receive mammograms are often left with more questions than answers.
What it does
By combining Computer Vision, generative AI, and an accessible user interface, Mammo gives women more agency in their own wellbeing.
With Mammo, rather than being a passive bystander, users are empowered to drive the conversation around their own healthcare.
Mammo is a comprehensive application, featuring a computer vision-powered mammogram scan and a generative AI chatbot tailored to answer and recommend steps for patients. Rather than only recommending steps, Mammo makes it easy to instantly take action by providing relevant URLs and links for the suggested action, seamlessly connecting the advice to practical implementation.
Mammo represents the next step in healthcare: AI-enhanced care.
How we built it
Our tech stack is cutting edge. The frontend tech stack features Shadcn, Tailwind CSS, React, Next.js, and Typescript. The backend utilizes Node.js, TRPC, Typescript, FastAPI, Python, Gemini, and PyTorch.
Challenges we ran into
Difficulties finding and training a mammogram CV model. Working with little sleep.
Accomplishments that we're proud of
Figuring out the CV model proved to be the biggest challenge of the entire project. So, making something that worked was something we're very proud of.
What we learned
Kevin without sleep is a whole other Kevin.
What's next for Mammo
We want to implement a way to export and present your screenings and history to doctors to make the conversation around our health easier to start.
Built With
- fastapi
- figma
- next.js
- python
- react
- shadcn
- trpc
- typescript
- zod



Log in or sign up for Devpost to join the conversation.