Inspiration
There are many people who cannot afford to go to a dermatologist, but they still need some kind of medical support. So, I made an app that is very easy to use and easily available, so that people who are poor can still stand a chance against cancer.
What it does
It takes a picture of a mole on your body and runs it through a binary deep neural network which gives an output that whether the mole is malignant or benign.
How I built it
I first built the neural network using Tensorflow. Then, I converted it into a tflite model so I can use it in an app. After building an app with flutter and dart I used the model with the app. The app can work offline too.
Challenges I ran into
I had a bit of difficulty in connecting different parts.
Accomplishments that I'm proud of
I am proud that the app is ready also the website had a pretty great design.
What I learned
I do not have much experience with flutter and dart, but I learned quite a bit while making the app.
What's next for DocDer
I think I will try to increase the model's accuracy and also make the interface more user-friendly.
Built With
- css3
- dart
- flutter
- html5
- keras
- machine-learning
- python
- tensorflow



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