After the deadline we were able to integrate the AI and host the website. We couldn't host the AI model because the free tier wouldnt allow it and the AI models were quite large, but you can check everything else out. (There are some minor bugs related to styling, but if you enter an image and your email it should work!)
The github repo was updated according to the changes as well.
The images needeed for diagnosis are dermascopy images which need to be taken by a dermatologist. Thus this isn't entirely remote, however by providing a more effective and accurate analysis this could cut down on the number of trips required to the dermatologist and can also be much more convenient and cheaper.
MelanomAI is still a much better alternative to current methods of diagnosis.
There are ways for people to do self dermascopy, but those ideas are still in development. (This could be something we do in another hackathon or after this hackathon to suplement and support this idea)
Melanoma is a deadly skin cancer which affects all ages. It starts off as a cancerous growth but can spread to other parts of the body as well.
The worst part is that Melanoma has a 25 - 30 percent misdiagnosis rate meaning 1 in 4 people have been misdiagnosed with the cancer.
Considering how dangerous and scary cancer can be a 25% misdiagnosis rate is too high.
1 in 4 people should not have to suffer due to an accident that can be avoided.
MelanomAI works to fix this problem by making Melanoma diagnosis easy, fast, and above all accurate.
What it does
MelanomAI is a 6 layer convolutional neural network which can analyze an image to detect and classify melanoma. Convolutional neural networks are very good at analyzing images and giving accurate results. With enough time our team is confident that we could bring accuracy into the mid to high 90’s.
Here’s how it works for the user:
- Go over to our website
- Upload an image of melanoma
- Enter your email
- Check your email for results!
Diagnosing Melanoma accurately is just 5 steps away.
How We built it
We used pytorch to build the AI model and train it.
We used bootstrap, django, css, and html to create the website.
Challenges I ran into
One of our members lost half of their files 3 hours before the hackathon and had to recode all of them.
It was a traumatic experience and was a good learning opportunity on how to store files and use github.
We struggled to actually integrate the AI and the website due to some errors, given some more time we might have been able to fix it.
Accomplishments that I'm proud of
We are proud of our accuracy. We were able to get an extremely high accuracy in such a little timeframe and with more time we are confident we can get the accuracy to above 90%.
We are also proud of our website as this was out first time making an AI and a UI to go along with it in a Hackathon.
What I learned
How to work with AI(Pytorch)
How to use django to build websites.
The benefits of using github as source control and a way to ‘backup’ files.
What's next for MelanomAI
We want to integrate the self standing AI and the website, we faced issues with this part, but given some more time we are confident we would have been able to succesfully integrate the two.
Once we get a complete product we want to host the website to make it available to all, and given that it gains some popularity possible even try to implement it in the real world!