Devpost: https://devpost.com/software/melanomai-gbifmq MelanomaAI: Detecting and classifying Melanoma in an effective manner
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.
MelanomAI analyzes the image of suspected melanoma to detect whether or not it is melanoma. Once the analysis is complete the user gets and email confirming their results where they can then seek out the proper help based on the diagnosis.
Diagnosing Melanoma just needs 3 steps. Upload an image, enter your email, and click submit.
MelanomaAI is faster than modern day diagnosis and is also more accurate. It bring down the 1 in 4 number to about 3 in 20 an almost 70% imporvement.
We used pytorch to build the AI model and train it.
We used bootstrap, django, css, and html to create the website.
(Note: The AI and website work on their own, we have yet to integrate the 2)
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 are proud of our accuracy. The AI turned out to be more accurate then proffesionals which was a big surprise and we are glad they we could make it so accurate.
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.
We wish we could have integrated the two fully. Given 1 - 2 more hours it should have been possible to have a completely ready product.
How to work with AI(Pytorch)
How to use django.
Integrating the AI into the website so that it actually predicts based on image. The AI can do that right now but it isn't integrated with the website so the Demo was based off of a prewritten message and just a random image submit. The AI does work however, its just a matter of integration.
We want to host the website to make it available to all!