Our application seeks to provide a user-friendly platform where users can upload images of skin lesions or tumors for an instantaneous, preliminary analysis. Our model is trained on a myriad of skin tumor images to identify and categorize skin abnormalities with a high degree of accuracy. Upon uploading an image, the web app conducts a thorough analysis and provides immediate feedback on the characteristics of the lesion, categorizing it into potential risk categories. This instant, accessible, and user-friendly tool is designed to be an ally in raising awareness and promoting early detection of skin cancer. While the model aspires to be a helpful tool in skin abnormality detection, it firmly stands as an aid and not a substitute for professional medical diagnosis. Although our model is far from robust and an initial effort to identify them, we hope it is a decent foundation and can be bettered with more in depth data and better resources/systems/infrastructure.
Built With
- cnn
- colab
- kaggle
- python
- streamlit
- tensorflow
Log in or sign up for Devpost to join the conversation.