To build a CNN based model which can accurately detect melanoma. Melanoma is a type of cancer that can be deadly if not detected early. It accounts for 75% of skin cancer deaths. A solution that can evaluate images and alert dermatologists about the presence of melanoma has the potential to reduce a lot of manual effort needed in diagnosis.
- The project is built using tensorflow CNN
- The Project dataset include 9 types of different skin diseases. CNN Model is used to detect Melanoma
- We built 3 Different Model
- First Model was a overfit with Training Accuracy of 0.95 and validation of around 0.55
- We fixed this Model overfit, we added additional neural network and dropout layers, which handled overfitting.
- Since the data was skewed for number samples to train on was limited and hence we agumented data and achived a accuracy: 0.8027 and val_accuracy: 0.7988
- Tensorflow - version 2.8.0
Created by [@yashyennam] - feel free to contact me!