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.
- Actinic keratosis
- Basal cell carcinoma
- Dermatofibroma
- Melanoma
- Nevus
- Pigmented benign keratosis
- Seborrheic keratosis
- Squamous cell carcinoma
- Vascular lesion
- python - version 3.8
- tensorflow - version 2.8.0
- pandas
- numpy
After done Class imbalance our model accuracies get increase both validation and train accuracies
The final accuracy i get for train data is 96 and val accuracy as 85
This one is may seen like a overfitting because it has nealy 11% difference, because the epoch which we used is only 30, if we increase that may val accuracy is also will increase, but that need some computational power
After handled imbalance my accuracies get increased
The project done by Tosif Khan