Skin Lesion Images classification

[aaradhyasinghgaur]

Is your feature request related to a problem? Please describe. To classify between differnt skin lesions . The dataset for ISIC 2019 contains 25,331 images available for the classification of dermoscopic images among nine different diagnostic categories:

• Melanoma
• Melanocytic nevus
• Basal cell carcinoma
• Actinic keratosis
• Benign keratosis (solar lentigo / seborrheic keratosis / lichen planus-like keratosis)
• Dermatofibroma
• Vascular lesion
• Squamous cell carcinoma

• None of the above`

  dataset I'll use :- https://www.kaggle.com/datasets/salviohexia/isic-2019-skin-lesion-images-for-classification

Describe the solution you'd like

1. Data Preparation: Collect and preprocess a balanced dataset of real and fake face images, including normalization, resizing, and augmentation.
2. Base Model Selection: EfficientNetB0,VGG16 , Xception , InceptionV3 like 5 different models excluding its top layers, to leverage its learned features.
3. Model Construction: Add custom layers on top of the base model for binary classification, compiling with appropriate loss and metrics.
4. Initial Training: Train the model with the base layers frozen to only update the new layers.
5. Fine-Tuning: Unfreeze some or all of the base model layers and continue training with a lower learning rate to fine-tune the entire network. 6.) EDA analysis. 7.) Comaprioson using performance matrices such as accuracy scores , confusion matrix etc.

Describe alternatives you've considered A clear and concise description of any alternative solutions or features you've considered.

Additional context Add any other context or screenshots about the feature request here.

@TAHIR0110 kindly assign me this issue.

[TAHIR0110]

@kyra-09 assigned!