armin-abdollahi/brain-tumor-diagnosis

Brain tumor detection with CNN model on Kaggle dataset

Brain-Tumor-Diagnosis

Dataset Link

https://www.kaggle.com/datasets/navoneel/brain-mri-images-for-brain-tumor-detection

Dataset Description

The dataset has 253 samples, which are divided into two classes with tumor and non-tumor. The number of people with brain tumor is 155 and people with non-tumor is 98.

A summary of the CNN model

Training

• The optimizer is set to Adam.
• The loss function is set to binary cross-entropy, which is used for binary classification problems.
• The evaluation criterion is set to accuracy, which is used to measure the performance of the model during training and testing.
• The batch_size parameter specifies the number of samples per gradient update.
• The epochs parameter specifies the number of iterations in the entire training dataset.
• The validation_data parameter specifies the validation data used during training.
• The model is trained for 22 epochs, which means it is repeated 22 times on the entire training dataset.
• During training, the performance of the model is evaluated based on the validation data. This helps prevent overfitting and ensures that the model generalizes well to new data.

Results

Accuracy	Loss