DataMinds/cnn_brain_tumor_classification

Brain tumor classification using CNN

Model Details

Model Description

model.summary()
Out:
Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 rescaling (Rescaling)       (None, 200, 200, 1)       0         
                                                                 
 conv2d (Conv2D)             (None, 200, 200, 16)      160       
                                                                 
 max_pooling2d (MaxPooling2D  (None, 100, 100, 16)     0         
 )                                                               
                                                                 
 conv2d_1 (Conv2D)           (None, 100, 100, 32)      4640      
                                                                 
 max_pooling2d_1 (MaxPooling  (None, 50, 50, 32)       0         
 2D)                                                             
                                                                 
 conv2d_2 (Conv2D)           (None, 50, 50, 64)        18496     
                                                                 
 max_pooling2d_2 (MaxPooling  (None, 25, 25, 64)       0         
 2D)                                                             
                                                                 
 flatten (Flatten)           (None, 40000)             0         
                                                                 
 dense (Dense)               (None, 128)               5120128   
                                                                 
 dense_1 (Dense)             (None, 64)                8256      
                                                                 
 dense_2 (Dense)             (None, 128)               8320      
                                                                 
 dense_3 (Dense)             (None, 64)                8256      
                                                                 
 dense_4 (Dense)             (None, 32)                2080      
                                                                 
 dense_5 (Dense)             (None, 96)                3168      
                                                                 
 dense_6 (Dense)             (None, 96)                9312      
                                                                 
 dense_7 (Dense)             (None, 128)               12416     
                                                                 
 dense_8 (Dense)             (None, 1)                 129       
                                                                 
=================================================================
Total params: 5,195,361
Trainable params: 5,195,361
Non-trainable params: 0
_________________________________________________________________

Dataset

The dataset is composed of Brain Tumor Classification (MRI) and Brain MRI Images for Brain Tumor Detection

Using image data augmentation we get 199.632 files belonging to 2 classes.

train-test-split: 80/20

Training (159705 files):

• Using 143735 files for training
• Using 15970 files for validation

Test/Validation:

• 39927 files

Training

Coming Soon

Validation

Coming Soon

Hardware

Lenovo Thinkpad P14s

• CPU (# Cores/Threads): AMD Ryzen 7 PRO 5850U (8/16)
• RAM: 32 GB

Software

DataSpell 2023.1.2

• Python 3.10.9
• Tensorflow 2.12.0