Chest cancer classifier

It was a project about chest cancer detection using machine learning and deep leaning (CNN) . we classify and diagnose if the patient have cancer or not using AI model . We give them the information about the type of cancer and the way of treatment. we tried to collect all data we need to make the model classify the images easily. so i had to fetch data from many resources to start the project . I researched a lot to collect all the data from many resources and cleaned it for the CNN
MOHAMED HANY

Our goal in this project is to build a robust classifier that can predict the type of the tumor

Dataset

Data contain 3 chest cancer types :

Adenocarcinoma
Large cell carcinoma
Squamous cell carcinoma

database is available on Kaggle

API command

kaggle datasets download -d mohamedhanyyy/chest-ctscan-images

Model

for this classification task we will use the Xception model developed by François Chollet

This idea behind the Inception module is to make this process easier and more efficient by explicitly factoring it into a series of operations that would independently look at cross-channel correlations and at spatial correlations. We propose a convolutional neural network architecture based entirely on depthwise separable convolution layers. In effect, we make the following hypothesis: that the mapping of cross-channels correlations and spatial correlations in the feature maps of convolutional neural networks can be entirely decoupled. Because this hypothesis is a stronger version of the hypothesis underlying the Inception architecture, we name our proposed architecture Xception, which stands for “Extreme Inception”.

learn more : Paper

the architecture of the Xception model is given as

Evaluation of the model

epochs	batch size	accuracy on training	accuracy on test
12	32	0.9918	0.8539

use the model

clone the repository

  git clone https://github.com/mohamed-yassine-benkhadda/chest_cancer.git

load the model in a python file

  from tensorflow import keras
  model = keras.models.load_model('model.h5')

enjoy the model
```
  result = model.predict(X)
```