This is a Python project for lungs cancer detection using a Convolutional Neural Network (CNN) deep model. The project consists of four main parts: building a data pipeline, preprocessing data, building the deep neural network, and evaluating performance.
In this part, the focus is on creating a data pipeline to efficiently handle and process the dataset for lung cancer detection. This involves tasks such as data loading, data augmentation, and data splitting for training and testing.
Preprocessing data is an essential step in any machine learning project. In this part, the project aims to preprocess the lung cancer dataset to prepare it for training the deep neural network. Preprocessing tasks may include data normalization, resizing, and feature extraction.
The core of the project lies in building a deep neural network, specifically a Convolutional Neural Network (CNN), for lung cancer detection. This part involves designing the architecture of the CNN model, defining the layers, and implementing the necessary forward and backward propagation algorithms.
The final part of the project focuses on evaluating the performance of the trained CNN model. This includes testing the model on a separate test set, calculating performance metrics such as accuracy, precision, recall, and F1 score, and visualizing the results. The evaluation helps in understanding the effectiveness and accuracy of the lung cancer detection model.
Before running the project, ensure that the following dependencies are installed:
Dataset can be downloaded through this link https://drive.google.com/file/d/16aD8zoymIpg2V10iRroTu-F8kb3cKjI9/view?usp=sharing
Code can be found through the following link.