Deep Learning Based Lung Cancer Prediction Using CNN

Lung cancer remains a leading cause of global morbidity and mortality, necessitating advanced diagnostic tools for early detection and intervention. This project introduces a novel approach to lung cancer prediction by leveraging Convolutional Neural Networks (CNN) on lung X-ray images. The CNN model is trained to classify lung X-rays into four categories: adenocarcinoma, large cell carcinoma, normal, and squamous cell carcinoma. The methodology involves preprocessing of lung X-ray images, feature extraction using CNN layers, and classification through a carefully designed neural network architecture. The model's training is based on a dataset encompassing a diverse range of cases, facilitating robust learning and accurate predictions. The significance of this project lies in its potential to enhance early detection and streamline diagnosis, leading to timely medical interventions. By automating the categorization of lung cancer types through CNN analysis of chest X-rays, this system aims to contribute to the efficiency of healthcare services and improve patient outcomes. The evaluation of the proposed model involves comprehensive performance metrics, including accuracy, sensitivity, specificity, and precision. Results from extensive testing on diverse datasets showcase the model's efficacy in distinguishing between various lung cancer types and identifying normal cases.