Lung Cancer Detection using Neural Network and Content Based Image Retrieval

Abstract

Computer aided detection (CAD) systems that automatically detect and localize lung nodules in CT scans. A major problem in this system is the large number of false positives because of no provision for comparison of the predicted output. This paper commends anewsystemwiththecombination of CBIR and neural network t ofull fill the gap intheareaof early detection of lung cancer. From the preprocessed CT scan image the system identifies whether it contains nodules using Circular Hough Transform and classifies into benign or malignant nodule using Probabilistic Neural Network. Then, it search for the most similar images and retrieved it from the database. From the retrieved image it is easy to identify the present cancer stage of the patient. Experiments done based on both LIDC database and the locally collected database. The performance evaluation of the system is done by using both. The experimental results showsthat the proposed system can easily classify benign and malignant nodules with an efficiency of 97 % accuracy on LIDC dataset, 95 % accuracy on Local dataset and similar images are retrieved with its present stage from the available database with a higher precision and recallrate.