The number of people with lung cancer has reached approximately 2.09 million people worldwide. Out of 9.06 million cases of death, 1.76 million people die due to lung cancer. Lung cancer can be automatically identified using a computer-aided diagnosis system (CAD) such as image processing. The steps taken for early detection are pre-processing feature extraction, and classification. Pre-processing is carried out in several stages, namely grayscale images, noise removal, and contrast limited adaptive histogram equalization. This image feature extracted using gray level co-occurrence matrix (GLCM) and classified using 2 method of neural network which is feed forward neural network (FFNN) dan feed backward neural network (FBNN). This research aims to obtain the best neural network model to classify lung cancer a. Based on training time and accuracy, the best method of FFNN is kernel extreme learning machine (KELM), with a training time of 12 seconds and an accuracy of 93.45%, while the best method of FBNN is Backpropagation with a training time of 18 minutes 04 seconds and an accuracy of 97.5%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.