Dr.S.Pathur Nisha , S.Srividhya, Dr V S Thangarasu
Convolution Deep Learning, Lung Cancer Detection, and Neural Network
The majority of deaths in both men and women are caused by lung cancer, one of the deadliest cancers in the nation. 10% to 20% of lung cancer patients only have a five-year survival rate. The death rate can be reduced, though, if lung cancer is found early and treated right away. It is a highly challenging assignment for radiologists, but many nations have developed screening programmes to promote early identification of lung cancer from Computed Tomography (CT) pictures. It takes a lot of time to manually identify malignant lung nodules from these CT pictures. The clinical response to therapy may differ and can have a very favourable response when lung cancer is discovered early during the screening phase. A trustworthy, automated method may be very beneficial in both rural and early-stage lung cancer identification. A recent development in medical image analysis, particularly for lung cancer, is deep learning. The focus of the work that has been presented is on fusing clinical practises with deep learning algorithms to help radiologists diagnose pulmonary nodules and eliminate most false-negative images in lung cancer screening. The availability of a vast amount of data for training and testing is the primary factor contributing to the higher success rate of deep learning algorithms in medical imaging. A variety of datasets are available for the detection of lung cancer nodules, enabling deep learning to boost screening operations' efficiency and ultimately contributing to a decrease in lung cancer mortality and benefiting individuals in remote areas. Numerous studies have been done on identifying and classifying lung cancer, but the precision needed to apply such models for clinical applications and for radiologists to diagnose the carcinoma remains a significant barrier. The goal of transfer learning is to transfer information from one domain to another. It is a deep learning approach where characteristics from the source problem are applied to a different but related target problem. For achieving better accuracy, the research work presented functioning of pre-trained models MobileNet, Xception and VGG-16 for finding of lung cancer nodules from lung CT images. The dataset was collected from the LIDC-IDRI da
Article Details
Unique Paper ID: 158798

Publication Volume & Issue: Volume 9, Issue 10

Page(s): 748 - 754
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews