Title: An exhaustive study on the lung cancer risk models

Authors: Malayil Shanid; A. Anitha

Addresses: Department of Computer Science and Engineering, Noorul Islam Centre for Higher Education, Kanyakumari District, Tamil Nadu, 629180, India ' Information & Communication Engineering, Noorul Islam Centre for Higher Education, Kanyakumari District, Tamil Nadu, 629180, India

Abstract: One of the critical cancers leading to an upsurging rate of mortality is lung cancer. The Computed Tomography (CT) is the vastly adopted technique for effective cancer detection and risk assessment. The mortality rate and the intrusive surgery can be reduced through the risk assessment of cancer at the earlier stages. Hence, an essential lung cancer detection technique must be modelled for the risk assessment of cancer at the earlier stages. This review paper is made by carrying out a detailed survey on 40 research works presenting the existing lung cancer detection methodologies. Also extensive analysis and discussion is made with respect to the publication year, adopted detection schemes, evaluation metrics, utilised datasets, a simulation tool, accuracy range, and the extracted features. Subsequently, the research gaps and issues of the distinct lung cancer detection schemes are elucidated for directing the researchers to a better contribution of effective cancer risk assessment.

Keywords: lung cancer; computed tomography; SVM; support vector machine; accuracy; risk assessment; cancer detection; mortality rate; features; datasets; research gaps.

DOI: 10.1504/IJBRA.2020.108429

International Journal of Bioinformatics Research and Applications, 2020 Vol.16 No.2, pp.151 - 172

Received: 04 Jul 2018
Accepted: 03 Apr 2019

Published online: 05 Jul 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article