Early Lung Cancer Detection by Using Artificial Intelligence System

Author First name, Last name, Institution

Fatma Taher, Zayed UniversityFollow

Document Type

Book Chapter

Source of Publication

EAI/Springer Innovations in Communication and Computing

Publication Date

1-10-2023

Abstract

Lung cancer is by far the primary cause of cancer deaths globally. Computer-aided diagnosis (CAD) system is used for the prediction of lung cancer which helps to attain a high detection rate and reduces the time consumed for analyzing the sample. In this paper, CAD system based on sputum color images is proposed which consists of four main processing steps. It starts with the preprocessing step using a heuristic rule-based and a Bayesian classification method using the histogram analysis. In this step, the region of interest (ROI) representing the sputum cell is detected and extracted. In order to segment the nuclei from the cytoplasm, mean shift segmentation is used. The next step is feature analysis. Finally, the diagnosis is done using a rule-based algorithm alongside the artificial neural network (ANN) and support vector machine (SVM) for identifying cancerous and non-cancerous cells. The performance evaluation was done based on the sensitivity, specificity, and accuracy. Our methods are validating by using a set of experiments conducted with a data set of 100 images. The final results showed that the techniques used outperformed conventional methods. The proposed CAD system achieved a reasonable accuracy above 95% with high true positive rates that can basically meet the requirement of clinical diagnosis.

ISBN

978-3-031-15815-5, 978-3-031-15816-2

ISSN

2522-8609

Publisher

Springer International Publishing

First Page

373

Last Page

397

Disciplines

Computer Sciences | Medicine and Health Sciences

Keywords

Lung cancer, Bayesian, Artificial neural network

Indexed in Scopus

no

Open Access

no

Share

COinS