Razi Journal of Medical Sciences

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

---

 
Background: Lung cancer was known as primary cancers. Early detection of lung cancer reduces the length of treatment and spends a great deal of cost on the survival and survival of the individual. In recent years, the use of computer techniques in the use of data mining and intelligent algorithms has accelerated the early diagnosis of this cancer. The purpose of this paper is to evaluate the role of the new method based on Principal Component Analysis and Multi-Layer Perceptron with Genetic Algorithm optimization for Diagnosis of Lung Cancer.
Methods: In this study, the lung cancer dataset used was taken from the UCI machine learning database, including 32 patient records with 57 features. After performing its preprocessing steps, in the process of extraction of features and reduction of data dimensions, the main data of lung cancer were reduced to 17 characteristics using a basic component analysis. Then, in the classification step, these characteristics were reduced to multilayer perceptron by optimizing the genetic algorithm and the sensitivity and specificity of the model were studied according to the accuracy, sensitivity and Specificity. All analysis and synthesis were performed using the software of MATLAB and SPSS.
Results: For the proposed model, the results of the simulations were the mean of classification accuracy, sensitivity and specificity, respectively, 98.86, 98 and 99.16%.
Conclusion: The results on real data indicate that the proposed system is very effective in the diagnosis of lung cancer and can be used for clinical applications.

Keywords: Lung cancer, Principal Component Analysis, Artificial neural network, Multilayer perceptron, Genetic Algorithm

Full-Text [PDF 1170 kb]   (1943 Downloads)    

Add your comments about this article : Your username or Email:

---

---