Open AccessLung Tumor Classification on Human Chest X-Ray Using Statistical Modelling Approach
Author(s) -
Nadhiyati Rizka,
Nur Chamidah
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/546/5/052065
Subject(s) - nonparametric statistics , lung cancer , parametric statistics , lung , logistic regression , estimator , parametric model , computer science , medicine , artificial intelligence , pathology , radiology , mathematics , statistics
Lung tumor is a group of abnormal cells that are formed from the process of excessive and uncoordinated cell division in the lung or known as a neoplasia. Neoplasia refers to the growth of new cells that are different from the growth of cells around it. The Tumor can formed to be benign tumors that not cause cancer and malignant tumors that can cause cancer. Chest X-ray is the most technique that used for detecting a lung tumor. Image processing is done by mean for distinguishing the classification lung tumor. Based on previous research the most used method is the mathematical method, but the result obtained are not maximal. Therefore, in this study we propose methods to classify lung tumor by using statistical modelling approach with logit link function based on parametric model, and nonparametric model using penalized spline estimator. Based on the proposed method, we get the classification accuracy of 80% for parametric model approach and 85% for nonparametric model approach, it means that the nonparametric model approach is better than the parametric model approach.