Gray Level Co-Occurrence Matrices and Support Vector Machine for Improved Lung Cancer Detection

Authors

DOI:

https://doi.org/10.3991/ijoe.v19i05.35665

Keywords:

CTScan, GLCM, Lung cancer detection, Support Vector Machine

Abstract


A detection system based on digital image processing and machine learning classification was developed to detect normal and cancerous lung conditions. 340 data from LIDC –IDRI were processed through several stages. The first stage is pre-processing using three filter variations and contrast stretching, which reduce noise and increase image contrast. The image segmentation process uses Otsu Thresholding to clarify the ROI of the image. The texture feature extraction with GLCM was applied using 21 feature variations. Data extraction is used as a label value learned by the classification system in the form of SVM. The results of the training data classification are processed with a confusion matrix which shows that the high pass filter has higher accuracy than the other two variations. The proposed method was assessed in terms of accuracy, precision and recall. The model provided an accuracy of 99.67 % training data and 97.50 % testing data.

Author Biographies

Mohtar Yunianto, Yunianto

Assistant Professor in Medical Physics with ID SCOPUS 57190936216

A. Suparmi, Physics Department, Universitas Sebelas Maret

Professor in Theory and Computational Physics with ID SCOPUS 7409510765

C. Cari, Physics Department, Universitas Sebelas Maret

Professor in Optic and Computational Physics with ID SCOPUS 33267518100

Tonang Dwi Ardyanto, Clinical Pathology Department, Universitas Sebelas Maret

Associate Professor in Clinical Pathology with ID SCOPUS 6507015742

Downloads

Published

2023-04-27

How to Cite

Yunianto, M., Suparmi, A., Cari, C., & Dwi Ardyanto, T. (2023). Gray Level Co-Occurrence Matrices and Support Vector Machine for Improved Lung Cancer Detection. International Journal of Online and Biomedical Engineering (iJOE), 19(05), pp. 129–145. https://doi.org/10.3991/ijoe.v19i05.35665

Issue

Section

Papers