Using Decision Tree With First and Second-Order Statistical Feature Extraction for Classification of Lung Cancer

Mohtar Yunianto (Physics Department, Universitas Sebelas Maret)
Rizka Dewi Meilina (Physics Department, Universitas Sebelas Maret)
Esti Suryani (Informatics Department, Universitas Sebelas Maret)

INDONESIAN JOURNAL OF APPLIED PHYSICS
Vol 14, No 2 (2024): October

The classification of CT-Scan images on images with lung cancer and normal lung has been done by improving the image quality of the median and Gabor filters, extraction of first and second-order statistical features, and decision tree classification. The data used comes from LIDC-IDRI as much as 100 training data and 40 test data. The median filter removes noise without removing edges in the image. A Gabor filter is used to facilitate texture analysis on the image. At the feature extraction stage, statistical variations of the first order, second order statistics and the merging of first and second-order statistics. The best results obtained at the testing stage are program designs with variations of feature extraction combining first and second-order statistics. The level of accuracy obtained is 97.5%, with a sensitivity of 100% and a specificity of 95%.