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

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