Residue detection in the large intestine from colonoscopy video using the support vector machine method

As colonoscopy is the gold standard screening test for colorectal cancer, studies of applying image processing to colonoscopy video are increasing. When performing colonoscopy or applying image processing to colonoscopy video, the presence of a residue in the large intestine is a negative affecting factor. In this reason, the colonoscopist evaluates and records the colon cleanliness after performing colonoscopy. However, these assessments can be influenced by the subjectivity of the colonoscopist. In order to quantify the frequency of residues in the large intestine, we applied image processing and machine learning techniques to the digital images obtained from colonoscopy. Support vector machine technique was applied to distinguish informative frames from colonoscopy videos, and to classify residue frames and the others. The sensitivity, specificity, and accuracy were evaluated for five patients.