Analysis of New Endoscopic Features and Variable Stiffness in Colonoscopy: Prospective Randomised Trial

The aim of the present study is to develop and evaluate a computer-based methods for automated and improved detection and classification of different colorectal lesions, especially polyps. For this purpose first, pit pattern and vascularization features of up to 1000 polyps with a size of 10 mm or smaller will be detected and stored in our web based picture database made by a zoom BLI colonoscopy. These polyps are going to be imaged and subsequently removed for histological analysis. The polyp images are analyzed by a newly developed deep learning computer algorithm. The results of the deep learning automatic classification (sensitivity, specificity, negative predictive value, positive predictive value and accuracy) are compared to those of human observers, who were blinded to the histological gold standard.
In a second approach we are planning to use LCI of the colon, rather than the usual white light. Here, we will determine, whether this technique could improve the detection of flat neoplastic lesions, laterally spreading tumors, small pedunculated adenomas and serrated polyps. The polyps are called serrated because of their appearance under the microscope after they have been removed. They tend to be located up high in the colon, far away from the rectum. They have been definitely shown to be a type of precancerous polyp and it is possible that using LCI will make it easier to see them, as they can be quite difficult to see with standard white light.