Computer Assisted Detection & Selection of Serrated Adenomas and Neoplastic Polyps - a New Clinical DRAft

Overview

The aim of the study is to develop a computer program which is able to automatically detect colorectal polyps in endoscopic video sequences. Furthermore, the program shall be able to automatically distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features of the polyps. Video sequences of polyps will be collected during routine colonoscopy procedures. All polyps will be resected endoscopically so that histopathological diagnoses (gold standard) can be notified. In the validation phase of the study a computer program will be established which aims to distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features derived from the videos. A deep learning approach will be used for programming. Afterwards, in the testing phase of the study, videos of 100 polyps (not used in the validation phase) will be presented to the computer program. The establishment of a well- functioning computer program is the primary aim of the study.

Adenomas are polyps of the colorectum that have the potential to develop into colon cancer \[1\]. However, some adenomas never become malignant and if they do, progression from adenoma into cancer usually takes a long time. As a result, screening colonoscopy programs were established in order to detect and resect adenomas at an early stage \[2\]. After resection, polyps should be sent to pathology in order to make a histological diagnosis. Not every colorectal polyp has adenomatous histology. Approximately 40-50% of all polyps contain other benign histology (e.g. hyperplastic polyps). These polyps do not bear the risk of colon cancer. The implementation of screening programs has led to increasing numbers of colonoscopies in the last years \[3\]. This approach naturally implies higher amounts of detected polyps. The removal of these polyps and consultation of a pathologist in order to make a diagnosis is time consuming and expensive. An optical- based prediction of polyp histology (adenomatous versus non- adenomatous) would enable endoscopists to save money and to inform patients faster about examination results. The approach of predicting polyp histology on the basis of optical features is called the "optical biopsy" method. The prediction is made by the endoscopists during real-time colonoscopy. The aim of this strategy is to make an optical diagnosis which enables users to resect polyps without sending the specimen to pathology. Narrow Band Imaging (NBI) is a light-filter device which can be switched on during colonoscopy. NBI is useful to better display vascular patterns of the colon mucosa. It has been shown that the use of NBI can facilitate optical classification of colorectal polyps \[5\]. A NBI- based classification schemes exists which can be used to assign polyps into specific polyp categories (adenomatous versus non- adenomatous) \[6\]. Prior to the implementation of the optical classification approach for routine use in endoscopy it is necessary to proof its feasibility and accuracy \[7\]. Otherwise the approach would entail the risk of wrong diagnoses which could lead to wrong recommendations on further diagnostic or therapeutic steps. Until now, some clinical trials have shown good accuracy for the optical biopsy method \[5\]. However, there is growing evidence that optical biopsy does not yet meet demanded accuracy thresholds \[8\]. The aim of our study is to create a computer program that is able to distinguish between adenomas, serrated adenomas and hyperplastic polyps. Video sequences of colorectal polyps will be used for machine learning (validation phase). Afterwards a set of 100 videos will be used to test whether the computer program is able to distinguish between adenomatous and non- adenomatous polyps (primary endpoint). Statistical measures (accuracy, sensitivity, specificity) will be calculated. The 100 videos will also be presented to human experts who will also predict polyp diagnoses based on optical features. Comparing the accuracy of optical predictions made by the computer and by human experts will be another endpoint of the study.