A Survey on Object Detection, Annotation and Anomaly Detection Methods for Endoscopic Videos

摘要

Endoscopy is a minimally invasive and non-surgical procedure that is used for the imaging and examination of the human body to study internal organs in detail to detect and understand anomalies. The method of drawing insights from endoscopic procedures for analysis and therapeutic purposes is currently fully reliant on the Doctor’s knowledge and experience. Thus in rural areas several diseases go undetected and untreated. Our objective is to understand the current research, methods and technology used for endoscopic video annotation and analysis which has been extrapolated to a detailed literature survey of automatic anomaly detection as well as object detection in the context of annotation of live endoscopic videos. This will serve the purpose of analysing the merits and demerits of existing research in this domain which can be leveraged to recommend the best methods and technology to aid the current manual process. This will not only assist in reducing the dependence on experienced human medical care but will also aid the development of solutions for effective automated analysis and real-time feedback which can provide assistance to the surgeon for better visualization and therapy.