INTELLIGENT BIOMEDICAL MEASUREMENT SYSTEM

Abstract

Early diagnosis of various diseases significantly improves survival. However, more than half of these cases are diagnosed late due to the high demand for colonoscopy - the "gold standard" of screening. Colonoscopy is limited by the outdated design of conventional endoscopes due to the high complexity and cost of use. Magnetic endoscopes are a promising alternative and overcome the cost disadvantages, but their translational phase is difficult to achieve because magnetic manipulations are complex and unintuitive. In this work, we use machine vision to develop an intelligent and autonomous endoscope control that allows non-expert users to efficiently perform in vivo magnetic colonoscopy. We combine the use of robotics, computer vision, and advanced control to offer an intuitive and efficient endoscopic system. Furthermore, we define the characteristics required to achieve autonomy in robotic endoscopy. The paradigm described here can be applied to a variety of applications requiring navigation in an unstructured environment, such as catheters, pancreatic endoscopy, bronchoscopy, and gastroscopy. This work brings alternative endoscopic technologies closer to the translational stage, increasing the availability of early disease treatment. Keywords: endoscope models, portable, capsule, mobile systems, mobile devices, picture completeness, modern technology