Automated Bowel Polyp Detection Based on Actively Controlled Capsule Endoscopy: Feasibility Study.

Manh Cuong Hoang,Kim Tien Nguyen,Jayoung Kim,Jong-Oh Park,Chang-Sei Kim

doi:10.3390/diagnostics11101878

Manh Cuong Hoang, Kim Tien Nguyen + Show 3 more

Open Access

https://doi.org/10.3390/diagnostics11101878

Copy DOI

Journal: Diagnostics	Publication Date: Oct 12, 2021
Citations: 9	License type: CC BY 4.0

Affiliation: Chonnam National University

Abstract

This paper presents an active locomotion capsule endoscope system with 5D position sensing and real-time automated polyp detection for small-bowel and colon applications. An electromagnetic actuation system (EMA) consisting of stationary electromagnets is utilized to remotely control a magnetic capsule endoscope with multi-degree-of-freedom locomotion. For position sensing, an electronic system using a magnetic sensor array is built to track the position and orientation of the magnetic capsule during movement. The system is integrated with a deep learning model, named YOLOv3, which can automatically identify colorectal polyps in real-time with an average precision of 85%. The feasibility of the proposed method concerning active locomotion and localization is validated and demonstrated through in vitro experiments in a phantom duodenum. This study provides a high-potential solution for automatic diagnostics of the bowel and colon using an active locomotion capsule endoscope, which can be applied for a clinical site in the future.

Highlights

As a result of the behavior examination of the electromagnetic actuation system (EMA) system, we experias a result of the behavior examination of the EMA system, we experimentally explored mentally explored that a ratio of magnetic field B and gradient field (in Tesla that a ratio of magnetic field B and gradient field of 1:10 per meter) of 1:10 resulted in a high uniformity of the magnetic field in the region of interest (ROI) and precise resulted in a high uniformity of the magnetic field in the ROI and precise control
YOLOv3 is built on a Darknet53 backbone network used to extract features
In this study,above, we addressed a complete methodology capable of autonomous abnorpositiondetection of the capsule with captured the polyp as historical for mality in the endoscope small bowel andacolon withimage activeoflocomotion and positiondata recogthe intervention

Summary

Introduction

This study provides a high-potential solution for automatic diagnostics of the bowel and colon using an active locomotion capsule endoscope, which can be applied for a clinical site in the future. Small-bowel tumors have over 40 different histological types, in which adenocarcinoma has been the most dominant histology of all time, followed by the carcinoid, the lymphoma, and the sarcoma [4]. These tumors arise in all three sections of the small bowel with a 60% distribution rate in the duodenum, followed by the jejunum with 25% to 29% and 10% to 13% in the ileum [2].

Methods

Results

Conclusion