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

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1878
Author(s):  
Manh Cuong Hoang ◽  
Kim Tien Nguyen ◽  
Jayoung Kim ◽  
Jong-Oh Park ◽  
Chang-Sei Kim
Keyword(s):  
Real Time ◽  
Electronic System ◽  
Colorectal Polyps ◽  
Capsule Endoscope ◽  
Polyp Detection ◽  
Position Sensing ◽  
Actuation System ◽  
Electromagnetic Actuation System ◽  
Active Locomotion

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.

scholarly journals The Assessment of the Colo-rectal Polyps in Order to the New Diagnostic and Therapeutic Strategies

2015 ◽  
Vol 61 (3) ◽  
pp. 161-164
Author(s):  
Diac Andreea Raluca ◽  
Brusnic Olga ◽  
Gabos Gabriella ◽  
Onisor Danusia ◽  
Drasoveanu Silvia Cosmina ◽  
...  
Keyword(s):  
Real Time ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Colorectal Polyps ◽  
Tubular Adenoma ◽  
Polyp Detection ◽  
Time Prediction ◽  
Predominant Type ◽  
Polyp Detection Rate ◽  
Rectal Polyps

Abstract Objective. Assessment of the histological and endoscopic features of the colo-rectal polyps is requered for the application of the new diagnostic and therapeutical strategies in the managment of the diminutive polyps. Methods. This paper is a descriptive retrospective study on 52 pacients reffered for colonoscopy in Gastroenterology Clinic – Clinical County Hospital Targu Mures from January until September 2014. 80 polyps were assessed. Narrow band imaging examination targeted on the protrusive lezions allowed NICE (Narrow Band Imaging International Colorectal Endoscopic) classification and corroboration of the histology prediction and pathological assessment. Results. Polyp detection rate was 48,58%, given the quality of bowel preparation in hospital fair in 84,5%. The predominant histological type was the tubular adenoma (46,25%), and 40% of the polyps were located in the sigmoid. Among the diminutive polyps, 58,33% were hyperplastic(p<0,0001), mainly in the recto-sigmoid (66,67%); the incidence of high grade displasia or cancer was 0. Real –time prediction of the histology of the colorectal polyps using NBI established: NICE 1: 19 polpyps, histology- 16 hyperplastic, (p<0,0001, sensitivity: 100%, specificity: 95%), NICE 2: 59 polyps, histology- 53 adenomatous, (p<0,0001, sensitivity: 96%, specificity: 76%), NICE 3: 2 polyps- histology-cancer. Conclusions. We did not observe any distribution pattern in the topography of the diminutive polyps. Histologicaly the predominant type was the hyperplastic type. NBI was accurate in real-time prediction of the histology of the colo-rectal polyps. The results are relevant for application of the new strategies in the managment of the diminutive polyps.

Active locomotion of a paddling-based capsule endoscope in an in vitro and in vivo experiment (with videos)

2010 ◽  
Vol 72 (2) ◽  
pp. 381-387 ◽  
Author(s):  
Hee Man Kim ◽  
Sungwook Yang ◽  
Jinseok Kim ◽  
Semi Park ◽  
Jae Hee Cho ◽  
...  
Keyword(s):  
Capsule Endoscope ◽  
In Vivo Experiment ◽  
Active Locomotion

scholarly journals Real-time monitoring of liver fibrosis through embedded sensors in a microphysiological system

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Hafiz Muhammad Umer Farooqi ◽  
Bohye Kang ◽  
Muhammad Asad Ullah Khalid ◽  
Abdul Rahim Chethikkattuveli Salih ◽  
Kinam Hyun ◽  
...  
Keyword(s):  
Cell Culture ◽  
Liver Fibrosis ◽  
Real Time ◽  
Hepatic Fibrosis ◽  
Transforming Growth Factor ◽  
Cell Monolayer ◽  
Embedded Sensors ◽  
Matrix Deposition ◽  
Tgf Β1

AbstractHepatic fibrosis is a foreshadowing of future adverse events like liver cirrhosis, liver failure, and cancer. Hepatic stellate cell activation is the main event of liver fibrosis, which results in excessive extracellular matrix deposition and hepatic parenchyma's disintegration. Several biochemical and molecular assays have been introduced for in vitro study of the hepatic fibrosis progression. However, they do not forecast real-time events happening to the in vitro models. Trans-epithelial electrical resistance (TEER) is used in cell culture science to measure cell monolayer barrier integrity. Herein, we explored TEER measurement's utility for monitoring fibrosis development in a dynamic cell culture microphysiological system. Immortal HepG2 cells and fibroblasts were co-cultured, and transforming growth factor β1 (TGF-β1) was used as a fibrosis stimulus to create a liver fibrosis-on-chip model. A glass chip-based embedded TEER and reactive oxygen species (ROS) sensors were employed to gauge the effect of TGF-β1 within the microphysiological system, which promotes a positive feedback response in fibrosis development. Furthermore, albumin, Urea, CYP450 measurements, and immunofluorescent microscopy were performed to correlate the following data with embedded sensors responses. We found that chip embedded electrochemical sensors could be used as a potential substitute for conventional end-point assays for studying fibrosis in microphysiological systems.

Real-time quantitative monitoring of in vitro nasal drug delivery by a nasal epithelial mucosa-on-a-chip model

2021 ◽  
Author(s):  
Hanieh Gholizadeh ◽  
Hui Xin Ong ◽  
Peta Bradbury ◽  
Agisilaos Kourmatzis ◽  
Daniela Traini ◽  
...  
Keyword(s):  
Drug Delivery ◽  
Real Time ◽  
Nasal Drug Delivery ◽  
Quantitative Monitoring

scholarly journals TOWARDS AN UNIFIED FRAMEWORK FOR VALIDATING DEEP LEARNING METHODS FOR COLORECTAL POLYPS: FIRST STEPS

2021 ◽  
Vol 108 (Supplement_3) ◽  
Author(s):  
L F Sánchez Peralta ◽  
J F Ortega Morán ◽  
Cr L Saratxaga ◽  
J B Pagador ◽  
A Picón ◽  
...  
Keyword(s):  
Deep Learning ◽  
Colorectal Polyps ◽  
Polyp Detection ◽  
Unified Framework ◽  
Endoscopic Image ◽  
Learning Techniques ◽  
Great Utility ◽  
Adenoma Detection ◽  
Definition Of ◽  
Basic Features

Abstract INTRODUCTION Deep learning techniques have significantly contributed to the field of medical imaging analysis. In case of colorectal cancer, they have shown a great utility for increasing the adenoma detection rate at colonoscopy, but a common validation methodology is still missing. In this study, we present preliminary efforts towards the definition of a validation framework. MATERIAL AND METHODS Different models based on different backbones and encoder-decoder architectures have been trained with a publicly available dataset that contains white light and NBI colonoscopy videos, with 76 different lesions from colonoscopy procedures in 48 human patients. A computer aided detection (CADe) demonstrator has been implemented to show the performance of the models. RESULTS This CADe demonstrator shows the areas detected as polyp by overlapping the predicted mask on the endoscopic image. It allows selecting the video to be used, among those from the test set. Although it only present basic features such as play, pause and moving to the next video, it easily loads the model and allows for visualization of results. The demonstrator is accompanied by a set of metrics to be used depending on the aimed task: polyp detection, localization and segmentation. CONCLUSIONS The use of this CADe demonstrator, together with a publicly available dataset and predefined metrics will allow for an easier and more fair comparison of methods. Further work is still required to validate the proposed framework.

Sign in / Sign up

Export Citation Format

Share Document