Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Year of publication
- 2023 (2) (remove)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- endoscopy (2)
- 3D printing (1)
- automation (1)
- deep learning (1)
- endoscopic instruments (1)
- endoscopic intervention (1)
- gastroenterology (1)
- machine learning (1)
- minimally invasive surgery (1)
- object detection (1)
Institute
(1) Background: Interventional endoscopic procedures are growing more popular, requiring innovative instruments and novel techniques. Three-dimensional printing has demonstrated great potential for the rapid development of prototypes that can be used for the early assessment of various concepts. In this work, we present the development of a flexible endoscopic instrument and explore its potential benefits. (2) Methods: The properties of the instrument, such as its maneuverability, flexibility, and bending force, were evaluated in a series of bench tests. Additionally, the effectiveness of the instrument was evaluated in an ex vivo porcine model by medical experts, who graded its properties and performance. Furthermore, the time necessary to complete various interventional endoscopic tasks was recorded. (3) Results: The instrument achieved bending angles of ±216° while achieving a bending force of 7.85 (±0.53) Newtons. The time needed to reach the operating region was 120 s median, while it took 70 s median to insert an object in a cavity. Furthermore, it took 220 s median to insert the instrument and remove an object from the cavity. (4) Conclusions: This study presents the development of a flexible endoscopic instrument using three-dimensional printing technology and its evaluation. The instrument demonstrated high bending angles and forces, and superior properties compared to the current state of the art. Furthermore, it was able to complete various interventional endoscopic tasks in minimal time, thus potentially leading to the improved safety and effectiveness of interventional endoscopic procedures in the future.
Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24% on the open-source CVC-VideoClinicDB benchmark.