Related Experiment Video
Updated: Oct 12, 2025
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
1.8K
An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large
Ishak Pacal1, Ahmet Karaman2, Dervis Karaboga3
1Computer Engineering Department, Engineering Faculty, Igdir University, Igdir, Turkey.
Computers in Biology and Medicine
|November 22, 2021
Summary
Deep learning models enhance colonoscopy by improving polyp detection accuracy and real-time performance. These advancements in artificial intelligence aim to reduce missed colorectal cancer precursors, boosting screening effectiveness.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Colorectal cancer (CRC) poses a significant mortality risk, with colonoscopy being the primary screening method.
- Missed polyps during colonoscopy, precursors to CRC, remain a challenge, necessitating improved detection systems.
- Artificial intelligence (AI) offers potential solutions for enhancing polyp detection rates in colonoscopy.
Purpose of the Study:
- To develop and evaluate deep learning-based methods for reliable computer-assisted polyp detection.
- To improve the real-time performance and accuracy of automatic polyp detection systems.
- To compare the efficacy of different activation functions and loss functions for polyp detection.
Main Methods:
- Integration of Cross Stage Partial Network (CSPNet) with YOLOv3 and YOLOv4 object detection algorithms.
- Application of advanced data augmentation and transfer learning techniques.
- Substitution of Sigmoid-weighted Linear Unit (SiLU) activation functions and Complete Intersection over Union (CIoU) loss function for enhanced performance with negative samples.
- Comparative analysis of activation functions for polyp detection.
Main Results:
- The proposed deep learning methods demonstrated superior performance in both real-time capabilities and polyp detection accuracy.
- The integration of CSPNet significantly improved the performance of YOLOv3 and YOLOv4.
- The use of SiLU activation and CIoU loss function further enhanced polyp detection, particularly with negative samples.
Conclusions:
- The developed deep learning models offer a reliable and efficient solution for computer-assisted polyp detection in colonoscopy.
- These advanced AI methods show promise in reducing missed polyps and improving overall CRC screening effectiveness.
- The study highlights the potential of AI in enhancing diagnostic accuracy and real-time performance in medical imaging applications.
Related Concept Videos
01:26Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy
174
This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
174
01:25Endoscopic Procedures II: Colonoscopy
245
The colon, or large intestine, is the final segment of the digestive system. Its primary functions include absorbing water and vitamins produced by gut bacteria and transforming waste from liquid to solid to form stool. In adults, the large intestine is approximately 5 feet long and consists of four main sections:
245