Return
Real-Time Multi-Task Deep Learning Model for Polyp Detection, Characterization, and Size Estimation
DOI:10.1109/ACCESS.2025.3527720.png)
Abstract
En 中文
While performing a colonoscopy, there are many tasks to be done: finding polyps, classifying them, and deciding the next procedure for the polyps, whether to incise them or not. Such tasks are challenging for fellow doctors. All these three tasks can have an intrapersonal error, which varies among endoscopists. A proven method for enhancing performance is computer-aided detection and a diagnosis system for endoscopists, which tends to be a real-time system. In this work, we present a modified convolutional neural network (CNN) based deep learning (DL) model to perform these tasks in real-time, utilizing existing object detection models: YOLOv5 and YOLOv8. For the various tasks, the models are trained using datasets with incomplete labels, leading to a comparison of different training strategies. Our model, YOLOv8, achieved an F1-score of 95.96% for the polyp detection task, 85.24% F1-score for the polyp classification task, and 78.41% macro F1-score for the polyp size estimation task. Such results, when compared with fellow doctors' findings proved superior in both accuracy and macro F1-score, maintaining a real-time inference speed.
Keywords:
Real-time systems
YOLO
Estimation
Accuracy
Endoscopes
Colon
Training
Medical diagnostic imaging
Mathematical models
Convolutional neural networks
Colonic polyp
deep learning
real-time image classification
real-time object detection
real-time size estimation
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
Cited Papers
Airways Obstruction and Arterial Blood Gas Tensions in Chronic Obstructive Lung Disease
Respiration
IF0
Artificial intelligence-based measurement outperforms current methods for colorectal polyp size measurement
DIGESTIVE ENDOSCOPY
IF4.7

