Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations

Abstract

Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.

References in corpus (17)

• SSD: Single Shot MultiBox Detector
• A Survey on Deep Learning in Medical Image Analysis
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• YOLOv3: An Incremental Improvement
• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• DetNet: A Backbone network for Object Detection
• Anatomy-specific classification of medical images using deep convolutional nets
• A Comparative Study on Polyp Classification using Convolutional Neural Networks
• Deep Feature Augmentation for Occluded Image Classification
• Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation
• MDFN: Multi-Scale Deep Feature Learning Network for Object Detection
• Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation
• Plug-and-Play Rescaling Based Crowd Counting in Static Images
• Adversarially Approximated Autoencoder for Image Generation and Manipulation
• SGNet: A Super-class Guided Network for Image Classification and Object Detection
• Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters
• Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization