Saved in:
Bibliographic Details
Main Authors: Zhou, Ziyu, Shen, Wenyuan, Liu, Chang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.11355
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913318685376512
author Zhou, Ziyu
Shen, Wenyuan
Liu, Chang
author_facet Zhou, Ziyu
Shen, Wenyuan
Liu, Chang
contents Colorectal cancer (CRC), which frequently originates from initially benign polyps, remains a significant contributor to global cancer-related mortality. Early and accurate detection of these polyps via colonoscopy is crucial for CRC prevention. However, traditional colonoscopy methods depend heavily on the operator's experience, leading to suboptimal polyp detection rates. Besides, the public database are limited in polyp size and shape diversity. To enhance the available data for polyp detection, we introduce Consisaug, an innovative and effective methodology to augment data that leverages deep learning. We utilize the constraint that when the image is flipped the class label should be equal and the bonding boxes should be consistent. We implement our Consisaug on five public polyp datasets and at three backbones, and the results show the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11355
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Consisaug: A Consistency-based Augmentation for Polyp Detection in Endoscopy Image Analysis
Zhou, Ziyu
Shen, Wenyuan
Liu, Chang
Computer Vision and Pattern Recognition
Colorectal cancer (CRC), which frequently originates from initially benign polyps, remains a significant contributor to global cancer-related mortality. Early and accurate detection of these polyps via colonoscopy is crucial for CRC prevention. However, traditional colonoscopy methods depend heavily on the operator's experience, leading to suboptimal polyp detection rates. Besides, the public database are limited in polyp size and shape diversity. To enhance the available data for polyp detection, we introduce Consisaug, an innovative and effective methodology to augment data that leverages deep learning. We utilize the constraint that when the image is flipped the class label should be equal and the bonding boxes should be consistent. We implement our Consisaug on five public polyp datasets and at three backbones, and the results show the effectiveness of our method.
title Consisaug: A Consistency-based Augmentation for Polyp Detection in Endoscopy Image Analysis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.11355