[Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network].

Q4 Medicine
Yiyang Li, Jiayi Zhao, Ruoyi Yu, Huixiang Liu, Shuang Liang, Yu Gu
{"title":"[Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network].","authors":"Yiyang Li, Jiayi Zhao, Ruoyi Yu, Huixiang Liu, Shuang Liang, Yu Gu","doi":"10.7507/1001-5515.202312014","DOIUrl":null,"url":null,"abstract":"<p><p>Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"41 5","pages":"911-918"},"PeriodicalIF":0.0000,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11527748/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"生物医学工程学杂志","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.7507/1001-5515.202312014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

Abstract

Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.

[基于多尺度、多层次特征融合和轻量级卷积神经网络的结肠息肉检测]。
大肠息肉的早期诊断和治疗对预防大肠癌至关重要。本文提出了一种用于大肠息肉自动检测和辅助诊断的轻量级卷积神经网络。首先,使用 53 层卷积主干网络,结合空间金字塔池化模块,实现不同感受野大小的特征提取。随后,利用特征金字塔网络对骨干网络的特征图进行跨尺度融合。空间注意力模块用于增强对息肉图像边界和细节的感知。此外,位置模式注意模块用于自动挖掘和整合不同层次特征图的关键特征,从而实现快速、高效、准确的大肠息肉自动检测。该模型在临床数据集上进行了评估,在每秒 74 帧的帧率和 9 个参数的情况下,在交集大于联合(IOU)阈值为 0.5 时,准确率达到 0.9982,召回率达到 0.9988,F1 分数达到 0.9984,平均精度(mAP)达到 0.9953。08 M。与现有的主流方法相比,所提出的方法具有轻便、操作配置要求低、检测速度快、精确度高等特点,是一种可行的技术方法,也是结直肠癌早期检测和诊断的重要工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
生物医学工程学杂志
生物医学工程学杂志 Medicine-Medicine (all)
CiteScore
0.80
自引率
0.00%
发文量
4868
期刊介绍:
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信