河北大学学报(自然科学版) ›› 2023, Vol. 43 ›› Issue (1): 103-112.DOI: 10.3969/j.issn.1000-1565.2023.01.015

• • 上一篇    

基于改进的Faster R-CNN的息肉目标检测和分类方法

杨昆1,2,3,原嘉成1,高聪4,孙宇锋1,路宇飞1,常世龙1,薛林雁1,2,3   

  • 收稿日期:2022-02-12 出版日期:2023-01-25 发布日期:2023-02-22
  • 通讯作者: 薛林雁(1981—)
  • 作者简介:杨昆(1976—),男,河北保定人,河北大学教授,博士生导师,博士,主要从事生物医学图像处理方向研究.
    E-mail:yangkun@hbu.edu.cn
  • 基金资助:
    河北省自然科学基金资助项目(A2011201155);河北大学校长科研基金资助项目(XZJJ201914);河北大学多学科交叉研究项目(DXK201914)

Object detection and classification of polyps based on improved Faster R-CNN

YANG Kun1,2,3, YUAN Jiacheng1, GAO Cong4, SUN Yufeng1, LU Yufei1,CHANG Shilong1, XUE Linyan1,2,3   

  1. 1.College of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2. National & Local Joint Engineering Research Center of Metrology Instrument and System, Baoding 071002, China; 3.New Energy Vehicle Power System Lightweight Technology Innovation Center of Hebei Province, Baoding 071002, China; 4.Hebei Far East Communication System Engineering Co., Ltd, Shijiazhuang 050200, China
  • Received:2022-02-12 Online:2023-01-25 Published:2023-02-22

摘要: 为了解决结肠镜下腺瘤性息肉和增生性息肉不易分型的问题,提出一种基于改进的Faster R-CNN的目标检测及息肉分类模型.在数据预处理阶段,对原有的2 426张息肉图像(1 582张腺瘤性息肉图像,844张增生性息肉图像)通过2种方式进行图像增强,并且通过改进的特征提取、边界框回归以及非极大值抑制的网络,用602张图像(386张腺瘤性图像,216张增生性息肉图像)进行测试.通过实验证明,在交并比(IoU)取0.5时,获得了86.8%的平均精度均值,相较于改进之前提升了2.3%.实验结果验证了该模型的潜在临床应用价值.

关键词: 息肉, 目标检测, 分类, Faster R-CNN

Abstract: In order to solve the problem of difficult classification of adenomatous polyps and hyperplastic polyps under colorectoscopy, an object detection and polyp classification model based on improved Faster R-CNN was proposed. Polyp images(1582 adenomatous polyp images, 844 hyperplastic polyp images)were image-enhanced in two ways, and 602 images(386 adenomatous images, 216 hyperplastic- DOI:10.3969/j.issn.1000-1565.2023.01.015基于改进的Faster R-CNN的息肉目标检测和分类方法杨昆1,2,3,原嘉成1,高聪4,孙宇锋1,路宇飞1,常世龙1,薛林雁1,2,3(1.河北大学 质量技术监督学院,河北 保定 071002;2.计量仪器与系统国家地方联合工程研究中心,河北 保定 071002;3.河北省新能源汽车动力系统轻量化技术创新中心, 河北 保定 071002;4.河北远东通信系统工程有限公司,河北 石家庄 050200)摘 要:为了解决结肠镜下腺瘤性息肉和增生性息肉不易分型的问题,提出一种基于改进的Faster R-CNN的目标检测及息肉分类模型.在数据预处理阶段,对原有的2 426张息肉图像(1 582张腺瘤性息肉图像,844张增生性息肉图像)通过2种方式进行图像增强,并且通过改进的特征提取、边界框回归以及非极大值抑制的网络,用602张图像(386张腺瘤性图像,216张增生性息肉图像)进行测试.通过实验证明,在交并比(IoU)取0.5时,获得了86.8%的平均精度均值,相较于改进之前提升了2.3%.实验结果验证了该模型的潜在临床应用价值.关键词:息肉;目标检测;分类;Faster R-CNN中图分类号:TP192.7 文献标志码:A 文章编号:1000-1565(2023)01-0103-10Object detection and classification of polyps based onimproved Faster R-CNNYANG Kun1,2,3, YUAN Jiacheng1, GAO Cong4, SUN Yufeng1, LU Yufei1,CHANG Shilong1, XUE Linyan1,2,3(1.College of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2. National & Local Joint Engineering Research Center of Metrology Instrument and System, Baoding 071002, China; 3.New Energy Vehicle Power System Lightweight Technology Innovation Center of Hebei Province, Baoding 071002, China; 4.Hebei Far East Communication System Engineering Co., Ltd, Shijiazhuang 050200, China)Abstract: In order to solve the problem of difficult classification of adenomatous polyps and hyperplastic polyps under colorectoscopy, an object detection and polyp classification model based on improved Faster R-CNN was proposed. Polyp images(1582 adenomatous polyp images, 844 hyperplastic polyp images)were image-enhanced in two ways, and 602 images(386 adenomatous images, 216 hyperplastic- 收稿日期:2022-02-12 基金项目:河北省自然科学基金资助项目(A2011201155);河北大学校长科研基金资助项目(XZJJ201914);河北大学多学科交叉研究项目(DXK201914) 第一作者:杨昆(1976—),男,河北保定人,河北大学教授,博士生导师,博士,主要从事生物医学图像处理方向研究.E-mail:yangkun@hbu.edu.cn 通信作者:薛林雁(1981—),女,河北广平人,河北大学副教授,博士,主要从事生物医学图像处理方向研究.E-mail:lyxue@hbu.edu.cn第1期杨昆等:基于改进的Faster R-CNN的息肉目标检测和分类方法polyp images)were tested. It is proved by experiments that when the intersection-union ratio(IoU)is set to be 0.5, an average precision of 86.8% is obtained, which is 2.3% higher than that before the improvement. The experimental results verified the potential clinical application value of this model.

Key words: polyps, object detection, classification, Faster R-CNN

中图分类号: