首页> 外文会议>Asian Conference on Computer Vision >A System for Colorectal Tumor Classification in Magnifying Endoscopic NBI Images
【24h】

A System for Colorectal Tumor Classification in Magnifying Endoscopic NBI Images

机译:放大内镜NBI图像中的结直肠癌分类系统

获取原文

摘要

In this paper we propose a recognition system for classifying NBI images of colorectal tumors into three types (A, and C3) of structures of microvessels on the colorectal surface. These types have a strong correlation with histologic diagnosis: hyperplasias (HP), tubular adenomas (TA), and carcinomas with massive submucosal invasion (SM-m). Images are represented by Bag-of-features of the SIFF descriptors densely sampled on a grid, and then classified by an SVM with an REF kernel. A dataset of 907 NBI images were used for experiments with 10-fold cross-validation, and recognition rate of 94.1% were obtained.
机译:本文提出了一种识别系统,用于将结直肠肿瘤的NBI图像分类为结直肠表面上微孔丝结构的三种类型(A和C3)。这些类型具有与组织学诊断的强烈相关性:增生(HP),管状腺瘤(TA)和具有巨大粘膜侵袭(SM-M)的癌症。图像由SIFF描述符的袋子特性表示,在网格上密集地采样,然后由SVM与REF内核进行分类。 907 NBI图像的数据集用于10倍交叉验证的实验,并获得94.1%的识别率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号