• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine;Society of Photo-Optical Instrumentation Engineers >Comparison of Classification Methods of Barret’s and Dysplasia in the Esophagus from In Vivo Optical Coherence Tomography Images
【24h】

Comparison of Classification Methods of Barret’s and Dysplasia in the Esophagus from In Vivo Optical Coherence Tomography Images

机译：体内光学相干断层扫描图像比较食管中Barret和异型增生的分类方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Endoscopic Optical Coherence Tomography (EOCT) systems can perform in vivo, real-time, high-resolution imaging ofthe human esophagus and, thus, play an important role in the earlier diagnosis and better prognosis of esophageal diseasessuch as Barrett’s, dysplasia and adenocarcinoma. However, the high image throughput and massive data volumes makemanual evaluation of the generated information extremely difficult. Unfortunately, the algorithms, developed thus far,have not been able to provide effective computer-aided diagnosis. In this study, we compare different machine learningmethods for tissue segmentation and classification of esophageal tissue in in vivo OCT images. An automated algorithmwas developed, capable of discriminating normal tissue from Barrett’s Esophagus (BE) and dysplasia. The classificationwas based on various features of the epithelium, extracted from EOCT images, such as intensity-based statistics, the groupvelocity dispersion (GVD), estimated from the image speckle, and the scatterer size, calculated using the bandwidth of thecorrelation of the derivative (COD) method. The comparison and evaluation of various machine learning techniques hasshown that a neural network based approach provided the best performance, classifying Barret’s esophagus and dysplasia,for individual A-Scans, with an accuracy of 89%.
机译：内窥镜光学相干断层扫描（EOCT）系统可以执行活体内，实时，高分辨率成像 人食道，因此在食道疾病的早期诊断和更好的预后中起着重要的作用 例如Barrett病，不典型增生和腺癌。但是，高图像吞吐量和海量数据使 手动评估生成的信息非常困难。不幸的是，到目前为止开发的算法 尚未能够提供有效的计算机辅助诊断。在这项研究中，我们比较了不同的机器学习 体内OCT图像中食管组织的组织分割和分类方法。自动化算法 被开发出来，能够区分Barrett食管（BE）和发育不良的正常组织。分类 基于上皮的各种特征，这些特征是从EOCT图像中提取的，例如基于强度的统计数据， 速度散度（GVD）（根据图像斑点估计）和散射体大小（使用像素的带宽计算得出） 导数（COD）方法的相关性。各种机器学习技术的比较和评估具有 表明基于神经网络的方法可提供最佳性能，对Barret的食道和发育不良进行了分类， 适用于单个A扫描，精度为89％。

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