• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SPIE Medical Imaging Conference >Fundus Analysis Software Tool (FAST): Development of software integrating CAD with the HER for the longitudinal study of fundus images
【24h】

Fundus Analysis Software Tool (FAST): Development of software integrating CAD with the HER for the longitudinal study of fundus images

机译：USFUS分析软件工具（快速）：开发软件将CAD与她整合CAD对眼底图像的纵向研究

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

摘要

In this paper, we present the previous development and deployment of Fundus Analysis Software Tool (FAST) to enablethe analysis of different anatomical features and pathologies within fundus images over time, and demonstrate itsusefulness with three use cases. First, we utilized FAST to acquire 616 fundus images from a remote clinic in a HIPAAcompliantmanner. An ophthalmologist at the clinic then used FAST to annotate 190 fundus images containing exudatesat the pixelwise level in a time-efficient manner. In comparison with publicly available datasets, our dataset constitutesthe largest pixelwise-labeled collection of images and the first exudate segmentation dataset with eye-matched pairs ofimages for a given patient. Second, we developed an optic disk CAD segmentation algorithm, where our algorithmachieved a mean intersection over union of 0.930, comparable to the disagreement between ophthalmologist annotations.We deployed this algorithm into FAST, where it segments and flushes the segmentation onto the computer screen whilesimultaneously filling out specified optic disk fields of a DICOM-SR report on the fundus image. Third, we integratedour software with the open-source HER framework OpenMRS, where our software can upload both automatic andmanual analyses of the fundus to a remote server using HL7 FHIR standard then retrieve historical reports for a patientchronologically. Finally, we discuss our design decisions in developing FAST, particularly those relating to its treatmentof DICOM-SR reports based on fundus images and its usage of the FHIR standard and its next steps towards enablingeffective analyses of fundus images.
机译：在本文中，我们介绍了先前的开发和部署基底分析软件工具（快速）启用随着时间的推移分析眼底图像中不同解剖特征和病理学，并证明其三种用例的用处。首先，我们利用快速获取来自HipaAcomplant的远程诊所的616个眼底图像方式。诊所的眼科医生然后快速使用含有渗出物的190个眼底图像以较效的方式在像素级别。与公共数据集相比，我们的数据集构成最大的像素标记的图像集合和具有眼匹配对的第一个渗出的分割数据集给定患者的图像。其次，我们开发了一种光盘CAD分段算法，其中我们的算法实现了0.930的联盟的平均交叉，可与眼科医生注释之间的分歧相媲美。我们将此算法部署到快速，在其中段并将分段刷新到计算机屏幕上同时填写在眼底图像上的DICOM-SR报告的指定视镜磁盘字段。第三，我们整合我们的软件与她的开源框架OpenMRS，我们的软件可以上传自动和使用HL7 FHIR标准手动对远程服务器的基底分析，然后检索患者的历史报告按时间顺序。最后，我们讨论了我们在开发快速发展方面的设计决策，特别是与其治疗有关的设计决策基于眼底图像的DICOM-SR报告及其利用FHIR标准及其对实现的下一个步骤对眼底图像的有效分析。

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