• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Society of Photo-Optical Instrumentation Engineers;SPIE Medical Imaging Conference >Two-Tier Classifier for Identifying Small Objects in Histological Tissue Classification: Experiments with Colon Cancer Tissue Mapping
【24h】

Two-Tier Classifier for Identifying Small Objects in Histological Tissue Classification: Experiments with Colon Cancer Tissue Mapping

机译：在组织学组织分类中识别小物体的两层分类器：结肠癌组织作图实验

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

摘要

Tissue classification on histological images is a useful alternative to manual histology analysis, and has been well-studiedin a variety of machine learning approaches. However, classification of whole slide images at high resolution is a difficultand computationally-intensive task. In addition, many tissue analysis tasks are targeted at identifying rare or small regionsof tissue. In colon cancer, small groups of tumor cells (tumor buds) exist on the front edge of the invasive tumor regionand are an important indicator of cancer aggressiveness. These small objects are difficult or impossible to detect whenexamining an image at lower resolution, while running the classifier at an appropriate high resolution can be timeconsuming.In this work, a two-tier convolutional neural network classification approach is explored to identify small butimportant tissue regions on whole-slide tissue scans. The first tier is a coarse-level classifier trained with patches extractedfrom the image at a low power field (4x optical magnification), designed to identify two main tissue types: tumor and nontumorareas. Regions that are likely to contain tumor buds (non-tumor regions) are passed to a fine-level classifier thatclassifies the patches into 9 additional tissue types at a high-power field (40x). The system achieves a 43% reduction inprocessing time (3 hours to 1.7 hours for a 19,200-by-19,200 pixel image). The two-tier classifier provides an efficientwhole-slide tissue classification by narrowing down the regions of interest, increasing the chances of tumor buds beingidentified.
机译：组织学图像的组织分类是手动组织学分析的有用替代品，并且已经很好地研究 在各种机器学习方法中。然而，高分辨率下整个幻灯片图像的分类是困难的 和计算密集的任务。此外，许多组织分析任务是针对识别稀有或小区域的目标 组织。在结肠癌中，侵袭性肿瘤区域的前沿存在小组肿瘤细胞（肿瘤芽） 并且是癌症侵略性的重要指标。这些小物体难以或无法检测到何时 在较低分辨率下检查图像，同时以适当的高分辨率运行分类器可以是TimeConsuming。 在这项工作中，探索了双层卷积神经网络分类方法来识别小但 全载组织扫描上的重要组织区。第一层是一个粗略级别的分类器，用提取的补丁培训 从低功率场（4倍光学放大倍数）的图像，旨在识别两种主要组织类型：肿瘤和非肿瘤 地区。可能含有肿瘤芽（非肿瘤区域）的区域通过了细水分分类器 在高功率场（40倍）上将贴片分类为9种附加组织类型。该系统降低了43％ 处理时间（19,200×19,200像素图像的3小时到1.7小时）。双层分类器提供有效 通过缩小感兴趣的区域，增加肿瘤芽的机会，通过缩小整个滑动组织分类 确定。

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