• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on Imaging Informatics for Healthcare, Research, and Applications >Preprocessing of clinical neuro-oncology MRI studies for big data applications
【24h】

Preprocessing of clinical neuro-oncology MRI studies for big data applications

机译：临床神经肿瘤学MRI研究的预处理

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

摘要

Clinically acquired, multimodal and multi-site MRI datasets are widely used for neuro-oncology research. However,manual preprocessing of such data is extremely tedious and error prone due to high intrinsic heterogeneity. Automaticstandardization of such datasets is therefore important for data-hungry applications like deep learning. Despite rapidadvances in MRI data acquisition and processing algorithms, only limited effort was dedicated to automatic methodologiesfor standardization of such data.To address this challenge, we augment our previously developed Multimodal Glioma Analysis (MGA) pipeline withautomation tools to achieve processing scale suitable for big data applications. This new pipeline implements a naturallanguage processing (NLP) based scan-type classifier, with features constructed from DICOM metadata based on bag-ofwordsmodel. The classifier automatically assigns one of 18 pre-defined scan types to all scans in MRI study.Using the described data model, we trained three types of classifiers: logistic regression, linear SVM, and multi-layerartificial neural network (ANN) on the same dataset. Their performance was validated on four datasets from multiplesources. ANN implementation achieved the highest performance, yielding an average classification accuracy of over 99%.We also built a Jupyter notebook based graphical user interface (GUI) which is used to run MGA in semi-automatic modefor progress tracking purposes and quality control to ensure reproducibility of the analyses based thereof. MGA has beenimplemented as a Docker container image to ensure portability and easy deployment. The application can run in a singleor batch study mode, using either local DICOM data or XNAT cloud storage.
机译：临床获取，多式联运和多点MRI数据集广泛用于神经肿瘤学研究。然而，由于高固有的异质性，这些数据的手动预处理是极其繁琐的并且易于出错。自动的因此，这种数据集的标准化对于深度学习等数据饥饿的应用是重要的。尽管如此MRI数据采集和处理算法的进步，只有有限的努力致力于自动方法用于这些数据的标准化。为了解决这一挑战，我们增强了先前开发的多峰胶质瘤分析（MGA）管道自动化工具实现适用于大数据应用的处理规模。这个新的管道实现了自然的基于语言处理（NLP）的扫描型分类器，具有从基于BAG-ofWory的DICOM元数据构造的功能模型。分类器自动为MRI研究中的所有扫描自动分配18种预定义扫描类型中的一个。使用所描述的数据模型，我们培训了三种类型的分类器：Logistic回归，线性SVM和多层在同一数据集上的人工神经网络（ANN）。它们的性能在多个来自四个数据集上验证来源。 ANN实施实现了最高的性能，平均分类准确性超过99％。我们还建立了基于Jupyter Notebook的图形用户界面（GUI），用于在半自动模式下运行MGA为了进行进展跟踪目的和质量控制，以确保基于分析的再现性。 MGA已经实现为Docker容器图像，以确保可移植性和部署方便。应用程序可以单一运行或批量学习模式，使用本地DICOM数据或XNAT云存储。

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