• 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);SPIE Proceedings >Computer-aided diagnosis of leukoencephalopathy in children treated for acute lymphoblastic leukemia
【24h】

Computer-aided diagnosis of leukoencephalopathy in children treated for acute lymphoblastic leukemia

机译：儿童急性淋巴细胞白血病的儿童白脑病的计算机辅助诊断

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

摘要

The purpose of this study was to use objective quantitative MR imaging methods to develop a computer-aideddiagnosis tool to differentiate white matter (WM) hyperintensities as either leukoencephalopathy (LE) or normalmaturational processes in children treated for acute lymphoblastic leukemia with intravenous high dose methotrexate. Acombined imaging set consisting of T1, T2, PD, and FLAIR MR images and WM, gray matter, and cerebrospinal fluid apriori maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a KohonenSelf-Organizing Map. Segmented regions were manually classified to identify the most hyperintense WM region and thenormal appearing genu region. Signal intensity differences normalized to the genu within each examination weregenerated for two time points in 203 children. An unsupervised hierarchical clustering algorithm with the agglomerationmethod of McQuitty was used to divide data from the first examination into normal appearing or LE groups. A Csupportvector machine (C-SVM) was then trained on the first examination data and used to classify the data from thesecond examination. The overall accuracy of the computer-aided detection tool was 83.5% (299 / 358) with sensitivity tonormal WM of 86.9% (199 / 229) and specificity to LE of 77.5% (100 / 129) when compared to the readings of twoexpert observers. These results suggest that subtle therapy-induced leukoencephalopathy can be objectively andreproducibly detected in children treated for cancer using this computer-aided detection approach based on relativedifferences in quantitative signal intensity measures normalized within each examination.
机译：这项研究的目的是使用客观的定量MR成像方法来开发一种计算机辅助诊断工具，以区分接受静脉内高剂量甲氨蝶呤治疗的急性淋巴细胞性白血病的儿童白质（WM）高信号是白质脑病（LE）还是正常成熟过程。使用基于KohonenSelf-Organizing Map的神经网络分割，分析了由T1，T2，PD和FLAIR MR图像以及WM，灰质和脑脊液先天图组成的组合成像集，并使用了基于空间归一化图集的WM，灰质和脑脊液先天图。手动对分割的区域进行分类，以识别最强的WM区域和正常出现的Genu区域。在203个儿童中，在两个时间点生成了针对每个检查归一化的信号强度差异的时间。使用具有McQuitty聚集方法的无监督分层聚类算法，将来自第一次检查的数据划分为正常出现或LE组。然后，对Csupportvector机器（C-SVM）进行了第一次检查数据的训练，并用于对第二次检查的数据进行分类。与两名专家观察员的读数相比，计算机辅助检测工具的总体准确性为83.5％（299/358），对正常WM的敏感性为86.9％（199/229），对LE的特异性为77.5％（100/129）。 。这些结果表明，基于每次检查中归一化的定量信号强度测量值的相对差异，使用这种计算机辅助检测方法，可以客观而可重复地检测出接受癌症治疗的儿童的细微疗法引起的白质脑病。

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