• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Pattern Analysis and Applications >Automated hippocampal segmentation in 3D MRI using random undersampling with boosting algorithm
【24h】

Automated hippocampal segmentation in 3D MRI using random undersampling with boosting algorithm

机译：使用Boosting算法的随机欠采样在3D MRI中自动进行海马区分割

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The automated identification of brain structure in Magnetic Resonance Imaging is very important both in neuroscience research and as a possible clinical diagnostic tool. In this study, a novel strategy for fully automated hippocampal segmentation in MRI is presented. It is based on a supervised algorithm, called RUSBoost, which combines data random undersampling with a boosting algorithm. RUSBoost is an algorithm specifically designed for imbalanced classification, suitable for large data sets because it uses random undersampling of the majority class. The RUSBoost performances were compared with those of ADABoost, Random Forest and the publicly available brain segmentation package, FreeSurfer. This study was conducted on a data set of 50 T1-weighted structural brain images. The RUSBoost-based segmentation tool achieved the best results with a Dice's index of () for the left (right) brain hemisphere. An independent data set of 50 T1-weighted structural brain scans was used for an independent validation of the fully trained strategies. Again the RUSBoost segmentations compared favorably with manual segmentations with the highest performances among the four tools. Moreover, the Pearson correlation coefficient between hippocampal volumes computed by manual and RUSBoost segmentations was 0.83 (0.82) for left (right) side, statistically significant, and higher than those computed by Adaboost, Random Forest and FreeSurfer. The proposed method may be suitable for accurate, robust and statistically significant segmentations of hippocampi.
机译：磁共振成像中大脑结构的自动识别在神经科学研究和可能的临床诊断工具中都非常重要。在这项研究中，提出了一种在MRI中进行全自动海马分割的新策略。它基于一种称为RUSBoost的监督算法，该算法将数据随机欠采样与提升算法结合在一起。 RUSBoost是一种专为不平衡分类而设计的算法，由于它使用多数类的随机欠采样，因此适用于大型数据集。将RUSBoost的性能与ADABoost，Random Forest和可公开获得的大脑分割软件包FreeSurfer的性能进行了比较。这项研究是基于50个T1加权结构脑图像的数据集进行的。基于RUSBoost的分割工具在左（右）脑半球的Dice指数为（）时取得了最佳结果。 50个T1加权结构性脑部扫描的独立数据集用于对经过全面培训的策略进行独立验证。再次，RUSBoost细分与四种工具中性能最高的手动细分相比具有优势。此外，通过手动分割和RUSBoost分割计算的海马体积之间的Pearson相关系数，左侧（右侧）为0.83（0.82），具有统计学意义，并且高于Adaboost，Random Forest和FreeSurfer所计算的。所提出的方法可能适用于海马体的准确，鲁棒性和统计学意义的分割。

著录项

  • 来源
    《Pattern Analysis and Applications》 |2016年第2期|579-591|共13页
  • 作者

    Maglietta Rosalia; Amoroso Nicola; Boccardi Marina; Bruno Stefania; Chincarini Andrea; Frisoni Giovanni B.; Inglese Paolo; Redolfi Alberto; Tangaro Sabina; Tateo Andrea; Bellotti Roberto;

  • 作者单位

    CNR, Ist Studi Sistemi Intelligent Automaz, Via G Amendola 122, I-70126 Bari, Italy;

    Univ Bari, Dipartimento Interateneo Fis M Merlin, Bari, Italy|Ist Nazl Fis Nucl, Sez Bari, I-70126 Bari, Italy;

    FBF, IRCCS S Giovanni di Dio, LENITEM Lab Epidemiol Neuroimaging & Telemed, Brescia, Italy;

    Overdale Hosp, St Helier, Jersey, Italy;

    Ist Nazl Fis Nucl, Sez Genova, Via Dodecaneso 33, I-16146 Genoa, Italy;

    FBF, IRCCS S Giovanni di Dio, LENITEM Lab Epidemiol Neuroimaging & Telemed, Brescia, Italy|AFaR Assoc FateBeneFratelli Ric, Rome, Italy|FBF, IRCCS S Giovanni di Dio, Psychogeriatr Ward, Brescia, Italy;

    Univ Bari, Dipartimento Interateneo Fis M Merlin, Bari, Italy|Ist Nazl Fis Nucl, Sez Bari, I-70126 Bari, Italy;

    FBF, IRCCS S Giovanni di Dio, LENITEM Lab Epidemiol Neuroimaging & Telemed, Brescia, Italy;

    Ist Nazl Fis Nucl, Sez Bari, I-70126 Bari, Italy;

    Univ Bari, Dipartimento Interateneo Fis M Merlin, Bari, Italy|Ist Nazl Fis Nucl, Sez Bari, I-70126 Bari, Italy;

    Univ Bari, Dipartimento Interateneo Fis M Merlin, Bari, Italy|Ist Nazl Fis Nucl, Sez Bari, I-70126 Bari, Italy;

  • 收录信息 美国《科学引文索引》(SCI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Supervised learning; Classification; Segmentation; MRI;

    机译：监督学习;分类;分割;MRI;

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