GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation.
GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation.
复制标题
DOI：
10.1007/978-3-319-30858-6_1
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Davatzikos C
中科院分区：
文献类型：
--
作者：
Bakas S;Zeng K;Sotiras A;Rathore S;Akbari H;Gaonkar B;Rozycki M;Pati S;Davatzikos C
我们提出了一种方法分割低，高级别胶质瘤的多模态磁共振成像体积。所提出的方法是基于一个混合生成判别模型。首先，使用基于期望最大化框架的生成方法将脑扫描分割成肿瘤以及健康组织标签，该框架结合了胶质瘤生长模型。其次，使用梯度提升多类分类方案来基于来自多个患者的信息细化肿瘤标签。最后，采用概率贝叶斯策略，根据来自多种模态的患者特异性强度统计，进一步细化和完成肿瘤分割。我们在BRAin肿瘤分割（BRATS）2015挑战的训练阶段对186例病例进行了评估，并报告了有希望的结果。在测试阶段，该算法还在53个看不见的情况下进行了评估，在竞争方法中获得了最佳性能。
We present an approach for segmenting low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative approach based on an Expectation-Maximization framework that incorporates a glioma growth model is used to segment the brain scans into tumor, as well as healthy tissue labels. Secondly, a gradient boosting multi-class classification scheme is used to refine tumor labels based on information from multiple patients. Lastly, a probabilistic Bayesian strategy is employed to further refine and finalize the tumor segmentation based on patient-specific intensity statistics from the multiple modalities. We evaluated our approach in 186 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2015 challenge and report promising results. During the testing phase, the algorithm was additionally evaluated in 53 unseen cases, achieving the best performance among the competing methods.