The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
Rutgers Cancer Institute of New Jersey, Rutgers University, NJ 08903, USA.
Neuroimage. 2020 May 1;211:116620. doi: 10.1016/j.neuroimage.2020.116620. Epub 2020 Feb 11.
Segmentation of brain lesions from magnetic resonance images (MRI) is an important step for disease diagnosis, surgical planning, radiotherapy and chemotherapy. However, due to noise, motion, and partial volume effects, automated segmentation of lesions from MRI is still a challenging task. In this paper, we propose a two-stage supervised learning framework for automatic brain lesion segmentation. Specifically, in the first stage, intensity-based statistical features, template-based asymmetric features, and GMM-based tissue probability maps are used to train the initial random forest classifier. Next, the dense conditional random field optimizes the probability maps from the initial random forest classifier and derives the whole tumor regions referred as the region of interest (ROI). In the second stage, the optimized probability maps are further intergraded with features from the intensity-based statistical features and template-based asymmetric features to train subsequent random forest, focusing on classifying voxels within the ROI. The output probability maps will be also optimized by the dense conditional random fields, and further used to iteratively train a cascade of random forests. Through hierarchical learning of the cascaded random forests and dense conditional random fields, the multimodal local and global appearance information is integrated with the contextual information, and the output probability maps are improved layer by layer to finally obtain optimal segmentation results. We evaluated the proposed method on the publicly available brain tumor datasets BRATS 2015 & BRATS 2018, as well as the ischemic stroke dataset ISLES 2015. The results have shown that our framework achieves competitive performance compared to the state-of-the-art brain lesion segmentation methods. In addition, contralateral difference and skewness were identified as the important features in the brain tumor and ischemic stroke segmentation tasks, which conforms to the knowledge and experience of medical experts, further reflecting the reliability and interpretability of our framework.
从磁共振图像（MRI）中分割脑病变是疾病诊断、手术规划、放疗和化疗的重要步骤。然而，由于噪声、运动和部分容积效应，MRI 中病变的自动分割仍然是一项具有挑战性的任务。在本文中，我们提出了一种用于自动脑病变分割的两阶段监督学习框架。具体来说，在第一阶段，使用基于强度的统计特征、基于模板的不对称特征和基于 GMM 的组织概率图来训练初始随机森林分类器。接下来，密集条件随机场优化初始随机森林分类器的概率图，并得出整个肿瘤区域，即感兴趣区域（ROI）。在第二阶段，优化后的概率图与基于强度的统计特征和基于模板的不对称特征的特征进一步集成，以训练后续的随机森林，重点是对 ROI 内的体素进行分类。输出概率图也将通过密集条件随机场进行优化，并进一步用于迭代训练级联随机森林。通过级联随机森林和密集条件随机场的分层学习，将多模态局部和全局外观信息与上下文信息集成，并通过分层学习来逐层优化输出概率图，最终获得最佳分割结果。我们在公开的脑肿瘤数据集 BRATS 2015 和 BRATS 2018 以及缺血性中风数据集 ISLES 2015 上评估了所提出的方法。结果表明，与最先进的脑病变分割方法相比，我们的框架具有竞争力。此外，在脑肿瘤和缺血性中风分割任务中，我们识别出了对侧差异和偏度是重要特征，这符合医学专家的知识和经验，进一步反映了我们框架的可靠性和可解释性。
