Brain Hematoma Segmentation Using Active Learning and an Active Contour Model
Brain Hematoma Segmentation Using Active Learning and an Active Contour Model
复制标题
DOI：
10.1007/978-3-030-17935-9_35
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Heming Yao;C. Williamson;Jonathan Gryak;K. Najarian
中科院分区：
文献类型：
--
作者：
Heming Yao;C. Williamson;Jonathan Gryak;K. Najarian
创伤性脑损伤（TBI）是世界范围内的一个严重的公共卫生问题。准确、快速的脑血肿自动分割对于TBI的诊断、治疗和预后预测具有重要意义。在这项研究中，我们开发了一种全自动系统来检测和分割急性 TBI 患者头部计算机断层扫描 (CT) 图像中的血肿区域。我们首先将大脑图像过度分割为超像素，然后提取统计和纹理特征以捕获超像素的特征。为了克服注释数据的短缺，设计了一种基于不确定性的主动学习策略，以自适应和迭代地选择信息最丰富的未标记数据进行注释，以训练支持向量机分类器（SVM）。最后，将SVM分类器的粗分割纳入主动轮廓模型中，以提高分割的准确性。从我们的实验来看，与常规机器学习相比，所提出的主动学习策略可以用少 5 倍的标记数据实现可比较的结果。我们提出的自动血肿分割系统在我们的数据集上实现了 0.60 的平均 Dice 系数，其中患者来自多个健康中心并处于多个损伤级别。我们的结果表明，所提出的方法可以有效克服数据集有限且高度变化的挑战。
Traumatic brain injury (TBI) is a massive public health problem worldwide. Accurate and fast automatic brain hematoma segmentation is important for TBI diagnosis, treatment and outcome prediction. In this study, we developed a fully automated system to detect and segment hematoma regions in head Computed Tomography (CT) images of patients with acute TBI. We first over-segmented brain images into superpixels and then extracted statistical and textural features to capture characteristics of superpixels. To overcome the shortage of annotated data, an uncertainty-based active learning strategy was designed to adaptively and iteratively select the most informative unlabeled data to be annotated for training a Support Vector Machine classifier (SVM). Finally, the coarse segmentation from the SVM classifier was incorporated into an active contour model to improve the accuracy of the segmentation. From our experiments, the proposed active learning strategy can achieve a comparable result with 5 times fewer labeled data compared with regular machine learning. Our proposed automatic hematoma segmentation system achieved an average Dice coefficient of 0.60 on our dataset, where patients are from multiple health centers and at multiple levels of injury. Our results show that the proposed method can effectively overcome the challenge of limited and highly varied dataset.