Lymph node detection and segmentation in chest CT data using discriminative learning and a spatial prior
Lymph node detection and segmentation in chest CT data using discriminative learning and a spatial prior
复制标题
DOI：
10.1016/j.media.2012.11.001
复制
发表时间：
2013-02-01
影响因子：
10.9
通讯作者：
Comaniciu, Dorin
中科院分区：
文献类型：
--
作者：
Feulner, Johannes;Zhou, S. Kevin;Comaniciu, Dorin
淋巴结具有高度的临床相关性，在临床实践中通常需要考虑。然而，由于混乱和低对比度，自动检测具有挑战性。本文提出了一种全自动检测和分割胸部 3D 计算机断层扫描图像中淋巴结的方法。淋巴结很容易与其他结构混淆，因此尽可能多地结合解剖学先验知识以实现良好的检测性能至关重要。在这里，使用学习到的空间分布先验来对这些知识进行建模。提出了复杂性不断增加的不同现有类型并进行了相互比较。这与强大的判别模型相结合，可以根据外观检测淋巴结。它首先生成一些可能的淋巴结中心位置的候选者。然后，用检测到的候选者初始化分割方法。图割法适用于淋巴结分割问题。我们提出了一种仅需要单个正种子的设置，同时解决了图割的小割问题。此外，我们提出了从分割中提取的特征集。分类器在此特征集上进行训练并用于拒绝误报。对 54 个 CT 数据集的交叉验证表明，对于每个体积图像固定数量的 4 个误报，使用空间先验时，检测率大大提高了一倍以上。总的来说，我们提出的方法检测纵隔淋巴结的真阳性率为 52.0%，每个体积图像仅 3.1 个误报，而每个体积图像只有 6.1 个误报，真阳性率为 60.9%，这与之前的纵隔淋巴结检测工作相比是有利的。 (C) 2012 Elsevier B.V. 保留所有权利。
Lymph nodes have high clinical relevance and routinely need to be considered in clinical practice. Automatic detection is, however, challenging due to clutter and low contrast. In this paper, a method is presented that fully automatically detects and segments lymph nodes in 3-D computed tomography images of the chest. Lymph nodes can easily be confused with other structures, it is therefore vital to incorporate as much anatomical prior knowledge as possible in order to achieve a good detection performance. Here, a learned prior of the spatial distribution is used to model this knowledge. Different prior types with increasing complexity are proposed and compared to each other. This is combined with a powerful discriminative model that detects lymph nodes from their appearance. It first generates a number of candidates of possible lymph node center positions. Then, a segmentation method is initialized with a detected candidate. The graph cuts method is adapted to the problem of lymph nodes segmentation. We propose a setting that requires only a single positive seed and at the same time solves the small cut problem of graph cuts. Furthermore, we propose a feature set that is extracted from the segmentation. A classifier is trained on this feature set and used to reject false alarms. Cross-validation on 54 CT datasets showed that for a fixed number of four false alarms per volume image, the detection rate is well more than doubled when using the spatial prior. In total, our proposed method detects mediastinal lymph nodes with a true positive rate of 52.0% at the cost of only 3.1 false alarms per volume image and a true positive rate of 60.9% with 6.1 false alarms per volume image, which compares favorably to prior work on mediastinal lymph node detection. (C) 2012 Elsevier B.V. All rights reserved.