Song Qi, Chen Mingqing, Bai Junjie, Sonka Milan, Wu Xiaodong
Department of Electrical & Computer Engineering, University of Iowa, Iowa City, IA 52242, USA.
Inf Process Med Imaging. 2011;22:61-72. doi: 10.1007/978-3-642-22092-0_6.
Multi-object segmentation with mutual interaction is a challenging task in medical image analysis. We report a novel solution to a segmentation problem, in which target objects of arbitrary shape mutually interact with terrain-like surfaces, which widely exists in the medical imaging field. The approach incorporates context information used during simultaneous segmentation of multiple objects. The object-surface interaction information is encoded by adding weighted inter-graph arcs to our graph model. A globally optimal solution is achieved by solving a single maximum flow problem in a low-order polynomial time. The performance of the method was evaluated in robust delineation of lung tumors in megavoltage cone-beam CT images in comparison with an expert-defined independent standard. The evaluation showed that our method generated highly accurate tumor segmentations. Compared with the conventional graph-cut method, our new approach provided significantly better results (p < 0.001). The Dice coefficient obtained by the conventional graph-cut approach (0.76 +/- 0.10) was improved to 0.84 +/- 0.05 when employing our new method for pulmonary tumor segmentation.
具有相互作用的多目标分割是医学图像分析中的一项具有挑战性的任务。我们报告了一种针对分割问题的新颖解决方案，其中任意形状的目标物体与医学成像领域中广泛存在的类似地形的表面相互作用。该方法在多个物体的同时分割过程中纳入了上下文信息。通过在我们的图模型中添加加权图间弧来编码物体 - 表面相互作用信息。通过在低阶多项式时间内求解单个最大流问题来获得全局最优解。与专家定义的独立标准相比，在兆伏级锥形束CT图像中对肺肿瘤进行稳健描绘时评估了该方法的性能。评估表明，我们的方法生成了高度准确的肿瘤分割结果。与传统的图割方法相比，我们的新方法提供了显著更好的结果（p < 0.001）。当采用我们的新方法进行肺部肿瘤分割时，传统图割方法获得的骰子系数（0.76 +/- 0.10）提高到了0.84 +/- 0.05。
