Deep learning (DL) based semantic segmentation methods have achieved excellent performance in biomedical image segmentation, producing high quality probability maps to allow extraction of rich instance information to facilitate good instance segmentation. While numerous efforts were put into developing new DL semantic segmentation models, less attention was paid to a key issue of how to effectively explore their probability maps to attain the best possible instance segmentation. We observe that probability maps by DL semantic segmentation models can be used to generate many possible instance candidates, and accurate instance segmentation can be achieved by selecting from them a set of "optimized" candidates as output instances. Further, the generated instance candidates form a well-behaved hierarchical structure (a forest), which allows selecting instances in an optimized manner. Hence, we propose a novel framework, called hierarchical earth mover's distance (H-EMD), for instance segmentation in biomedical 2D+time videos and 3D images, which judiciously incorporates consistent instance selection with semantic-segmentation-generated probability maps. H-EMD contains two main stages. (1) Instance candidate generation: capturing instance-structured information in probability maps by generating many instance candidates in a forest structure. (2) Instance candidate selection: selecting instances from the candidate set for final instance segmentation. We formulate a key instance selection problem on the instance candidate forest as an optimization problem based on the earth mover's distance (EMD), and solve it by integer linear programming. Extensive experiments on eight biomedical video or 3D datasets demonstrate that H-EMD consistently boosts DL semantic segmentation models and is highly competitive with state-of-the-art methods.
翻译:深度学习( DL) 的语义分解方法在生物医学图像分解中取得了极佳的性能, 产生了高质量的概率图, 以便提取丰富的实例信息, 从而便于进行良好的实例分解。 虽然在开发新的 DL 语义分解模型方面做出了许多努力, 但对于如何有效探索其概率图以达到最佳可能的示例分解的关键问题, 却没有那么重视。 我们观察到, DL 语义分解模型的概率图可用于产生许多可能的试选对象, 并且可以通过从中选择一组“ 优化” 候选人作为输出实例, 从而实现准确的示例分解。 此外, 生成的实选候选人形成了一种稳妥的等级结构( 森林) 。 因此, 我们提出了一个新颖的框架, 称为等级地心移动器的距离( H- EMD ), 例如, 生物2D+ 时间编程视频和 3D 图像, 明智地将实例选择与语义分解- 高度的概率地图相匹配。 H- EMD 包含两个主要阶段。 (1) 试度候选人生成: 获取实例- 直观- 直观 选择 H- 直径段 选择 选择选择选择选择选择候选人的选机构