期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 41, 期 10, 页码 2582-2597出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2022.3169449
关键词
Image segmentation; Semantics; Biomedical imaging; Videos; Three-dimensional displays; Earth; Forestry; Instance segmentation; earth mover's distance; integer linear programming; videos; 3D images
类别
资金
- NSF [CCF-1617735]
- U.S. Army Research Office [W911NF-17-1-0448]
- Notre Dame Eck Institute for Global Health
The study introduces a novel framework, hierarchical earth mover's distance (H-EMD), for instance segmentation in biomedical images, which effectively explores the probability maps generated by DL models to achieve better instance segmentation results.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据