Weakly Supervised Nuclei Segmentation Via Instance Learning

Weakly supervised nuclei segmentation is a critical prob- lem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost. Adopting point annotations, previous methods mostly rely on less expressive representations for nuclei instances and thus have difficulty in handling crowded nuclei. In this pa- per, we propose to decouple weakly supervised semantic and instance segmentation in order to enable more effective subtask learning and to promote instance-aware representa- tion learning. To achieve this, we design a modular deep network with two branches: a semantic proposal network and an instance encoding network, which are trained in a two-stage manner with an instance-sensitive loss. Empirical results show that our approach achieves the state-of-the-art performance on two public benchmarks of pathological im- ages from different types of organs. Our code is available at https://github.com/weizhenFrank/WeakNucleiSeg.