Weakly-Supervised Nucleus Segmentation Based on Point Annotations: A Coarse-to-Fine Self-Stimulated Learning Strategy
| Autor: | Jun Zhang, Haocheng Shen, Jianhua Yao, Kezhou Yan, Shannon Che, Pei Dong, Kuan Tian, Pifu Luo, Xiao Han |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Computer science business.industry Digital pathology Pattern recognition 030218 nuclear medicine & medical imaging Image (mathematics) 03 medical and health sciences Task (computing) 030104 developmental biology 0302 clinical medicine Binary classification Code (cryptography) Segmentation Point (geometry) Artificial intelligence Cluster analysis business |
| Zdroj: | Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 ISBN: 9783030597214 MICCAI (5) |
| DOI: | 10.1007/978-3-030-59722-1_29 |
| Popis: | Nucleus segmentation is a fundamental task in digital pathology analysis. However, it is labor-expensive and time-consuming to manually annotate the pixel-level full nucleus masks, while it is easier to make point annotations. In this paper, we propose a coarse-to-fine weakly-supervised framework to train the segmentation model from only point annotations to reduce the labor cost of generating pixel-level masks. Our coarse-to-fine strategy can improve segmentation performance progressively in a self-stimulated learning manner. Specifically, to generate coarse segmentation masks, we employ a self-supervision strategy using clustering to perform the binary classification. To avoid trivial solutions, our model is sparsely supervised by annotated positive points and geometric-constrained negative boundaries, via point-to-region spatial expansion and Voronoi partition, respectively. Then, to generate fine segmentation masks, the prior knowledge of edges in the unadorned image is additionally utilized by our proposed contour-sensitive constraint to further tune the nucleus contours. Experimental results on two public datasets show that our model trained with weakly-supervised data (i.e., point annotations) achieves competitive performance compared with the model trained with fully supervised data (i.e., full nucleus masks). The code is made publicly available at https://github.com/tiankuan93/C2FNet. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|