Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response
This addresses the time-consuming annotation burden in biomedical research for cell shape analysis, offering a weakly supervised approach that can use simpler annotations like nuclear stains.
The paper tackles the problem of segmenting individual cells in dense conditions with unclear boundaries without requiring detailed boundary annotations, achieving the highest accuracy compared to conventional methods on multiple datasets with various cell types and microscopy types.
Cell shape analysis is important in biomedical research. Deep learning methods may perform to segment individual cells if they use sufficient training data that the boundary of each cell is annotated. However, it is very time-consuming for preparing such detailed annotation for many cell culture conditions. In this paper, we propose a weakly supervised method that can segment individual cell regions who touch each other with unclear boundaries in dense conditions without the training data for cell regions. We demonstrated the efficacy of our method using several data-set including multiple cell types captured by several types of microscopy. Our method achieved the highest accuracy compared with several conventional methods. In addition, we demonstrated that our method can perform without any annotation by using fluorescence images that cell nuclear were stained as training data. Code is publicly available in "https://github.com/naivete5656/WSISPDR".