Microscopy cell nuclei segmentation with enhanced U-Net

摘要

Cell or cell nuclei segmentation is typically the first critical step for biomedical microscopy image analysis [ ]. On the basis of accurate cell or cell nuclei segmentation, multiple biological or medical analysis can be performed subsequently, including cell type classification [ ], particular cell counting [ ], cell phenotype analysis [ ] etc., providing valuable diagnostic information for doctors and researchers. Although conventional image processing techniques are still employed for this time and labor consuming task, they often cannot achieve the optimized performance due to multiple reasons, such as limited capability of dealing with diverse images [ ].