Nuclei Instance Segmentation and Classification in Histopathological Images using a DT-Yolact

Nuclei instance segmentation and classification in histology images is a challenging task, which requires not only a precise semantic segmentation at pixel-level but also an accurate classification at instance-level. To tackle the problem, in this paper, we propose a Double-Tower Yolact network named DT-Yolact, which introduces a bottom-up path augmentation (BPA) module to pair with the feature py...