CoNIC Solution

03/04/2022

∙

by   Wenhua Zhang, et al.

∙

0

∙

share

Nuclei segmentation and classification has been a challenge due to the high inter-class similarity and intra-class variability. Thus, a large-scale annotation and a specially-designed algorithm are needed to solve this problem. Lizard is therefore a great promotion in this area, containing around half a million nuclei annotated. In this paper, we propose a two-stage pipeline used in the CoNIC competition, which achieves much better results than the baseline method. We adopt a similar model as the original baseline method: HoVerNet, as the segmentaion model and then develop a new classification model to fine-tune the classification results. Code for this method will be made public soon. This is a conic solution in testing.