Colon Nuclei Instance Segmentation using a Probabilistic Two-Stage Detector
This work addresses the time-consuming and error-prone process of cancer diagnosis for pathologists, though it appears incremental as it adapts an existing detection model for segmentation.
The paper tackled the problem of automating cancer diagnosis by proposing SegCenterNet2, a modified CenterNet2 model for colon nuclei instance segmentation, and demonstrated that it outperforms Mask R-CNN on the CoNIC challenge dataset metrics.
Cancer is one of the leading causes of death in the developed world. Cancer diagnosis is performed through the microscopic analysis of a sample of suspicious tissue. This process is time consuming and error prone, but Deep Learning models could be helpful for pathologists during cancer diagnosis. We propose to change the CenterNet2 object detection model to also perform instance segmentation, which we call SegCenterNet2. We train SegCenterNet2 in the CoNIC challenge dataset and show that it performs better than Mask R-CNN in the competition metrics.