Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting
This addresses the problem of automating pathology analysis for computational pathology applications, but it is incremental as it builds on existing models like HoverNet and Cascade Mask-RCNN.
The paper tackles automated nuclear segmentation, classification, and quantification from histology images by proposing a simultaneous semantic and instance segmentation framework, which outperforms baselines by a large margin in the CoNIC Challenge.
We address the problem of automated nuclear segmentation, classification, and quantification from Haematoxylin and Eosin stained histology images, which is of great relevance for several downstream computational pathology applications. In this work, we present a solution framed as a simultaneous semantic and instance segmentation framework. Our solution is part of the Colon Nuclei Identification and Counting (CoNIC) Challenge. We first train a semantic and instance segmentation model separately. Our framework uses as backbone HoverNet and Cascade Mask-RCNN models. We then ensemble the results with a custom Non-Maximum Suppression embedding (NMS). In our framework, the semantic model computes a class prediction for the cells whilst the instance model provides a refined segmentation. We demonstrate, through our experimental results, that our model outperforms the provided baselines by a large margin.