Colorectal Nuclear Segmentation and Phenotypes
The colorectal nuclear segmentation and phenotypes (CoNSeP) dataset consists of 41 H&E stained image tiles, each of size 1,000×1,000 pixels at 40× objective magnification. The images were extracted from 16 colorectal adenocarcinoma (CRA) WSIs, each belonging to an individual patient, and scanned with an Omnyx VL120 scanner within the department of pathology at University Hospitals Coventry and Warwickshire, UK.
Source: HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images
Image Source: Graham et al
Variants: CoNSeP
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Multi-tissue Nucleus Segmentation | PointNu-Net | PointNu-Net: Keypoint-assisted Convolutional Neural Network … | 2021-11-01 |
| Multi-tissue Nucleus Segmentation | HoVer-Net | HoVer-Net: Simultaneous Segmentation and Classification … | 2018-12-16 |
Recent papers with results on this dataset: