The NCT-CRC-HE-100K dataset is a set of 100,000 non-overlapping image patches extracted from 86 H$\&$E stained human cancer tissue slides and normal tissue from the NCT biobank (National Center for Tumor Diseases) and the UMM pathology archive (University Medical Center Mannheim). While the dataset Colorectal Cacner-Validation-Histology-7K (CRC-VAL-HE-7K) consist of 7180 images extracted from 50 patients with colorectal adenocarcinoma and were used to create a dataset that does not overlap with patients in the NCT-CRC-HE-100K dataset. It was created by pathologists by manually delineating tissue regions in whole slide images into the following nine tissue classes: Adipose (ADI), background (BACK), debris (DEB), lymphocytes (LYM), mucus (MUC), smooth muscle (MUS), normal colon mucosa (NORM), cancer-associated stroma (STR), colorectal adenocarcinoma epithelium (TUM).
Image source: https://www.cs.unc.edu/~mn/sites/default/files/macenko2009.pdf
Variants: NCT-CRC-HE-100K
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Classification | SAG-ViT | SAG-ViT: A Scale-Aware, High-Fidelity Patching … | 2024-11-14 |
| Medical Image Classification | ResNeXt-50-32x4d | ResNet strikes back: An improved … | 2021-10-01 |
| Medical Image Classification | RegNetY-3.2GF | RegNet: Self-Regulated Network for Image … | 2021-01-03 |
| Medical Image Classification | Efficientnet-b0 | EfficientNet: Rethinking Model Scaling for … | 2019-05-28 |
| Medical Image Classification | Res2Net-50 | Res2Net: A New Multi-scale Backbone … | 2019-04-02 |
| Medical Image Classification | DenseNet-169 | Densely Connected Convolutional Networks | 2016-08-25 |
| Medical Image Classification | ResNet-18 | Deep Residual Learning for Image … | 2015-12-10 |
| Medical Image Classification | ResNet-50 | Deep Residual Learning for Image … | 2015-12-10 |
Recent papers with results on this dataset: