Four pathologists from Longhua Hospital Shanghai University of Traditional Chinese Medicine provide 600 images of gastric cancer pathology images at size 2048$\times$2048 pixels. These images were scanned using a NewUsbCamera and digitized at $\times$20 magnification, tissue-level labels were also given by the four experienced pathologists. Based on that, five biomedical researchers from Northeastern University cropped them to 245,196 sub-sized gastric cancer pathology images, and two experienced pathologists from Liaoning Cancer Hospital and Institute perform the calibration. The 245,196 images were split to three sizes (160$\times$160, 120$\times$120, 80$\times$80) for two categories: abnormal and normal.
Variants: GasHisSDB
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Classification | CoAtNet-1 | CoAtNet: Marrying Convolution and Attention … | 2021-06-09 |
| Image Classification | RegNetY-3.2GF | RegNet: Self-Regulated Network for Image … | 2021-01-03 |
| Image Classification | EfficientNet-b0 | EfficientNet: Rethinking Model Scaling for … | 2019-05-28 |
| Image Classification | Res2Net-50 | Res2Net: A New Multi-scale Backbone … | 2019-04-02 |
| Image Classification | ResNeXt-50-32x4d | Aggregated Residual Transformations for Deep … | 2016-11-16 |
| Image Classification | DenseNet-169 | Densely Connected Convolutional Networks | 2016-08-25 |
| Image Classification | ResNet-18 | Deep Residual Learning for Image … | 2015-12-10 |
| Image Classification | ResNet-50 | Deep Residual Learning for Image … | 2015-12-10 |
Recent papers with results on this dataset: