In the Glioma-MDC 2025 Challenge, a *case* is defined as a single histopathological image patch of glioma tissue, with multiple cases provided for analysis. Each *case* includes **varied locations** represented by coordinates and their **corresponding labels**. The objective is to develop a model capable of accurately predicting labels in these pre-annotated regions.

## Training Cases
Each training case comprises a stained image patch accompanied by a JSON file detailing the coordinates identifying specific cell locations. These cells are labeled as either *"Non-mitosis"* or *"Mitosis"*, providing the ground truth necessary for model training.

## Test Cases
Each test case also includes a stained image patch and an associated JSON file with multiple coordinate locations. However, the labels for these coordinates are left *blank*. Challenge participants must analyze these unlabeled coordinates and classify each one as either *"Non-mitosis"* or *"Mitosis"*.


### Example of imaging
Showing training0001.jpg. Each H&E slide is standardized as 512-by-512 pixels `jpg` image.
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F22565116%2F0819052a29a3dc7f0752c39dea804af4%2Ftraining0001.jpg?generation=1728408278142408&alt=media)

### Example of annotation in JSON file
Showing training0001.json annotation file.
- `label` is the classification label
- `points` are the polygon points in pixel coordinate
```
{
  "version": "5.4.1",
  "flags": {},
  "shapes": [
    {
      "label": "Non-mitosis",
      "points": [
        [
          262.3829787234043,
          187.56028368794324
        ],
        [
          269.4751773049645,
          187.56028368794324
        ],
        ...
      ],
      "group_id": null,
      "description": "",
      "shape_type": "polygon",
      "flags": {},
      "mask": null
    }
  ],
  "imagePath": "training0001.jpg",
  "imageHeight": 512,
  "imageWidth": 512
}
```