adrianrm/pneumoniamnist

---
license: cc-by-4.0
task_categories:
- image-classification
tags:
- medical
- medmnist
- pneumoniamnist
configs:
- config_name: train-all-res224
data_files:
- split: train
path: train-all-res224/*.parquet
- config_name: train-normal-res224
data_files:
- split: train
path: train-normal-res224/*.parquet
- config_name: train-pneumonia-res224
data_files:
- split: train
path: train-pneumonia-res224/*.parquet
- config_name: val-all-res224
data_files:
- split: val
path: val-all-res224/*.parquet
- config_name: val-normal-res224
data_files:
- split: val
path: val-normal-res224/*.parquet
- config_name: val-pneumonia-res224
data_files:
- split: val
path: val-pneumonia-res224/*.parquet
- config_name: test-all-res224
data_files:
- split: test
path: test-all-res224/*.parquet
- config_name: test-normal-res224
data_files:
- split: test
path: test-normal-res224/*.parquet
- config_name: test-pneumonia-res224
data_files:
- split: test
path: test-pneumonia-res224/*.parquet
---

# pneumoniamnist (MedMNIST)

**Source:** [pneumoniamnist](https://medmnist.com/)
**Task:** binary-class
**Resolutions:** 224x224
**License:** CC BY 4.0

## Description

The PneumoniaMNIST is based on a prior dataset of 5,856 pediatric chest X-Ray images. The task is
binary-class classification of pneumonia against normal. We split the source training set with a
ratio of 9:1 into training and validation set and use its source validation set as the test set. The
source images are gray-scale, and their sizes are (384−2,916)×(127−2,713). We center-crop the images
and resize them into 1×28×28.

## Config naming convention

```
{split}-{class}-{res}

split : train | val | test
class : all | <sanitized class name>
res : res28 | res64 | res128 | res224
```

## Loading examples

```python
from datasets import load_dataset

# All training images at 224px
ds = load_dataset('.../pneumoniamnist', 'train-all-res224', split='train')

# Only 'normal' class, training split
ds = load_dataset('.../pneumoniamnist', 'train-normal-res224', split='train')
```

## Class labels

- `0` — normal (config key: `normal`)
- `1` — pneumonia (config key: `pneumonia`)

## Class distribution

### 224x224

**train** (N=4,708, IR=2.88x)

| Class | Config key | Count | Share |
|-------|-----------|------:|------:|
| normal | `normal` | 1,214 | 25.8% |
| pneumonia | `pneumonia` | 3,494 | 74.2% |

**val** (N=524, IR=2.88x)

| Class | Config key | Count | Share |
|-------|-----------|------:|------:|
| normal | `normal` | 135 | 25.8% |
| pneumonia | `pneumonia` | 389 | 74.2% |

**test** (N=624, IR=1.67x)

| Class | Config key | Count | Share |
|-------|-----------|------:|------:|
| normal | `normal` | 234 | 37.5% |
| pneumonia | `pneumonia` | 390 | 62.5% |

## Citation

```bibtex
@article{medmnistv2,
title={MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classification},
author={Yang, Jiancheng and Shi, Rui and Wei, Donglai and Liu, Zequan
and Zhao, Lin and Ke, Bilian and Pfister, Hanspeter and Ni, Bingbing},
journal={Scientific Data},
year={2023}
}
```