KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #ai-agent #developer-tools #codex #typescript #cli #deepseek-harness #claude-code #ai-agents #mcp #rust

MedIAnomaly

★ 86 Open GitHub ↗

[MedIA 2025] MedIAnomaly: A comparative study of anomaly detection in medical images

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# MedIAnomaly: A comparative study of anomaly detection in medical images

This is the repository for our benchmark paper [MedIAnomaly: A comparative study of anomaly detection in medical images](https://arxiv.org/abs/2404.04518).

## Environment

- Python 3.10
- PyTorch 2.1.2

## Data Preparation

We provide the pre-processed seven datasets.

1. Download our pre-processed datasets from: [MedIAnomaly-Data](https://zenodo.org/records/12677223)
2. Download the ISIC2018_Task3_Training, ISIC2018_Task3_Test, and their ground truth from [ISIC2018](https://challenge.isic-archive.com/data/#2018)
3. Unzip the datasets via:

```shell
tar -zxvf RSNA.tar.gz
tar -zxvf VinCXR.tar.gz
tar -zxvf BrainTumor.tar.gz
tar -zxvf LAG.tar.gz
tar -zxvf ISIC2018_Task3.tar.gz
tar -zxvf Camelyon16.tar.gz
tar -zxvf BraTS2021.tar.gz
```

4. Place the `MedIAnomaly-Data` directory in the user's home directory, i.e., `~/MedIAnomaly-Data/`. (Otherwise, you need to modify the data root in your code.)

**Finally, the data path should have the following structure:**

```
~/MedIAnomaly-Data
├─RSNA
│  ├─images
│  └─data.json
├─VinCXR
│  ├─images
│  └─data.json
├─BrainTumor
│  ├─images
│  └─data.json
├─LAG
│  ├─images
│  └─data.json
├─ISIC2018_Task3
│  ├─ISIC2018_Task3_Training_Input
│  ├─ISIC2018_Task3_Training_GroundTruth
│  ├─ISIC2018_Task3_Test_Input
│  └─ISIC2018_Task3_Test_GroundTruth
├─Camelyon16
│  ├─train
│  │  ├─good
│  ├─test
│  │  ├─good
│  └─ └─Ungood
├─BraTS2021
│  ├─train
│  ├─test
│  │  ├─normal
│  │  ├─tumor
└─ └─ └─annotation
```

## Train & Evaluate

### [Reconstruction-based methods](./reconstruction)

- [x] AE ($\ell_2$, $\ell_1$, SSIM, Perceptual Loss)

- [x] AE-Spatial

- [x] VAE

- [x] Constrained AE

- [x] MemAE

- [x] CeAE

- [x] GANomaly

- [x] AE-U

- [x] DAE

- [x] AE-Grad

- [x] VAE-Grad ($Grad_{ELBO}$, $Grad_{KL}$, $Grad_{rec}$, $Grad_{Combi}$)

Train and evaluate these methods via:

```bash
cd reconstruction/;
./train_eval.sh
```

**[Reproduce the results in [AE4AD](https://github.com/caiyu6666/AE4AD)]** Train and evaluate AE with different latent size via:
```bash
cd reconstruction/;
./train_eval_latent_size.sh
```

### [SSL-based methods](./ssl)

#### one-stage

- [x] CutPaste
- [x] FPI
- [x] PII
- [x] NSA

Train and evaluate these methods via:

```bash
cd ssl/one_stage/;
./train_eval.sh
```

#### two-stage

- [x] CutPaste
- [x] AnatPaste
- [x] ResNet18-ImageNet

Train and evaluate these methods via:

```bash
cd ssl/two_stage/;
./train_eval.sh
```

## Visualization

## Acknowledgement

Some datasets and codes in this repository are based on [DDAD-ASR](https://github.com/caiyu6666/DDAD-ASR), [BMAD](https://github.com/DorisBao/BMAD), [NSA](https://github.com/hmsch/natural-synthetic-anomalies), [CutPaste](https://github.com/Runinho/pytorch-cutpaste), [AnatPaste](https://github.com/jun-sato/AnatPaste). We thank the original authors for their excellent work.

## Contact

If any questions, feel free to raise an issue or contact Yu Cai: [yu.cai@connect.ust.hk](mailto:yu.cai@connect.ust.hk).

## Citation
```
@article{cai2024medianomaly,
  title={MedIAnomaly: A comparative study of anomaly detection in medical images},
  author={Cai, Yu and Zhang, Weiwen and Chen, Hao and Cheng, Kwang-Ting},
  journal={arXiv preprint arXiv:2404.04518},
  year={2024}
}
@inproceedings{cai2024rethinking,
  title={Rethinking autoencoders for medical anomaly detection from a theoretical perspective},
  author={Cai, Yu and Chen, Hao and Cheng, Kwang-Ting},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={544--554},
  year={2024},
  organization={Springer}
}
```

MedIAnomaly

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README