---
language:
- en
library_name: tf-keras
license: wtfpl
pipeline_tag: image-segmentation
---
# *Cavity Detection Tool* (CADET)

[***CADET***](https://tomasplsek.github.io/CADET/) is a machine learning pipeline trained for identification of surface brightness depressions (so-called *X-ray cavities*) on noisy *Chandra* images of early-type galaxies and galaxy clusters. The pipeline consists of a convolutional neural network trained for producing pixel-wise cavity predictions and a DBSCAN clustering algorithm, which decomposes the predictions into individual cavities. The pipeline is further described in [Plšek et al. 2023](https://arxiv.org/abs/2304.05457).

![Architecture](figures/architecture.png)

## How to use

```python
from huggingface_hub import from_pretrained_keras

model = from_pretrained_keras("Plsek/CADET-v1")

y_pred = model.predict(X.reshape(1,128,128,1))
```

## How to cite

The ***CADET*** pipeline was originally developed as a part of my [diploma thesis](https://is.muni.cz/th/x68od/?lang=en) and was further described in [Plšek et al. 2023](https://arxiv.org/abs/2304.05457). If you use the ***CADET***  pipeline in your research, please cite the following paper:

```
@misc{plšek2023cavity,
      title={CAvity DEtection Tool (CADET): Pipeline for automatic detection of X-ray cavities in hot galactic and cluster atmospheres}, 
      author={Tomáš Plšek and Norbert Werner and Martin Topinka and Aurora Simionescu},
      year={2023},
      eprint={2304.05457},
      archivePrefix={arXiv},
      primaryClass={astro-ph.HE}
}
```