cristinaperez9/VISTACT

---
license: cc-by-nc-nd-4.0
task_categories:
- image-to-image
language:
- en
tags:
- pathology
- virtual_staining
- microCT
- 3D_pathology
size_categories:
- 100B<n<1T
---

# VISTACT: VIrtual histological STAining of micro-Computed Tomography<!-- omit in toc -->

<img src="vistact_overview.jpg" style="width: 50%;" align="right" />

## What is VISTACT dataset?

It is a set of phase-contrast micro-computed tomography volumes (PCμCT) of human lung tissue with corresponding serial histological sections stained with Elastin-van-Gieson (EvG), which is the gold-standard stain for pulmonary hypertension disease in the pathology workflow.
Additionally, we also include a PCμCT dataset from mouse heart-lung tissue with corresponding H\&E histological sections.
**Scan resolution**: Human lung microCT scans: 1.63 μm/voxel ; Mouse lung microCT scan: 0.88 μm/voxel.

📄 [Preprint](https://www.biorxiv.org/content/10.1101/2025.10.02.678959v1)

🤖 [Codebase](https://github.com/cristinaperez9/VISTACT)

## Instructions for Setting Up HuggingFace Account and inspect the dataset

### 1. Create an Account on HuggingFace
Follow the instructions provided on the [HuggingFace sign-up page](https://huggingface.co/join).

**At this stage, you can already manually inspect the data by navigating in the `Files and version`.**

<!-- ### Additional instructions for Setting Up HuggingFace Token and download the dataset from Python:

### 3. Create a Hugging Face Token

1. **Go to Settings:** Navigate to your profile settings by clicking on your profile picture in the top right corner and selecting `Settings` from the dropdown menu.

2. **Access Tokens:** In the settings menu, find and click on `Access tokens`.

3. **Create New Token:**
- Click on `New token`.
- Set the token name (e.g., `vistact`).
- Set the access level to `Write`.
- Click on `Create`.

4. **Copy Token:** After the token is created, copy it to your clipboard. You will need this token for authentication.

### 4. Logging in

1. Install huggingface-hub

```
pip install huggingface-hub
```

2. Log in

```
from huggingface_hub import login

login(token="YOUR HUGGINGFACE TOKEN")
```

## Download the entire VISTACT dataset:
```python
import os
import zipfile

from huggingface_hub import snapshot_download
from tqdm import tqdm

local_dir='vistact_data' # vistact will be dowloaded to this folder

# Note that the full dataset is around 1TB of data
download_vistact('*', local_dir) -->

# Cite<a id='ack'></a>
If you find this dataset useful in your research, please cite our paper:

```bibtext
@article{almagro2025histology,
title={Histology-guided 3D virtual staining of microCT-imaged lung tissue via deep learning},
author={Almagro-P{\'e}rez, Cristina and Peruzzi, Niccol{\`o} and Galambos, Csaba and Song, Andrew H and Brunnstr{\"o}m, Hans and Gawlik, Kinga I and Stampanoni, Marco and Tran-Lundmark, Karin and Lovric, Goran},
journal={bioRxiv},
pages={2025--10},
year={2025},
publisher={Cold Spring Harbor Laboratory}
}
```