🖥️ Lungs segmentation web application

A web-based application for automated lung segmentation using deep learning, powered by Gradio and PyTorch. This tool allows users to upload lung images and obtain segmented outputs efficiently.

---

Try the app

The application is running on Hugging Face, try it using this link!

Example File

If you don't have your own .tif image, the app includes a built-in example file that can be used directly from the UI by clicking "Try an example!".

Load from URL (?file_url)

You can load a remote .tif/.tiff by appending a file_url query parameter to the app URL. Prefer a direct-download link.

• Example on Hugging Face: https://huggingface.co/spaces/qchapp/3d-lungs-segmentation/?file_url=https://zenodo.org/record/8099852/files/lungs_ct.tif?download=1

• Example when running locally: http://127.0.0.1:7860/?file_url=https://zenodo.org/record/8099852/files/lungs_ct.tif?download=1 (or change to point to the corresponding local URL)

Notes:

• Large files may take time to download and render.
• Only .tif/.tiff files are supported.
• If your link isn’t a direct file URL (e.g., redirects to an HTML page), the download will fail. In that case, use the host’s “Direct download” URL or URL‑encode the value of file_url.

---

Installation

We recommend performing the installation in a clean Python environment.

The code requires python>=3.10, as well as pytorch>=2.0. Please install Pytorch first and separately following the instructions for your platform on pytorch.org.

After that please run the following command:

pip install -r requirements.txt

---

Usage

Run:

python app.py

And go to the indicated local URL.

---

Usage as an API

Install gradio_client and run the following Python code:

from pathlib import Path
import shutil
from gradio_client import Client, handle_file

client = Client("qchapp/3d-lungs-segmentation")
result_path = client.predict(
    file_obj=handle_file("https://zenodo.org/record/8099852/files/lungs_ct.tif?download=1"),
    api_name="/segment",
)

dest = Path("outputs/mask.tif")
dest.parent.mkdir(parents=True, exist_ok=True)
shutil.copy(result_path, dest)
print("Saved the mask in:", dest.resolve())

---

About Lungs Segmentation

If you are interested in the package used for segmentation please check the following GitHub repository!

---