RailNet Tooth Segmentation In CBCT Image
This model has been pushed to the Hub using the PytorchModelHubMixin integration: Hugging Face Space (available now): Code: Paper: RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT
Modellquelle
- Art
- Other
- Dateigröße
- 36,1–801 MB
- Version
- vRevision f00ceeb
- Aktualisiert
- 6. Okt. 2026
- Downloads
- 43
- Quelle
- Hugging Face
Quellenbeschreibung
This model has been pushed to the Hub using the PytorchModelHubMixin integration:
- Hugging Face Space (available now):
https://huggingface.co/spaces/Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image - Code: https://github.com/Tournesol-Saturday/RAIL
- Paper: RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT
Steps to use our model in this repository:
- Clone this repository with the following command:
git clone https://huggingface.co/Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image cd railNet-tooth-segmentation-in-CBCT-image - Create a virtual environment to experience our model using the following command:
conda create -n railnet python=3.10 conda activate railnet pip install -r requirements.txt python gradio_app.py - In the current working directory, find the
example_input_filefolder.
Select an arbitrary.h5file in this folder and drag it into theGradiointerface for model inference. - Waiting for about 1min~2min30s, the model inference is completed and the segmentation result and 3D rendering visualization will be produced.
Both the original image and the segmentation result are saved in.nii.gzformat in theoutputfolder of the same directory. - Since
Gradioperforms 1/2 downsampling on the 3D segmentation visualization, the segmentation accuracy is degraded.
Users can drag the.nii.gzformat files in theoutputfolder into theITK-SNAPsoftware to view the accurate segmentation visualization.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 6. Okt.
Download files
Modellartefakte
10 Artefakte
Modellartefakte
10 Artefaktemodel weights/rail_0_iter_7995_best.pth
pth · 36,1 MB · SHA-256 9085f5b56d75…79d3 · Hugging Face
Download filemodel weights/rail_1_iter_7995_best.pth
pth · 36,1 MB · SHA-256 66a4b9ba3314…2857 · Hugging Face
Download filemodel weights/rail_2_iter_7995_best.pth
pth · 96,6 MB · SHA-256 ef122d5b0770…4359 · Hugging Face
Download filemodel weights/rail_3_iter_7995_best.pth
pth · 96,6 MB · SHA-256 01e921070416…f85d · Hugging Face
Download filemodel weights/roi_best_model.pth
pth · 36,1 MB · SHA-256 629e02002b68…ae57 · Hugging Face
Download fileQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- tags: - model_hub_mixin - pytorch_model_hub_mixin - medical license: apache-2.0 language: - en metrics: - Dice - Jaccard - 95HD - ASD pipeline_tag: image-segmentation library_name: pytorch --- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration: - **Hugging Face Space** (available now): https://huggingface.co/spaces/Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image - Code: https://github.com/Tournesol-Saturday/RAIL - Paper: [RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT](https://huggingface.co/papers/2505.03538) **Steps to use our model in this repository:** 1. Clone this repository with the following command: ```bash git clone https://huggingface.co/Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image cd railNet-tooth-segmentation-in-CBCT-image ``` 3. Create a virtual environment to experience our model using the following command: ```python conda create -n railnet python=3.10 conda activate railnet pip install -r requirements.txt python gradio_app.py ``` 4. In the current working directory, find the `example_input_file` folder. Select an arbitrary `.h5` file in this folder and drag it into the `Gradio` interface for model inference. 5. Waiting for about 1min~2min30s, the model inference is completed and the segmentation result and 3D rendering visualization will be produced. Both the original image and the segmentation result are saved in `.nii.gz` format in the `output` folder of the same directory. 6. Since `Gradio` performs 1/2 downsampling on the 3D segmentation visualization, the segmentation accuracy is degraded. Users can drag the `.nii.gz` format files in the `output` folder into the `ITK-SNAP` software to view the accurate segmentation visualization.
Source context: 43 downloads · 5 likes · Pipeline image-segmentation · Library pytorch · Repo Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image
Source context: 13 downloads · 3 likes · Pipeline image-segmentation · Library pytorch · Repo Tournesol-Saturday/railNet-tooth-segmentation-in-CBCT-image
