railNet Open-Source Teeth Segmentation Model - Achieve Accurate Teeth Segmentation for Free Based on CBCT Images

Home

Railnet Tooth Segmentation In CBCT Image

Developed by Tournesol-Saturday

PyTorch-based CBCT image tooth segmentation model using region-aware guided learning for semi-supervised segmentation

Image Segmentation

PyTorch

EnglishOpen Source License:Apache-2.0 #CBCT tooth segmentation #Semi-supervised learning #3D medical imaging

Downloads 144

Release Time : 5/8/2025

Model Overview

This model focuses on tooth segmentation tasks in Cone Beam CT (CBCT) images, achieving high-precision segmentation through Region-Aware Guided Learning (RAIL) method, particularly suitable for dental diagnosis and treatment planning

Model Features

Semi-supervised learning

Utilizes region-aware guided learning method to effectively train with limited annotated data

High-precision segmentation

Achieves accurate tooth structure segmentation in CBCT images

3D visualization support

Provides 3D rendering visualization of segmentation results, compatible with ITK-SNAP software

Model Capabilities

CBCT image analysis

Tooth structure segmentation

3D medical image processing

Semi-supervised learning

Use Cases

Dental diagnosis

Tooth structure analysis

Used for tooth structure segmentation and visualization prior to dental diagnosis

Provides precise tooth segmentation results to assist diagnosis

Treatment planning

Dental implant planning

Provides accurate tooth and bone structure information for dental implant surgery

Helps doctors develop more precise surgical plans

🚀 railNet-tooth-segmentation-in-CBCT-image

This model is designed for tooth segmentation in CBCT images, leveraging the PytorchModelHubMixin integration. It provides a user - friendly way to perform image segmentation tasks with detailed usage steps.

🚀 Quick Start

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

📦 Installation

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

💻 Usage Examples

Basic Usage

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.
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.
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.

📄 License

This model is licensed under the apache - 2.0 license.

Property	Details
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

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご