Virtual dental implant placement in cone-beam computed tomography (CBCT) is a prerequisite for digital implant surgery, carrying clinical significance. This study aims to achieve intelligent virtual dental implant placement through a 3-dimensional (3D) segmentation strategy, generating virtual implant from the edentulous region of CBCT and employed an approximation module for mathematical optimization. The tool demonstrated good performance in predicting both the dimension and position of the virtual implants, showing significant clinical application potential in implant planning.
conda create -n impgen python=3.8
conda activate impgen
pip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt- Make datasets by make_implant_dataset.py and make_location_dataset.py.
- Use train.py (or nnU-Net) to train location and generation models.
- Use test.py (or nnU-Net) to do inference.
- (Optional) Use postprocessing.py to get a standard cylinder.
- Use evaluation.py to evaluate generated implants.
- Use image_rebuild.py to rebuild augmented images (nii.gz and dicom) for further usage.
