Pre-trained models

For convenience, the following pre-trained models are ready-to-use:

  • t2-tumor: Cord tumor segmentation model, trained on T2-weighted contrast.
  • t2star_sc: Spinal cord segmentation model, trained on T2-star contrast.
  • mice_uqueensland_gm: Gray matter segmentation model on mouse MRI. Data from University of Queensland.
  • mice_uqueensland_sc: Cord segmentation model on mouse MRI. Data from University of Queensland.
  • findcord_tumor: Cord localisation model, trained on T2-weighted images with tumor.
  • model_find_disc_t1: Intervertebral disc detection model trained on T1-weighted images.
  • model_find_disc_t2: Intervertebral disc detection model trained on T2-weighted images.

Packaged model format

Each folder contains a model (.pt or .onnx) with its corresponding configuration file (.json). The packaged model is automatically generated during training. The folder containing the packaged model will be saved at the path specified by the key log_directory in the configuration file. The packaged model, the configuration file, and the model file will be named by the string specified by the key model_name in the configuration file.

my_model
├── my_model.json
└── my_model.onnx