I know very well that I am not asking a specific question. But I am asking for guidance about how to go about doing some work with medical imaging using NiftyNet. This will certainly empower me to do some work and seek help with pointed questions (They are bound to come).
I have no knowledge of Medical Imaging and usage of niftynet for classification. I am trying to come up with a simple classification task using this dataset and pre-trained models.
I have a small collection of jpg photos of several oral cavities. They are labeled with 3 labels (Normal, pre, pos). I am comfortable with python, pytorch and tensorflow. I need help with the following:
- Where do I look for using NiftyNet pre-trained models for such classification
- Is there any code base to get me going?
Thanks for the help.
Check the NiftyNet documentation, there is a Classification Application Module that you can use for classification problems. If you are looking for NiftyNet pre-trained models, you can check out their model zoo on Github, it contains several models for segmentation and regression tasks. For the code base, you can check out their main repository for the source code.
If you need sample configuration files to get started, you can download any of the samples in the model zoo (for example the Dense Vnet) to get a sense of what you should be including in your configuration files. You can check out the Configuration file page in their documentation to see what options you have.