An MD.ai project consists of DICOM datasets, users, label groups and labels. To create a project, ensure you have the requisite permissions, and click on "New Project" in the side panel.
Every project should contain at least one dataset. A common use case for having more than one dataset in a project is separating training and test sets. After creating the new project, click on the "Add Dataset" button to create the first dataset. This dataset will serve as the container into which you will load your data. Note the project and dataset IDs.
Supported Medical Modalities
- CR Computed Radiography
- CT Computed Tomography
- MR MRI
- NM Nuclear Medicine
- US Ultrasound
- PT Positron emission tomography
- RG Radiographic imaging (conventional film/screen)
- DX Digital Radiography
- MG Mammography
Load external data into project dataset
If your dataset source is set to "Upload", there are 2 options to load external data:
- Use the web UI directly (draganddrop a folder containing your DICOM images, or use the upload files/upload folder buttons).
- Use the MD.ai CLI tool. This is highly recommended for larger datasets (e.g., >100 MB). See the CLI Usage page for command descriptions.
Once uploading is complete, the uploaded data will be processed in the background. Once finished, the DICOM series thumbnails will appear:
The project can now be launched in the Annotator app:
Attach Project to your GCP Bucket
- Fill in name of bucket
- Give permissions in GCP bucket as outlined next to checkbox
- Check box
The following are the privileges associated with each viewer role.
• no access to project and no cases are visible
View only users
• view cases to which they have been given access or all cases if no restriction set
View and edit users
• create and edit their own annotations • upvote/downvote other users' annotations • reorder labels for themselves • bulk delete their own annotations
• create, edit, and delete Labels and Label Groups • create hanging protocols • assign, invite, and restrict users • create new datasets • download/upload images and annotations • all view/edit functions
• create new projects • have all the admin privileges • superusers are set up directly by MD.ai
Troubleshooting Processing is Stuck
If the processing of files gets stuck at a number divisible by 1000, it's likely due to an issue with your internet stability. You can cancel the current processing task and reload your images.
Go to the Project Card and choose the gear icon on the dataset for which you need to cancel and restart processing. Choose 'Cancel Processing' and then restart with either CLI tool or drag and drop.
Turn off sleep mode
Turn off your computer's sleep mode temporarily for loading large datasets. When the computer goes to sleep, it will disconnect the processing. If that happens, choose
Cancel Processing on the Edit page of the project and reload the data.