-
Notifications
You must be signed in to change notification settings - Fork 199
FAQ
- What is a MONAILabel App?
- What is the difference between DeepGrow and DeepEdit
- Does MONAILabel work for multiple labels?
- Which image modalities MONAI Label supports?
- Does MONAILabel support multimodality images?
- What is the difference between MONAILabel and NVIDIA Clara AI-Assisted Annotation (AIAA) tool?
- Can I use other libraries different from MONAI to create a MONAILabel App?
- Does MONAILabel support other inputs such as ROI, Line, or closed curves from Slicer?
- How to create a fixed validation split while training and updating models?
It is a software application that developers designed to run on the MONAILabel server. It is where researchers or developers define their own pipeline to facilitate the image annotation process. They can use the provided Slicer MONAI Label plugin or customize their own to process inputs and outputs sent to the App. An example of this is DeepEdit, which uses clicks provided by the user/clinician to facilitate the image annotation.
DeepGrow is a click-based interactive segmentation model, where the user can guide the segmentation with positive and negative clicks. The positive clicks are intended to guide the segmentation towards the region of interest while the negative clicks are used for neglecting the background (Sakinis, T., "Interactive segmentation of medical images through fully convolutional neural networks", arXiv e-prints, 2019).
DeepEdit combines the power of this interactive model with a standard segmentation algorithm that only uses the only images to segment the organ of interest. This means DeepEdit allows the user to do both interactive and standard segmentation.
The provided MONAI Label Apps in version 0.1 were developed to work on single-label annotation. However, MONAI Label can easily support Apps that work for multiple label annotation.
Users can develop MONAI Label Apps for any modality they want. Version 0.1 of MONAI Label made Apps available to work on CT and MR images.
Yes, but this depends more on the viewer than the MONAI Label Apps. Users can easily create Apps that process multimodality images.
For now, MONAI label is targeted for a single researchers/clinician user with a workstation. Whereas NVIDIA Clara AIAA can scale for multiple annotators being served from the same Annotation server using different clients. Another main difference is that MONAI Label allows the user to create App to train and test their own pipeline. NVIDIA Clara AIAA was mainly developed to perform inference.
Yes, users can use any library they like. However, MONAI Label team recommends the use of MONAI as the primary library to create AI models.
Yes, users can send to the server any file their App uses as input. It can be points, segmentations, ROIs, etc. To do this, users can start from the current Slicer module and create their custom Slicer module that communicates with a MONAI Label App.
Currently the 'Model Update' process based on the validation split hyper-parameter randomly selects the 3D volumes for the validation. However, it is possible that a user/developer would want to fix the validation split as they might be interested in observing the consistent performance improvements over a fixed set.
This can be done easily in the custom app that is being created by the user. The template for a custom app always has main.py. For e.g the specific use case of Deepgrow Spleen App, please look at the following lines of code in the main.py:
# Datalist for train/validation
train_d, val_d = self.partition_datalist(self.datastore().datalist(), request.get("val_split", 0.2))
The above line can just be replaced with the entire datastore being assigned to the training data list such as:
train_d = self.datastore().datalist()
val_d = Give your own dictionary as a datastore {} here in the same format as in the datastore, make sure the keys are consistent as image and label