LONI Brain Parser Information
Description
LONI Brain Parser software segments 56 anatomical brain structures (both cortical and sub-cortical based on the LPBA40 atlas, Shattuck et al. 2007) by using a learning-based approach and a pre-trained model targeted at common structures of interest. The LONI Brain Parser will expect skull-stripped, registered and normalized data before segmenting (for more information, see the documentation) and this data will subsequently need to be warped back to its original space. Alternatively, a LONI Pipeline Workflow containing LONI Brain Parser is available for download or online usage with these pre- and post- processing steps already set up. The automated segmentation portion usually takes 30 minutes while the whole workflow takes about an hour depending on the complexity of the data and computing power available.
Although LONI Brain Parser comes pre-trained with an ideal model, the software also has the ability to train the model to segment the user's own regions of interest. The user will need a set of at least 10 TI MRI volumes, hand-segmented, ground truth labels and will need to supervise the training process. The quality of the MRI volumes and the labels will affect the success of the auto-segmentation and must be in correspondence. There is no limitation to how few or how many structures the software can be trained to segment.
Although LONI Brain Parser comes pre-trained with an ideal model, the software also has the ability to train the model to segment the user's own regions of interest. The user will need a set of at least 10 TI MRI volumes, hand-segmented, ground truth labels and will need to supervise the training process. The quality of the MRI volumes and the labels will affect the success of the auto-segmentation and must be in correspondence. There is no limitation to how few or how many structures the software can be trained to segment.
Features
- Awarded the "Best Automated Segmentation" Award at the 2007 International Medical Image Computing and Computer Assisted Intervention conference
- Learning based and highly adaptive
- Efficient computation, whole brain segmentation in 30 minutes or less
- Seamless integration of image appearance and context
Usage
Developer's Note
The following steps are required to go from raw data to fully segmented data:
Alternatively, you can run the LONI Brain Parser-Pipeline Workflow in our Try it now area. The workflow has been setup with the pre-processing and post-processing steps predefined for ease of use.
- Data must be in Analyze Image 16 bit short format and should have a reasonable intensity range from 0 to 5000
- Data must be aligned to the template image
- Skull stripping
- Registration
- Intensity normalization
- After you run LONI Brain Parser you will need to invert your registration to match the orientation of the original data
Alternatively, you can run the LONI Brain Parser-Pipeline Workflow in our Try it now area. The workflow has been setup with the pre-processing and post-processing steps predefined for ease of use.
System Requirements
OS: Linux 32 bit, Memory: 2 GB, Processor: 2.8MHz processor or higher
Installation
Windows
Download the Windows exe and double click to launch.
Linux
Download the Linux binary and double click to launch.
Via the LONI Pipeline Workflow
The Try it now area offers a test drive of the LONI Pipeline-Brain Parser Workflow. You can try out your data with all the processing steps set up for you. This will require Java 1.5 or higher. If you have the LONI Pipeline running locally on your machine you can download the .pipe file. You can hit "Play" which will connect you to our guest computer cluster. Otherwise, you can edit the "Connection" details and login to the main cluster if you have already gained access. If you would like to use our cluster but do not currently have access, you may request it on the LONI Pipeline website.
Download the Windows exe and double click to launch.
Linux
Download the Linux binary and double click to launch.
Via the LONI Pipeline Workflow
The Try it now area offers a test drive of the LONI Pipeline-Brain Parser Workflow. You can try out your data with all the processing steps set up for you. This will require Java 1.5 or higher. If you have the LONI Pipeline running locally on your machine you can download the .pipe file. You can hit "Play" which will connect you to our guest computer cluster. Otherwise, you can edit the "Connection" details and login to the main cluster if you have already gained access. If you would like to use our cluster but do not currently have access, you may request it on the LONI Pipeline website.
Purpose
LONI Brain Parser allows the user to quickly segment anatomical brain structures using automated delineation methods. The software can also be "trained" to locate areas of interest in the brain that it is not programmed to locate by default. Whereas segmentation by hand can take hours or even days, auto-segmentation only takes about half an hour. With this segmented data researchers can study the shape and morphometry of the structures to discover new patterns and associations in areas such as development and disease.
Online Support
Forum
Please submit your questions about LONI Brain Parser to the forum.
Documentation
Consult the software documentation for more detailed information not covered on this page.
Please submit your questions about LONI Brain Parser to the forum.
Documentation
Consult the software documentation for more detailed information not covered on this page.
You can follow any responses to this entry through the RSS 2.0 feed.
highest download
current month's download