multi-atlas-segmentation / Git / Diff of /README.md

Models:

SCallahan/

multi-atlas-segmentation

Downloads: 1

Diff of /README.md [a6edca] .. [d325d5]

Switch to unified view


# Multi Atlas Segmentation and Morphometric Analysis Toolkit (MASMAT)

 Originally designed for mouse brain MRI, but is applicable to any spicious (e.g. Non-human primate, or even human neuroimages)

Author: Da Ma (dma@wakehealth.edu; da_ma@sfu.ca; d.ma.11@ucl.ac.uk)

## Description

Automatic brain structural parcellation through registration-based segmentation-propagation and multi-atlas-based label-fusion
This bash scripts is created for `Multi-atlas based automatic brain structural parcellation`, mainly for mouse brain MRI.

This script achieve automatic brain MRI image segmentation with given [__mouse brain MRI atlases__](https://github.com/dancebean/mouse-brain-atlas) - which is a set of pairs of template images along with their manually labells. Sample atlases can be downloadable from the Github respsitory [here](https://github.com/dancebean/mouse-brain-atlas). For detailed description of the pipeline, please refer to the papers [[1]](http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0086576) [[2]](https://www.frontiersin.org/articles/10.3389/fnins.2019.00011). [Citation](#citation) of the two papers are listed at the bottom of this page.
The MASMAT tool has been extensively tested to segment mouse brain MRI. It should be also capable of handelling the multi-atlas-based parcellation/segmentation for other type of images, organs, or species (e.g. CT, heart, embryo, human, macaque, _etc._), providing appropriate atlases are givien.

...
  - `-a`: text file list the templates inside the atlas folder to be used (default:  `template_list.cfg` file within the atlas folder)
  - `-p`: configuration file to tune the parameters for the registration and label fusion algorithms
  - `-e`: specify to run locally (`local`) on on `cluster` . Specify `cluster` will submit parallel pbs jobs to cluster; specify `local` will run job sequentially on local machine. cluster is set by default

= Step 2. bias field correction
This is an important step before the parcellation. It is skipped in the demo as the images are already "bias-corrected" using the N4 algorithm
`mas_N4_batch`

- Step 3. __*brain structure parcellation*__

  `mas_parcellation_batch -T "target_dir" -t "target_list" -A "atlas_dir" -r "result_dir" -M "targetmask_dir" -M "dilate_mask_dir" -m "mask_suffix" -e "exe_mode"`
...
  - `-a`: text file list the templates inside the atlas folder to be used (default:  `template_list.cfg` file within the atlas folder)
  - `-p`: configuration file to tune the parameters for the registration and label fusion algorithms
  - `-a`: text file list the templates inside the atlas folder to be used (default:  `template_list.cfg` file within the atlas folder)
  - `-p`: configuration file to tune the parameters for the registration and label fusion algorithms




## List of functions

[Basic functions]
- `check_image_file`
...

## Funding
The works in this repositories received multiple funding from EPSRC, UCL School of Engineering, Alzheimer's Society Research Program (Alzheimer's Society of Canada), UCL Leonard Wolfson Experimental Neurology center, Medical Research Council (MRC), the NIHR Biomedical Research Unit (Dementia) at UCL and the National Institute for Health Research University College London Hospitals Biomedical Research center, the UK Regenerative Medicine Platform Safety Hub, and the Kings College London and UCL Comprehensive Cancer Imaging center CRUK & EPSRC in association with the MRC and DoH (England), UCL Faculty of Engineering funding scheme, Alzheimer Society Reseasrch Program from Alzheimer Society Canada, NSERC, CIHR, MSFHR Canada， Eli Lilly and Company, Wellcome Trust, the Francis Crick Institute, Cancer Research UK, and University of Melbourne McKenzie Fellowship.

	a/README.md		b/README.md
1	# Multi Atlas Segmentation and Morphometric Analysis Toolkit (MASMAT)	1	# Multi Atlas Segmentation and Morphometric Analysis Toolkit (MASMAT)
2		2
3	> Originally designed for mouse brain MRI, but is applicable to any spicious (e.g. Non-human primate, or even human neuroimages)	3	Originally designed for mouse brain MRI, but is applicable to any spicious (e.g. Non-human primate, or even human neuroimages)
4		4
5	Author: Da Ma (dma@wakehealth.edu; da_ma@sfu.ca; d.ma.11@ucl.ac.uk)	5	Author: Da Ma (dma@wakehealth.edu; da_ma@sfu.ca; d.ma.11@ucl.ac.uk)
6		6
7	## Description	7	## Description
8		8
9	> Automatic brain structural parcellation through registration-based segmentation-propagation and multi-atlas-based label-fusion	9	Automatic brain structural parcellation through registration-based segmentation-propagation and multi-atlas-based label-fusion
10	This bash scripts is created for `Multi-atlas based automatic brain structural parcellation`, mainly for mouse brain MRI.	10	This bash scripts is created for `Multi-atlas based automatic brain structural parcellation`, mainly for mouse brain MRI.
11		11
12	This script achieve automatic brain MRI image segmentation with given [__mouse brain MRI atlases__](https://github.com/dancebean/mouse-brain-atlas) - which is a set of pairs of template images along with their manually labells. Sample atlases can be downloadable from the Github respsitory [here](https://github.com/dancebean/mouse-brain-atlas). For detailed description of the pipeline, please refer to the papers [[1]](http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0086576) [[2]](https://www.frontiersin.org/articles/10.3389/fnins.2019.00011). [Citation](#citation) of the two papers are listed at the bottom of this page.	12	This script achieve automatic brain MRI image segmentation with given [__mouse brain MRI atlases__](https://github.com/dancebean/mouse-brain-atlas) - which is a set of pairs of template images along with their manually labells. Sample atlases can be downloadable from the Github respsitory [here](https://github.com/dancebean/mouse-brain-atlas). For detailed description of the pipeline, please refer to the papers [[1]](http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0086576) [[2]](https://www.frontiersin.org/articles/10.3389/fnins.2019.00011). [Citation](#citation) of the two papers are listed at the bottom of this page.
13	The MASMAT tool has been extensively tested to segment mouse brain MRI. It should be also capable of handelling the multi-atlas-based parcellation/segmentation for other type of images, organs, or species (e.g. CT, heart, embryo, human, macaque, _etc._), providing appropriate atlases are givien.	13	The MASMAT tool has been extensively tested to segment mouse brain MRI. It should be also capable of handelling the multi-atlas-based parcellation/segmentation for other type of images, organs, or species (e.g. CT, heart, embryo, human, macaque, _etc._), providing appropriate atlases are givien.
14		14
	...		...
114	- `-a`: text file list the templates inside the atlas folder to be used (default: `template_list.cfg` file within the atlas folder)	114	- `-a`: text file list the templates inside the atlas folder to be used (default: `template_list.cfg` file within the atlas folder)
115	- `-p`: configuration file to tune the parameters for the registration and label fusion algorithms	115	- `-p`: configuration file to tune the parameters for the registration and label fusion algorithms
116	- `-e`: specify to run locally (`local`) on on `cluster` . Specify `cluster` will submit parallel pbs jobs to cluster; specify `local` will run job sequentially on local machine. cluster is set by default	116	- `-e`: specify to run locally (`local`) on on `cluster` . Specify `cluster` will submit parallel pbs jobs to cluster; specify `local` will run job sequentially on local machine. cluster is set by default
117		117
118	= Step 2. bias field correction	118	= Step 2. bias field correction
119	> This is an important step before the parcellation. It is skipped in the demo as the images are already "bias-corrected" using the N4 algorithm	119	This is an important step before the parcellation. It is skipped in the demo as the images are already "bias-corrected" using the N4 algorithm
120	`mas_N4_batch`	120	`mas_N4_batch`
121		121
122	- Step 3. __brain structure parcellation__	122	- Step 3. __brain structure parcellation__
123		123
124	`mas_parcellation_batch -T "target_dir" -t "target_list" -A "atlas_dir" -r "result_dir" -M "targetmask_dir" -M "dilate_mask_dir" -m "mask_suffix" -e "exe_mode"`	124	`mas_parcellation_batch -T "target_dir" -t "target_list" -A "atlas_dir" -r "result_dir" -M "targetmask_dir" -M "dilate_mask_dir" -m "mask_suffix" -e "exe_mode"`
	...		...
134	- `-a`: text file list the templates inside the atlas folder to be used (default: `template_list.cfg` file within the atlas folder)	134	- `-a`: text file list the templates inside the atlas folder to be used (default: `template_list.cfg` file within the atlas folder)
135	- `-p`: configuration file to tune the parameters for the registration and label fusion algorithms	135	- `-p`: configuration file to tune the parameters for the registration and label fusion algorithms
136	- `-a`: text file list the templates inside the atlas folder to be used (default: `template_list.cfg` file within the atlas folder)	136	- `-a`: text file list the templates inside the atlas folder to be used (default: `template_list.cfg` file within the atlas folder)
137	- `-p`: configuration file to tune the parameters for the registration and label fusion algorithms	137	- `-p`: configuration file to tune the parameters for the registration and label fusion algorithms
138		138
139	### Sample image of the pipeline output
140	[![Sample output](docs/quickcheckdemo.png) "Click for sample quality control image of the parcellation output (generated using mas_quickcheck)."](docs/quickcheckdemo.png) The similar color between the olfactory bulb and the cortex is due to the limited colormap of `jet`.
141		139
142	## List of functions	140	## List of functions
143		141
144	[Basic functions]	142	[Basic functions]
145	- `check_image_file`	143	- `check_image_file`
	...		...
229		227
230	## Funding	228	## Funding
231	The works in this repositories received multiple funding from EPSRC, UCL School of Engineering, Alzheimer's Society Research Program (Alzheimer's Society of Canada), UCL Leonard Wolfson Experimental Neurology center, Medical Research Council (MRC), the NIHR Biomedical Research Unit (Dementia) at UCL and the National Institute for Health Research University College London Hospitals Biomedical Research center, the UK Regenerative Medicine Platform Safety Hub, and the Kings College London and UCL Comprehensive Cancer Imaging center CRUK & EPSRC in association with the MRC and DoH (England), UCL Faculty of Engineering funding scheme, Alzheimer Society Reseasrch Program from Alzheimer Society Canada, NSERC, CIHR, MSFHR Canada， Eli Lilly and Company, Wellcome Trust, the Francis Crick Institute, Cancer Research UK, and University of Melbourne McKenzie Fellowship.	229	The works in this repositories received multiple funding from EPSRC, UCL School of Engineering, Alzheimer's Society Research Program (Alzheimer's Society of Canada), UCL Leonard Wolfson Experimental Neurology center, Medical Research Council (MRC), the NIHR Biomedical Research Unit (Dementia) at UCL and the National Institute for Health Research University College London Hospitals Biomedical Research center, the UK Regenerative Medicine Platform Safety Hub, and the Kings College London and UCL Comprehensive Cancer Imaging center CRUK & EPSRC in association with the MRC and DoH (England), UCL Faculty of Engineering funding scheme, Alzheimer Society Reseasrch Program from Alzheimer Society Canada, NSERC, CIHR, MSFHR Canada， Eli Lilly and Company, Wellcome Trust, the Francis Crick Institute, Cancer Research UK, and University of Melbourne McKenzie Fellowship.