Difference between revisions of "Cerebellum CNN"

From IACL
Jump to navigation Jump to search
(Updated with the new publication.)
Line 6: Line 6:
 
{{iacl-pub| author=S. Han, A. Carass, Y. He, and J.L. Prince| title=Automatic Cerebellum Anatomical Parcellation using U-Net with Locally Constrained Optimization| jrnl=ni| number=218:116819| when=2020| doi=10.1016/j.neuroimage.2020.116819}}
 
{{iacl-pub| author=S. Han, A. Carass, Y. He, and J.L. Prince| title=Automatic Cerebellum Anatomical Parcellation using U-Net with Locally Constrained Optimization| jrnl=ni| number=218:116819| when=2020| doi=10.1016/j.neuroimage.2020.116819}}
  
−
It can be downloaded as a {{iacl|~shuo/data/cerebellum-parcellation_v2.simg|Singularity image}}. The download is 1.3GB. If you use it please cite the NeurooImage paper.
+
It can be downloaded as a {{iacl|~shuo/data/acapulco.tar.gz |Docker image}}. The download is ???GB. If you use it please cite the above paper.
 
If you have any questions, please email Shuo Han at <code>shan50@jhu.edu</code>.
 
If you have any questions, please email Shuo Han at <code>shan50@jhu.edu</code>.
  
 +
{{h3|Instructions}}
  
−
{{h3|What the Singularity image can do}}
+
The instructions are at [https://gitlab.com/shuohan/keras-unet-cerebellum/-/blob/master/README.md instructions].
−
The Singularity performs the following steps:
 
−
* [https://www.nitrc.org/projects/robex ROBEX] is used to estimate a brain mask. This mask is then smoothed to generate a brain weight image. The mask is not used for skull-stripping. It is only used for the bias field correction below.
 
−
* N4 from [http://stnava.github.io/ANTs/ ANTs] is used to perform the bias field correction. The bias field is estimated using the weight image calculated above.
 
−
* The image is rigidly registered to the [http://www.bic.mni.mcgill.ca/ServicesAtlases/ICBM152NLin2009 ICBM2009c] nonlinear symmetric template using the ANTs package.
 
−
* The cerebellum of an MNI-registered MPRAGE image is parcellated using the method described in "Shuo Han, et al., Cerebellum parcellation with convolutional neural networks, SPIE 2019 Medical Imaging Image Processing".
 
−
:* Removing the neck should improve the results, such as using <code>robustfov</code> from [https://fsl.fmrib.ox.ac.uk/fslcourse/lectures/practicals/intro2/index.html fsl], but it is not done in this Singularity image.
 
−
* The parcellation is transformed back to the original space using ANTs with the "MultiLabel" interpolation.
 
−
* Generate .png files of slices in the axial, coronal, and sagittal views for quality control.
 
−
 
 
−
 
 
−
{{h3|File structure}}
 
−
 
 
−
The processing will create subfolders '''<code>n4/</code>''', '''<code>mni/</code>''', '''<code>parc/</code>''', and '''<code>pics/</code>''' under the output folder. The final parcellation result is directly under the output folder.
 
−
* '''<code>*n4.nii.gz</code>''' is the bias field corrected image
 
−
* '''<code>*n4_mni.nii.gz</code>''' is the image in the MNI space
 
−
* '''<code>*n4_mni_seg.nii.gz</code>''' is the parcellation from the deep networks
 
−
* '''<code>*n4_mni_seg_post.nii.gz</code>''' is the post-processed result.
 
−
* '''<code>*n4_mni_seg_post_inverse.nii.gz</code>''' is <u>the final post-processed result in the original space</u>.
 
−
* The subfolder '''<code>pics/final/</code>''' contains the axial, coronal, and sagittal slices of the file '''<code>*n4_mni_seg_post_inverse.nii.gz</code>'''.
 
−
 
 
−
 
 
−
{{h3|Installation}}
 
−
* Install [https://www.sylabs.io/guides/2.6/user-guide/installation.html Singularity 2.6]
 
−
 
 
−
 
 
−
{{h3|Example Usage}}
 
−
* The Singularity image can only run on '''CPU''' although [https://www.tensorflow.org TensorFlow] and [https://keras.io Keras] are used, because the Singularity image only contains the CPU version of TensorFlow.
 
−
 
 
−
* Assume that the Singularity image is <code>~/cerebellum-parcellation.simg</code>, the image to parcellate is <code>image.nii.gz</code>, and the output folder is <code>~/output</code>
 
−
 
 
−
singularity run ~/cerebellum-parcellation.simg -i ~/image.nii.gz -o ~/output
 
−
 
 
−
* If the <code>image.nii.gz</code> is under <code>/path/to/image</code> which is not under your home directory
 
−
 
 
−
singularity run -B /path/to/image:/mnt ~/cerebellum-parcellation.simg -i /mnt/image.nii.gz -o /mnt/output
 
−
 
 
−
* Print help
 
−
singularity run ~/cerebellum-parcellation.simg -h
 
−
 
 
  
 
{{h3|Cerebellum labels}}
 
{{h3|Cerebellum labels}}

Revision as of 21:42, 16 September 2020

<meta name="title" content="ACAPULCO: Cerebellum Parcellation with Convolutional Neural Networks"/>

Cerebellum Parcellation with Convolutional Neural Networks

Automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization (ACAPULCO) is our current cerebellum parcellation method. The associated publication is:

  • S. Han, A. Carass, Y. He, and J.L. Prince, "Automatic Cerebellum Anatomical Parcellation using U-Net with Locally Constrained Optimization", NeuroImage, 218:116819, 2020. (doi)

It can be downloaded as a Docker image. The download is ???GB. If you use it please cite the above paper. If you have any questions, please email Shuo Han at shan50@jhu.edu.

Instructions

The instructions are at instructions.

Cerebellum labels

   "12":  "Corpus_Medullare",
   "33":  "Left_Lobules_I-III",
   "36":  "Right_Lobules_I-III",
   "43":  "Left_Lobule_IV",
   "46":  "Right_Lobule_IV",
   "53":  "Left_Lobule_V",
   "56":  "Right_Lobule_V",
   "63":  "Left_Lobule_VI",
   "60":  "Vermis_VI",
   "66":  "Right_Lobule_VI",
   "73":  "Left_Lobule_VIIAf",
   "76":  "Right_Lobule_VIIAf",
   "74":  "Left_Lobule_VIIAt",
   "70":  "Vermis_VII",
   "77":  "Right_Lobule_VIIAt",
   "75":  "Left_Lobule_VIIB",
   "78":  "Right_Lobule_VIIB",
   "83":  "Left_Lobule_VIIIA",
   "80":  "Vermis_VIII",
   "86":  "Right_Lobule_VIIIA",
   "84":  "Left_Lobule_VIIIB",
   "87":  "Right_Lobule_VIIIB",
   "93":  "Left_Lobule_IX",
   "90":  "Vermis_IX",
   "96":  "Right_Lobule_IX",
   "103": "Left_Lobule_X",
   "100": "Vermis_X",
   "106": "Right_Lobule_X"
Retrieved from "https://iacl.ece.jhu.edu/index.php?title=Cerebellum_CNN&oldid=17251"