Difference between revisions of "Cerebellum CNN"

From IACL
Jump to navigation Jump to search
(Correction.)
Line 11: Line 11:
 
| colspan="2" align="center" | '''ACAPULCO'''
 
| colspan="2" align="center" | '''ACAPULCO'''
 
|-
 
|-
| {{iacl|~shuo/data/acapulco-adult.tar.gz|Docker image for Adult Data}}
+
| {{iacl|~shuo/data/acapulco_022.tar.gz|Docker image CPU}}
| 1.2GB
+
| 1.8GB
 
|-
 
|-
| {{iacl|~shuo/data/acapulco-pediatric.tar.gz|Docker image for Pediatric Data}}
+
| {{iacl|~shuo/data/acapulco_022_gpu.tar.gz|Docker image GPU}}
| 1.2GB
+
| 2.5GB
 +
|-
 +
| {{iacl|~shuo/data/acapulco_022.sif|Singularity image CPU}}
 +
| 1.7GB
 +
|-
 +
| {{iacl|~shuo/data/acapulco_022_gpu.sif|Singularity image GPU}}
 +
| 2.4GB
 
|-
 
|-
 
|}
 
|}
Line 25: Line 31:
 
{{h3|Instructions}}
 
{{h3|Instructions}}
  
The [https://gitlab.com/shuohan/keras-unet-cerebellum/-/blob/master/README.md instructions] are available [https://gitlab.com/shuohan/keras-unet-cerebellum/-/blob/master/README.md here].
+
The instructions are available [https://gitlab.com/shuohan/keras-unet-cerebellum/-/blob/master/README.md here].
 +
 
 +
{{h3| Delineation protocols: region names and voxel values}}
 +
 
 +
* Adult training data:
 +
"Background":            0,
 +
"Corpus Medullare":      12,
 +
"Left I-III":            33,
 +
"Right I-III":            36,
 +
"Left IV":                43,
 +
"Rigt IV":                46,
 +
"Left V":                53,
 +
"Right V":                56,
 +
"Vermis VI":              60,
 +
"Left VI":                63,
 +
"Right VI":              66,
 +
"Vermis VII":            70,
 +
"Left Crus I":            73,
 +
"Left Crus II":          74,
 +
"Left VIIB":              75,
 +
"Right Crus I":          76,
 +
"Right Crus II":          77,
 +
"Right VIIB":            78,
 +
"Vermis VIII":            80,
 +
"Left VIIIA":            83,
 +
"Left VIIIB":            84,
 +
"Right VIIIA":            86,
 +
"Right VIIIB":            87,
 +
"Vermis IX":              90,
 +
"Left IX":                93,
 +
"Right IX":              96,
 +
"Vermis X":              100,
 +
"Left X":                103,
 +
"Right X":              106
 +
 
  
  
{{h3|Cerebellum labels}}
+
* Pediatric training data:
    "12": "Corpus_Medullare",
+
"Background":             0,
    "33": "Left_Lobules_I-III",
+
  "Right Lobules I-V":      3,
    "36": "Right_Lobules_I-III",
+
"Right Lobule VI":         4,
    "43": "Left_Lobule_IV",
+
"Right Crus I":           5,
    "46": "Right_Lobule_IV",
+
"Right Crus II/VIIB":     6,
    "53": "Left_Lobule_V",
+
"Right Lobule VIII":       7,
    "56": "Right_Lobule_V",
+
"Right Lobule IX":         8,
    "63": "Left_Lobule_VI",
+
"Right Lobule X":         9,
    "60": "Vermis_VI",
+
  "Left Lobules I-V":       10,
    "66": "Right_Lobule_VI",
+
  "Left Lobule VI":         11,
    "73": "Left_Lobule_VIIAf",
+
  "Left Crus I":           12,
    "76": "Right_Lobule_VIIAf",
+
  "Left Crus II/VIIB":     13,
    "74": "Left_Lobule_VIIAt",
+
  "Left Lobule VIII":       14,
    "70": "Vermis_VII",
+
  "Left Lobule IX":         15,
    "77": "Right_Lobule_VIIAt",
+
  "Left Lobule X":         16,
    "75": "Left_Lobule_VIIB",
+
  "Vermis I-V":             17,
    "78": "Right_Lobule_VIIB",
+
  "Vermis VI-VII":         18,
    "83": "Left_Lobule_VIIIA",
+
"Vermis VIII-X":         19,
    "80": "Vermis_VIII",
+
"Corpus Medullare":       20
    "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"
 

Revision as of 23:27, 27 January 2021

<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)


ACAPULCO
Docker image CPU 1.8GB
Docker image GPU 2.5GB
Singularity image CPU 1.7GB
Singularity image GPU 2.4GB


If you use it please cite the above paper. If you have any questions, please email Shuo Han at shan50 _AT_ jhu.edu.


Instructions

The instructions are available here.

Delineation protocols: region names and voxel values

  • Adult training data:
"Background":             0,
"Corpus Medullare":       12, 
"Left I-III":             33, 
"Right I-III":            36, 
"Left IV":                43, 
"Rigt IV":                46, 
"Left V":                 53, 
"Right V":                56, 
"Vermis VI":              60, 
"Left VI":                63, 
"Right VI":               66, 
"Vermis VII":             70, 
"Left Crus I":            73, 
"Left Crus II":           74, 
"Left VIIB":              75, 
"Right Crus I":           76, 
"Right Crus II":          77, 
"Right VIIB":             78, 
"Vermis VIII":            80, 
"Left VIIIA":             83, 
"Left VIIIB":             84, 
"Right VIIIA":            86, 
"Right VIIIB":            87, 
"Vermis IX":              90, 
"Left IX":                93, 
"Right IX":               96, 
"Vermis X":              100,
"Left X":                103,
"Right X":               106


  • Pediatric training data:
"Background":              0,
"Right Lobules I-V":       3,
"Right Lobule VI":         4,
"Right Crus I":            5,
"Right Crus II/VIIB":      6,
"Right Lobule VIII":       7,
"Right Lobule IX":         8,
"Right Lobule X":          9,
"Left Lobules I-V":       10,
"Left Lobule VI":         11,
"Left Crus I":            12,
"Left Crus II/VIIB":      13,
"Left Lobule VIII":       14,
"Left Lobule IX":         15,
"Left Lobule X":          16,
"Vermis I-V":             17,
"Vermis VI-VII":          18,
"Vermis VIII-X":          19,
"Corpus Medullare":       20