Levelset Segmentation 
In [1]:
%matplotlib inline
import matplotlib.pyplot as plt
import SimpleITK as sitk
from myshow import myshow, myshow3d
# Download data to work on
%run update_path_to_download_script
from downloaddata import fetch_data as fdata
In [2]:
img_T1 = sitk.ReadImage(fdata("nac-hncma-atlas2013-Slicer4Version/Data/A1_grayT1.nrrd"))
img_T2 = sitk.ReadImage(fdata("nac-hncma-atlas2013-Slicer4Version/Data/A1_grayT2.nrrd"))
img_T1_255 = sitk.Cast(sitk.RescaleIntensity(img_T1), sitk.sitkUInt8)
img_T1_255 = sitk.Cast(sitk.RescaleIntensity(img_T1), sitk.sitkUInt8)
Fetching nac-hncma-atlas2013-Slicer4Version/Data/A1_grayT1.nrrd
Fetching nac-hncma-atlas2013-Slicer4Version/Data/A1_grayT2.nrrd
In [3]:
sitk.Show(img_T1, title="T1")
In [4]:
idx = (106, 116, 141)
pt = img_T1.TransformIndexToPhysicalPoint(idx)
In [5]:
seg = sitk.Image(img_T1.GetSize(), sitk.sitkUInt8)
seg.CopyInformation(img_T1)
seg[idx] = 1
seg = sitk.BinaryDilate(seg, [3] * 3)
myshow3d(
sitk.LabelOverlay(img_T1_255, seg),
zslices=range(idx[2] - 3, idx[2] + 4, 3),
dpi=30,
title="Initial Seed",
)
In [6]:
stats = sitk.LabelStatisticsImageFilter()
stats.Execute(img_T1, seg)
print(stats)
itk::simple::LabelStatisticsImageFilter
UseHistograms: 1
Labels: [ 1, 0 ]
Debug: 0
NumberOfThreads: 16
NumberOfWorkUnits: 0
Commands: (none)
ProgressMeasurement: 0
ActiveProcess:
LabelStatisticsImageFilter (0x7f9b48a2a640)
RTTI typeinfo: itk::LabelStatisticsImageFilter<itk::Image<float, 3u>, itk::Image<unsigned char, 3u> >
Reference Count: 1
Modified Time: 4810
Debug: Off
Object Name:
Observers:
DeleteEvent(FunctionCommand)
Inputs:
LabelInput: (0x7f9be98fa0e0) *
Primary: (0x7f9b48861ce0) *
Indexed Inputs:
0: Primary (0x7f9b48861ce0)
Required Input Names: LabelInput, Primary
NumberOfRequiredInputs: 1
Outputs:
Primary: (0x0)
Indexed Outputs:
0: Primary (0x0)
NumberOfRequiredOutputs: 0
Number Of Work Units: 64
ReleaseDataFlag: Off
ReleaseDataBeforeUpdateFlag: On
AbortGenerateData: Off
Progress: 1
Multithreader:
RTTI typeinfo: itk::PoolMultiThreader
Reference Count: 1
Modified Time: 4801
Debug: Off
Object Name:
Observers:
none
Number of Work Units: 64
Number of Threads: 16
Global Maximum Number Of Threads: 128
Global Default Number Of Threads: 16
Global Default Threader Type: itk::MultiThreaderBaseEnums::Threader::Pool
SingleMethod: 0
SingleData: 0x0
Current Request Number: -1
NumberOfStreamDivisions: 1
RegionSplitter: ImageRegionSplitterSlowDimension (0x6000019aef00)
RTTI typeinfo: itk::ImageRegionSplitterSlowDimension
Reference Count: 2
Modified Time: 4803
Debug: Off
Object Name:
Observers:
none
CoordinateTolerance: 1e-06
DirectionTolerance: 1e-06
LabelStatistics:
{: Count: 179
Minimum: 323.044
Maximum: 561.325
Mean: 476.567
Sum: 85305.5
SumOfSquares: 4.14695e+07
Sigma: 67.6929
Variance: 4582.33
BoundingBox: (103, 109, 113, 119, 138, 144)
Histogram: Histogram (0x7f9b4fc04390)
RTTI typeinfo: itk::Statistics::Histogram<double, itk::Statistics::DenseFrequencyContainer2>
Reference Count: 1
Modified Time: 5012
Debug: Off
Object Name:
Observers:
none
Source: (none)
Source output name: (none)
Release Data: Off
Data Released: False
Global Release Data: Off
PipelineMTime: 0
UpdateMTime: 0
RealTimeStamp: 0 seconds
Length of measurement vectors in the sample: 1
Size: [256]
OffsetTable:
[0]: 1
[1]: 256
FrequencyContainer:
DenseFrequencyContainer2 (0x600002fa4140)
RTTI typeinfo: itk::Statistics::DenseFrequencyContainer2
Reference Count: 1
Modified Time: 5010
Debug: Off
Object Name:
Observers:
none
NumberOfInstances: 256
Min:
[0]: -135.632
[1]: -126.774
[2]: -117.917
[3]: -109.059
[4]: -100.202
[5]: -91.3446
[6]: -82.4872
[7]: -73.6297
[8]: -64.7723
[9]: -55.9149
[10]: -47.0575
[11]: -38.2001
[12]: -29.3427
[13]: -20.4853
[14]: -11.6279
[15]: -2.77046
[16]: 6.08694
[17]: 14.9444
[18]: 23.8018
[19]: 32.6592
[20]: 41.5166
[21]: 50.374
[22]: 59.2314
[23]: 68.0888
[24]: 76.9462
[25]: 85.8036
[26]: 94.661
[27]: 103.518
[28]: 112.376
[29]: 121.233
[30]: 130.091
[31]: 138.948
[32]: 147.806
[33]: 156.663
[34]: 165.52
[35]: 174.378
[36]: 183.235
[37]: 192.093
[38]: 200.95
[39]: 209.807
[40]: 218.665
[41]: 227.522
[42]: 236.38
[43]: 245.237
[44]: 254.094
[45]: 262.952
[46]: 271.809
[47]: 280.667
[48]: 289.524
[49]: 298.382
[50]: 307.239
[51]: 316.096
[52]: 324.954
[53]: 333.811
[54]: 342.669
[55]: 351.526
[56]: 360.383
[57]: 369.241
[58]: 378.098
[59]: 386.956
[60]: 395.813
[61]: 404.67
[62]: 413.528
[63]: 422.385
[64]: 431.243
[65]: 440.1
[66]: 448.957
[67]: 457.815
[68]: 466.672
[69]: 475.53
[70]: 484.387
[71]: 493.245
[72]: 502.102
[73]: 510.959
[74]: 519.817
[75]: 528.674
[76]: 537.532
[77]: 546.389
[78]: 555.246
[79]: 564.104
[80]: 572.961
[81]: 581.819
[82]: 590.676
[83]: 599.533
[84]: 608.391
[85]: 617.248
[86]: 626.106
[87]: 634.963
[88]: 643.821
[89]: 652.678
[90]: 661.535
[91]: 670.393
[92]: 679.25
[93]: 688.108
[94]: 696.965
[95]: 705.822
[96]: 714.68
[97]: 723.537
[98]: 732.395
[99]: 741.252
[100]: 750.109
[101]: 758.967
[102]: 767.824
[103]: 776.682
[104]: 785.539
[105]: 794.396
[106]: 803.254
[107]: 812.111
[108]: 820.969
[109]: 829.826
[110]: 838.684
[111]: 847.541
[112]: 856.398
[113]: 865.256
[114]: 874.113
[115]: 882.971
[116]: 891.828
[117]: 900.685
[118]: 909.543
[119]: 918.4
[120]: 927.258
[121]: 936.115
[122]: 944.973
[123]: 953.83
[124]: 962.687
[125]: 971.545
[126]: 980.402
[127]: 989.259
[128]: 998.117
[129]: 1006.97
[130]: 1015.83
[131]: 1024.69
[132]: 1033.55
[133]: 1042.4
[134]: 1051.26
[135]: 1060.12
[136]: 1068.98
[137]: 1077.83
[138]: 1086.69
[139]: 1095.55
[140]: 1104.41
[141]: 1113.26
[142]: 1122.12
[143]: 1130.98
[144]: 1139.84
[145]: 1148.69
[146]: 1157.55
[147]: 1166.41
[148]: 1175.27
[149]: 1184.12
[150]: 1192.98
[151]: 1201.84
[152]: 1210.69
[153]: 1219.55
[154]: 1228.41
[155]: 1237.27
[156]: 1246.12
[157]: 1254.98
[158]: 1263.84
[159]: 1272.7
[160]: 1281.55
[161]: 1290.41
[162]: 1299.27
[163]: 1308.13
[164]: 1316.98
[165]: 1325.84
[166]: 1334.7
[167]: 1343.56
[168]: 1352.41
[169]: 1361.27
[170]: 1370.13
[171]: 1378.99
[172]: 1387.84
[173]: 1396.7
[174]: 1405.56
[175]: 1414.42
[176]: 1423.27
[177]: 1432.13
[178]: 1440.99
[179]: 1449.84
[180]: 1458.7
[181]: 1467.56
[182]: 1476.42
[183]: 1485.27
[184]: 1494.13
[185]: 1502.99
[186]: 1511.85
[187]: 1520.7
[188]: 1529.56
[189]: 1538.42
[190]: 1547.28
[191]: 1556.13
[192]: 1564.99
[193]: 1573.85
[194]: 1582.71
[195]: 1591.56
[196]: 1600.42
[197]: 1609.28
[198]: 1618.14
[199]: 1626.99
[200]: 1635.85
[201]: 1644.71
[202]: 1653.57
[203]: 1662.42
[204]: 1671.28
[205]: 1680.14
[206]: 1688.99
[207]: 1697.85
[208]: 1706.71
[209]: 1715.57
[210]: 1724.42
[211]: 1733.28
[212]: 1742.14
[213]: 1751
[214]: 1759.85
[215]: 1768.71
[216]: 1777.57
[217]: 1786.43
[218]: 1795.28
[219]: 1804.14
[220]: 1813
[221]: 1821.86
[222]: 1830.71
[223]: 1839.57
[224]: 1848.43
[225]: 1857.29
[226]: 1866.14
[227]: 1875
[228]: 1883.86
[229]: 1892.72
[230]: 1901.57
[231]: 1910.43
[232]: 1919.29
[233]: 1928.14
[234]: 1937
[235]: 1945.86
[236]: 1954.72
[237]: 1963.57
[238]: 1972.43
[239]: 1981.29
[240]: 1990.15
[241]: 1999
[242]: 2007.86
[243]: 2016.72
[244]: 2025.58
[245]: 2034.43
[246]: 2043.29
[247]: 2052.15
[248]: 2061.01
[249]: 2069.86
[250]: 2078.72
[251]: 2087.58
[252]: 2096.44
[253]: 2105.29
[254]: 2114.15
[255]: 2123.01
Max:
[0]: -126.774
[1]: -117.917
[2]: -109.059
[3]: -100.202
[4]: -91.3446
[5]: -82.4872
[6]: -73.6297
[7]: -64.7723
[8]: -55.9149
[9]: -47.0575
[10]: -38.2001
[11]: -29.3427
[12]: -20.4853
[13]: -11.6279
[14]: -2.77046
[15]: 6.08694
[16]: 14.9444
[17]: 23.8018
[18]: 32.6592
[19]: 41.5166
[20]: 50.374
[21]: 59.2314
[22]: 68.0888
[23]: 76.9462
[24]: 85.8036
[25]: 94.661
[26]: 103.518
[27]: 112.376
[28]: 121.233
[29]: 130.091
[30]: 138.948
[31]: 147.806
[32]: 156.663
[33]: 165.52
[34]: 174.378
[35]: 183.235
[36]: 192.093
[37]: 200.95
[38]: 209.807
[39]: 218.665
[40]: 227.522
[41]: 236.38
[42]: 245.237
[43]: 254.094
[44]: 262.952
[45]: 271.809
[46]: 280.667
[47]: 289.524
[48]: 298.382
[49]: 307.239
[50]: 316.096
[51]: 324.954
[52]: 333.811
[53]: 342.669
[54]: 351.526
[55]: 360.383
[56]: 369.241
[57]: 378.098
[58]: 386.956
[59]: 395.813
[60]: 404.67
[61]: 413.528
[62]: 422.385
[63]: 431.243
[64]: 440.1
[65]: 448.957
[66]: 457.815
[67]: 466.672
[68]: 475.53
[69]: 484.387
[70]: 493.245
[71]: 502.102
[72]: 510.959
[73]: 519.817
[74]: 528.674
[75]: 537.532
[76]: 546.389
[77]: 555.246
[78]: 564.104
[79]: 572.961
[80]: 581.819
[81]: 590.676
[82]: 599.533
[83]: 608.391
[84]: 617.248
[85]: 626.106
[86]: 634.963
[87]: 643.821
[88]: 652.678
[89]: 661.535
[90]: 670.393
[91]: 679.25
[92]: 688.108
[93]: 696.965
[94]: 705.822
[95]: 714.68
[96]: 723.537
[97]: 732.395
[98]: 741.252
[99]: 750.109
[100]: 758.967
[101]: 767.824
[102]: 776.682
[103]: 785.539
[104]: 794.396
[105]: 803.254
[106]: 812.111
[107]: 820.969
[108]: 829.826
[109]: 838.684
[110]: 847.541
[111]: 856.398
[112]: 865.256
[113]: 874.113
[114]: 882.971
[115]: 891.828
[116]: 900.685
[117]: 909.543
[118]: 918.4
[119]: 927.258
[120]: 936.115
[121]: 944.973
[122]: 953.83
[123]: 962.687
[124]: 971.545
[125]: 980.402
[126]: 989.259
[127]: 998.117
[128]: 1006.97
[129]: 1015.83
[130]: 1024.69
[131]: 1033.55
[132]: 1042.4
[133]: 1051.26
[134]: 1060.12
[135]: 1068.98
[136]: 1077.83
[137]: 1086.69
[138]: 1095.55
[139]: 1104.41
[140]: 1113.26
[141]: 1122.12
[142]: 1130.98
[143]: 1139.84
[144]: 1148.69
[145]: 1157.55
[146]: 1166.41
[147]: 1175.27
[148]: 1184.12
[149]: 1192.98
[150]: 1201.84
[151]: 1210.69
[152]: 1219.55
[153]: 1228.41
[154]: 1237.27
[155]: 1246.12
[156]: 1254.98
[157]: 1263.84
[158]: 1272.7
[159]: 1281.55
[160]: 1290.41
[161]: 1299.27
[162]: 1308.13
[163]: 1316.98
[164]: 1325.84
[165]: 1334.7
[166]: 1343.56
[167]: 1352.41
[168]: 1361.27
[169]: 1370.13
[170]: 1378.99
[171]: 1387.84
[172]: 1396.7
[173]: 1405.56
[174]: 1414.42
[175]: 1423.27
[176]: 1432.13
[177]: 1440.99
[178]: 1449.84
[179]: 1458.7
[180]: 1467.56
[181]: 1476.42
[182]: 1485.27
[183]: 1494.13
[184]: 1502.99
[185]: 1511.85
[186]: 1520.7
[187]: 1529.56
[188]: 1538.42
[189]: 1547.28
[190]: 1556.13
[191]: 1564.99
[192]: 1573.85
[193]: 1582.71
[194]: 1591.56
[195]: 1600.42
[196]: 1609.28
[197]: 1618.14
[198]: 1626.99
[199]: 1635.85
[200]: 1644.71
[201]: 1653.57
[202]: 1662.42
[203]: 1671.28
[204]: 1680.14
[205]: 1688.99
[206]: 1697.85
[207]: 1706.71
[208]: 1715.57
[209]: 1724.42
[210]: 1733.28
[211]: 1742.14
[212]: 1751
[213]: 1759.85
[214]: 1768.71
[215]: 1777.57
[216]: 1786.43
[217]: 1795.28
[218]: 1804.14
[219]: 1813
[220]: 1821.86
[221]: 1830.71
[222]: 1839.57
[223]: 1848.43
[224]: 1857.29
[225]: 1866.14
[226]: 1875
[227]: 1883.86
[228]: 1892.72
[229]: 1901.57
[230]: 1910.43
[231]: 1919.29
[232]: 1928.14
[233]: 1937
[234]: 1945.86
[235]: 1954.72
[236]: 1963.57
[237]: 1972.43
[238]: 1981.29
[239]: 1990.15
[240]: 1999
[241]: 2007.86
[242]: 2016.72
[243]: 2025.58
[244]: 2034.43
[245]: 2043.29
[246]: 2052.15
[247]: 2061.01
[248]: 2069.86
[249]: 2078.72
[250]: 2087.58
[251]: 2096.44
[252]: 2105.29
[253]: 2114.15
[254]: 2123.01
[255]: 2131.87
TempMeasurementVector: [0]
TempIndex: [0]
ClipBinsAtEnds: On
}
{ : Count: 19169101
Minimum: -135.632
Maximum: 2131.87
Mean: 182.056
Sum: 3.48986e+09
SumOfSquares: 1.54579e+12
Sigma: 217.934
Variance: 47495.3
BoundingBox: (0, 287, 0, 319, 0, 207)
Histogram: Histogram (0x7f9b89104320)
RTTI typeinfo: itk::Statistics::Histogram<double, itk::Statistics::DenseFrequencyContainer2>
Reference Count: 1
Modified Time: 5064
Debug: Off
Object Name:
Observers:
none
Source: (none)
Source output name: (none)
Release Data: Off
Data Released: False
Global Release Data: Off
PipelineMTime: 0
UpdateMTime: 0
RealTimeStamp: 0 seconds
Length of measurement vectors in the sample: 1
Size: [256]
OffsetTable:
[0]: 1
[1]: 256
FrequencyContainer:
DenseFrequencyContainer2 (0x600002fa8140)
RTTI typeinfo: itk::Statistics::DenseFrequencyContainer2
Reference Count: 1
Modified Time: 5062
Debug: Off
Object Name:
Observers:
none
NumberOfInstances: 256
Min:
[0]: -135.632
[1]: -126.774
[2]: -117.917
[3]: -109.059
[4]: -100.202
[5]: -91.3446
[6]: -82.4872
[7]: -73.6297
[8]: -64.7723
[9]: -55.9149
[10]: -47.0575
[11]: -38.2001
[12]: -29.3427
[13]: -20.4853
[14]: -11.6279
[15]: -2.77046
[16]: 6.08694
[17]: 14.9444
[18]: 23.8018
[19]: 32.6592
[20]: 41.5166
[21]: 50.374
[22]: 59.2314
[23]: 68.0888
[24]: 76.9462
[25]: 85.8036
[26]: 94.661
[27]: 103.518
[28]: 112.376
[29]: 121.233
[30]: 130.091
[31]: 138.948
[32]: 147.806
[33]: 156.663
[34]: 165.52
[35]: 174.378
[36]: 183.235
[37]: 192.093
[38]: 200.95
[39]: 209.807
[40]: 218.665
[41]: 227.522
[42]: 236.38
[43]: 245.237
[44]: 254.094
[45]: 262.952
[46]: 271.809
[47]: 280.667
[48]: 289.524
[49]: 298.382
[50]: 307.239
[51]: 316.096
[52]: 324.954
[53]: 333.811
[54]: 342.669
[55]: 351.526
[56]: 360.383
[57]: 369.241
[58]: 378.098
[59]: 386.956
[60]: 395.813
[61]: 404.67
[62]: 413.528
[63]: 422.385
[64]: 431.243
[65]: 440.1
[66]: 448.957
[67]: 457.815
[68]: 466.672
[69]: 475.53
[70]: 484.387
[71]: 493.245
[72]: 502.102
[73]: 510.959
[74]: 519.817
[75]: 528.674
[76]: 537.532
[77]: 546.389
[78]: 555.246
[79]: 564.104
[80]: 572.961
[81]: 581.819
[82]: 590.676
[83]: 599.533
[84]: 608.391
[85]: 617.248
[86]: 626.106
[87]: 634.963
[88]: 643.821
[89]: 652.678
[90]: 661.535
[91]: 670.393
[92]: 679.25
[93]: 688.108
[94]: 696.965
[95]: 705.822
[96]: 714.68
[97]: 723.537
[98]: 732.395
[99]: 741.252
[100]: 750.109
[101]: 758.967
[102]: 767.824
[103]: 776.682
[104]: 785.539
[105]: 794.396
[106]: 803.254
[107]: 812.111
[108]: 820.969
[109]: 829.826
[110]: 838.684
[111]: 847.541
[112]: 856.398
[113]: 865.256
[114]: 874.113
[115]: 882.971
[116]: 891.828
[117]: 900.685
[118]: 909.543
[119]: 918.4
[120]: 927.258
[121]: 936.115
[122]: 944.973
[123]: 953.83
[124]: 962.687
[125]: 971.545
[126]: 980.402
[127]: 989.259
[128]: 998.117
[129]: 1006.97
[130]: 1015.83
[131]: 1024.69
[132]: 1033.55
[133]: 1042.4
[134]: 1051.26
[135]: 1060.12
[136]: 1068.98
[137]: 1077.83
[138]: 1086.69
[139]: 1095.55
[140]: 1104.41
[141]: 1113.26
[142]: 1122.12
[143]: 1130.98
[144]: 1139.84
[145]: 1148.69
[146]: 1157.55
[147]: 1166.41
[148]: 1175.27
[149]: 1184.12
[150]: 1192.98
[151]: 1201.84
[152]: 1210.69
[153]: 1219.55
[154]: 1228.41
[155]: 1237.27
[156]: 1246.12
[157]: 1254.98
[158]: 1263.84
[159]: 1272.7
[160]: 1281.55
[161]: 1290.41
[162]: 1299.27
[163]: 1308.13
[164]: 1316.98
[165]: 1325.84
[166]: 1334.7
[167]: 1343.56
[168]: 1352.41
[169]: 1361.27
[170]: 1370.13
[171]: 1378.99
[172]: 1387.84
[173]: 1396.7
[174]: 1405.56
[175]: 1414.42
[176]: 1423.27
[177]: 1432.13
[178]: 1440.99
[179]: 1449.84
[180]: 1458.7
[181]: 1467.56
[182]: 1476.42
[183]: 1485.27
[184]: 1494.13
[185]: 1502.99
[186]: 1511.85
[187]: 1520.7
[188]: 1529.56
[189]: 1538.42
[190]: 1547.28
[191]: 1556.13
[192]: 1564.99
[193]: 1573.85
[194]: 1582.71
[195]: 1591.56
[196]: 1600.42
[197]: 1609.28
[198]: 1618.14
[199]: 1626.99
[200]: 1635.85
[201]: 1644.71
[202]: 1653.57
[203]: 1662.42
[204]: 1671.28
[205]: 1680.14
[206]: 1688.99
[207]: 1697.85
[208]: 1706.71
[209]: 1715.57
[210]: 1724.42
[211]: 1733.28
[212]: 1742.14
[213]: 1751
[214]: 1759.85
[215]: 1768.71
[216]: 1777.57
[217]: 1786.43
[218]: 1795.28
[219]: 1804.14
[220]: 1813
[221]: 1821.86
[222]: 1830.71
[223]: 1839.57
[224]: 1848.43
[225]: 1857.29
[226]: 1866.14
[227]: 1875
[228]: 1883.86
[229]: 1892.72
[230]: 1901.57
[231]: 1910.43
[232]: 1919.29
[233]: 1928.14
[234]: 1937
[235]: 1945.86
[236]: 1954.72
[237]: 1963.57
[238]: 1972.43
[239]: 1981.29
[240]: 1990.15
[241]: 1999
[242]: 2007.86
[243]: 2016.72
[244]: 2025.58
[245]: 2034.43
[246]: 2043.29
[247]: 2052.15
[248]: 2061.01
[249]: 2069.86
[250]: 2078.72
[251]: 2087.58
[252]: 2096.44
[253]: 2105.29
[254]: 2114.15
[255]: 2123.01
Max:
[0]: -126.774
[1]: -117.917
[2]: -109.059
[3]: -100.202
[4]: -91.3446
[5]: -82.4872
[6]: -73.6297
[7]: -64.7723
[8]: -55.9149
[9]: -47.0575
[10]: -38.2001
[11]: -29.3427
[12]: -20.4853
[13]: -11.6279
[14]: -2.77046
[15]: 6.08694
[16]: 14.9444
[17]: 23.8018
[18]: 32.6592
[19]: 41.5166
[20]: 50.374
[21]: 59.2314
[22]: 68.0888
[23]: 76.9462
[24]: 85.8036
[25]: 94.661
[26]: 103.518
[27]: 112.376
[28]: 121.233
[29]: 130.091
[30]: 138.948
[31]: 147.806
[32]: 156.663
[33]: 165.52
[34]: 174.378
[35]: 183.235
[36]: 192.093
[37]: 200.95
[38]: 209.807
[39]: 218.665
[40]: 227.522
[41]: 236.38
[42]: 245.237
[43]: 254.094
[44]: 262.952
[45]: 271.809
[46]: 280.667
[47]: 289.524
[48]: 298.382
[49]: 307.239
[50]: 316.096
[51]: 324.954
[52]: 333.811
[53]: 342.669
[54]: 351.526
[55]: 360.383
[56]: 369.241
[57]: 378.098
[58]: 386.956
[59]: 395.813
[60]: 404.67
[61]: 413.528
[62]: 422.385
[63]: 431.243
[64]: 440.1
[65]: 448.957
[66]: 457.815
[67]: 466.672
[68]: 475.53
[69]: 484.387
[70]: 493.245
[71]: 502.102
[72]: 510.959
[73]: 519.817
[74]: 528.674
[75]: 537.532
[76]: 546.389
[77]: 555.246
[78]: 564.104
[79]: 572.961
[80]: 581.819
[81]: 590.676
[82]: 599.533
[83]: 608.391
[84]: 617.248
[85]: 626.106
[86]: 634.963
[87]: 643.821
[88]: 652.678
[89]: 661.535
[90]: 670.393
[91]: 679.25
[92]: 688.108
[93]: 696.965
[94]: 705.822
[95]: 714.68
[96]: 723.537
[97]: 732.395
[98]: 741.252
[99]: 750.109
[100]: 758.967
[101]: 767.824
[102]: 776.682
[103]: 785.539
[104]: 794.396
[105]: 803.254
[106]: 812.111
[107]: 820.969
[108]: 829.826
[109]: 838.684
[110]: 847.541
[111]: 856.398
[112]: 865.256
[113]: 874.113
[114]: 882.971
[115]: 891.828
[116]: 900.685
[117]: 909.543
[118]: 918.4
[119]: 927.258
[120]: 936.115
[121]: 944.973
[122]: 953.83
[123]: 962.687
[124]: 971.545
[125]: 980.402
[126]: 989.259
[127]: 998.117
[128]: 1006.97
[129]: 1015.83
[130]: 1024.69
[131]: 1033.55
[132]: 1042.4
[133]: 1051.26
[134]: 1060.12
[135]: 1068.98
[136]: 1077.83
[137]: 1086.69
[138]: 1095.55
[139]: 1104.41
[140]: 1113.26
[141]: 1122.12
[142]: 1130.98
[143]: 1139.84
[144]: 1148.69
[145]: 1157.55
[146]: 1166.41
[147]: 1175.27
[148]: 1184.12
[149]: 1192.98
[150]: 1201.84
[151]: 1210.69
[152]: 1219.55
[153]: 1228.41
[154]: 1237.27
[155]: 1246.12
[156]: 1254.98
[157]: 1263.84
[158]: 1272.7
[159]: 1281.55
[160]: 1290.41
[161]: 1299.27
[162]: 1308.13
[163]: 1316.98
[164]: 1325.84
[165]: 1334.7
[166]: 1343.56
[167]: 1352.41
[168]: 1361.27
[169]: 1370.13
[170]: 1378.99
[171]: 1387.84
[172]: 1396.7
[173]: 1405.56
[174]: 1414.42
[175]: 1423.27
[176]: 1432.13
[177]: 1440.99
[178]: 1449.84
[179]: 1458.7
[180]: 1467.56
[181]: 1476.42
[182]: 1485.27
[183]: 1494.13
[184]: 1502.99
[185]: 1511.85
[186]: 1520.7
[187]: 1529.56
[188]: 1538.42
[189]: 1547.28
[190]: 1556.13
[191]: 1564.99
[192]: 1573.85
[193]: 1582.71
[194]: 1591.56
[195]: 1600.42
[196]: 1609.28
[197]: 1618.14
[198]: 1626.99
[199]: 1635.85
[200]: 1644.71
[201]: 1653.57
[202]: 1662.42
[203]: 1671.28
[204]: 1680.14
[205]: 1688.99
[206]: 1697.85
[207]: 1706.71
[208]: 1715.57
[209]: 1724.42
[210]: 1733.28
[211]: 1742.14
[212]: 1751
[213]: 1759.85
[214]: 1768.71
[215]: 1777.57
[216]: 1786.43
[217]: 1795.28
[218]: 1804.14
[219]: 1813
[220]: 1821.86
[221]: 1830.71
[222]: 1839.57
[223]: 1848.43
[224]: 1857.29
[225]: 1866.14
[226]: 1875
[227]: 1883.86
[228]: 1892.72
[229]: 1901.57
[230]: 1910.43
[231]: 1919.29
[232]: 1928.14
[233]: 1937
[234]: 1945.86
[235]: 1954.72
[236]: 1963.57
[237]: 1972.43
[238]: 1981.29
[239]: 1990.15
[240]: 1999
[241]: 2007.86
[242]: 2016.72
[243]: 2025.58
[244]: 2034.43
[245]: 2043.29
[246]: 2052.15
[247]: 2061.01
[248]: 2069.86
[249]: 2078.72
[250]: 2087.58
[251]: 2096.44
[252]: 2105.29
[253]: 2114.15
[254]: 2123.01
[255]: 2131.87
TempMeasurementVector: [0]
TempIndex: [0]
ClipBinsAtEnds: On
}
ValidLabelValues: (, )
UseHistograms: On
NumBins: [256]
LowerBound: -135.632
UpperBound: 2131.87
In [7]:
factor = 1.5
lower_threshold = stats.GetMean(1) - factor * stats.GetSigma(1)
upper_threshold = stats.GetMean(1) + factor * stats.GetSigma(1)
In [8]:
init_ls = sitk.SignedMaurerDistanceMap(seg, insideIsPositive=True, useImageSpacing=True)
In [9]:
lsFilter = sitk.ThresholdSegmentationLevelSetImageFilter()
lsFilter.SetLowerThreshold(lower_threshold)
lsFilter.SetUpperThreshold(upper_threshold)
lsFilter.SetMaximumRMSError(0.02)
lsFilter.SetNumberOfIterations(100)
lsFilter.SetCurvatureScaling(1)
lsFilter.SetPropagationScaling(1)
lsFilter.ReverseExpansionDirectionOn()
ls = lsFilter.Execute(init_ls, sitk.Cast(img_T1, sitk.sitkFloat32))
print(lsFilter)
itk::simple::ThresholdSegmentationLevelSetImageFilter LowerThreshold: 375.028 UpperThreshold: 578.107 MaximumRMSError: 0.02 PropagationScaling: 1 CurvatureScaling: 1 NumberOfIterations: 100 ReverseExpansionDirection: 1 ElapsedIterations: 100 RMSChange: 0.0691501 Debug: 0 NumberOfThreads: 16 NumberOfWorkUnits: 0 Commands: (none) ProgressMeasurement: 1 ActiveProcess: (none)
In [10]:
zslice_offset = 4
t = "LevelSet after " + str(lsFilter.GetNumberOfIterations()) + " iterations"
myshow3d(
sitk.LabelOverlay(img_T1_255, ls > 0),
zslices=range(idx[2] - zslice_offset, idx[2] + zslice_offset + 1, zslice_offset),
dpi=20,
title=t,
)
In [11]:
lsFilter.SetNumberOfIterations(25)
img_T1f = sitk.Cast(img_T1, sitk.sitkFloat32)
ls = init_ls
niter = 0
for i in range(0, 10):
ls = lsFilter.Execute(ls, img_T1f)
niter += lsFilter.GetNumberOfIterations()
t = (
"LevelSet after "
+ str(niter)
+ " iterations and RMS "
+ str(lsFilter.GetRMSChange())
)
fig = myshow3d(
sitk.LabelOverlay(img_T1_255, ls > 0),
zslices=range(
idx[2] - zslice_offset, idx[2] + zslice_offset + 1, zslice_offset
),
dpi=20,
title=t,
)
