Statistics using Nyxus#
The Nyxus library contains a large number of features that can be extracted from image data. It can be installed using pip:
pip install nyxus==0.5.0
See also
Before we can do measurements, we need an image and a corresponding label_image. Therefore, we recapitulate filtering, thresholding and labeling:
from skimage.io import imread
import stackview
from nyxus import Nyxus
intensity_image = imread("../../data/blobs.tif")
stackview.insight(intensity_image)
|
|
label_image = imread("../../data/blobs_labeled.tif")
# visualization
stackview.insight(label_image)
|
|
Measurements#
We now use nyxus’ function featurize to extract quantitative measurements. For the beginning, we just use ALL features.
nyx = Nyxus(["*ALL*"])
features = nyx.featurize(intensity_image, label_image)
features
| mask_image | intensity_image | label | INTEGRATED_INTENSITY | MEAN | MEDIAN | MIN | MAX | RANGE | STANDARD_DEVIATION | ... | WEIGHTED_HU_M5 | WEIGHTED_HU_M6 | WEIGHTED_HU_M7 | GABOR_0 | GABOR_1 | GABOR_2 | GABOR_3 | GABOR_4 | GABOR_5 | GABOR_6 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | Segmentation0 | Intensity0 | 1 | 98336.0 | 159.119741 | 176.0 | 40.0 | 232.0 | 192.0 | 56.038438 | ... | 2.775224e-31 | 4.901126e-10 | 2.447020e-32 | 0.227322 | 0.0 | 0.0 | 0.800000 | 0.755191 | 0.726776 | 0.710383 |
| 1 | Segmentation0 | Intensity0 | 2 | 41104.0 | 148.389892 | 168.0 | 48.0 | 224.0 | 176.0 | 48.834751 | ... | 1.865947e-12 | 1.094818e-03 | -2.652105e-12 | 0.375358 | 0.0 | 0.0 | 0.922636 | 0.899713 | 0.888252 | 0.856734 |
| 2 | Segmentation0 | Intensity0 | 3 | 151632.0 | 178.180964 | 200.0 | 40.0 | 248.0 | 208.0 | 57.811867 | ... | 5.235402e-13 | 3.374755e-04 | -9.289798e-13 | 0.064581 | 0.0 | 0.0 | 0.957619 | 0.945510 | 0.926337 | 0.913219 |
| 3 | Segmentation0 | Intensity0 | 4 | 106800.0 | 181.942078 | 208.0 | 24.0 | 248.0 | 224.0 | 68.344166 | ... | -2.119980e-10 | 3.721221e-03 | 7.231199e-10 | 0.018598 | 0.0 | 0.0 | 0.932761 | 0.925608 | 0.907010 | 0.879828 |
| 4 | Segmentation0 | Intensity0 | 5 | 110136.0 | 188.266667 | 216.0 | 40.0 | 248.0 | 208.0 | 57.713131 | ... | 9.503623e-06 | -5.115360e-03 | 4.167152e-06 | 0.000000 | 0.0 | 0.0 | 0.976923 | 0.972308 | 0.953846 | 0.940000 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 58 | Segmentation0 | Intensity0 | 59 | 2752.0 | 105.846154 | 104.0 | 88.0 | 136.0 | 48.0 | 14.004834 | ... | NaN | NaN | NaN | inf | inf | inf | inf | inf | inf | inf |
| 59 | Segmentation0 | Intensity0 | 60 | 22632.0 | 136.337349 | 140.0 | 48.0 | 216.0 | 168.0 | 54.780505 | ... | NaN | NaN | NaN | 0.754808 | 0.0 | 0.0 | 0.966346 | 0.956731 | 0.927885 | 0.889423 |
| 60 | Segmentation0 | Intensity0 | 61 | 20040.0 | 137.260274 | 132.0 | 40.0 | 248.0 | 208.0 | 59.842097 | ... | NaN | NaN | NaN | 0.812500 | 0.0 | 0.0 | 0.988636 | 0.977273 | 0.954545 | 0.914773 |
| 61 | Segmentation0 | Intensity0 | 62 | 14320.0 | 132.592593 | 120.0 | 40.0 | 248.0 | 208.0 | 63.382099 | ... | NaN | NaN | NaN | 0.812030 | 0.0 | 0.0 | 0.977444 | 0.969925 | 0.932331 | 0.894737 |
| 62 | Segmentation0 | Intensity0 | 63 | 12880.0 | 125.048544 | 120.0 | 48.0 | 224.0 | 176.0 | 51.894195 | ... | NaN | NaN | NaN | 0.866667 | 0.0 | 0.0 | 1.000000 | 1.000000 | 0.966667 | 0.950000 |
63 rows × 417 columns
This table has a huge number of columns.
print([f for f in features.columns])
['mask_image', 'intensity_image', 'label', 'INTEGRATED_INTENSITY', 'MEAN', 'MEDIAN', 'MIN', 'MAX', 'RANGE', 'STANDARD_DEVIATION', 'STANDARD_ERROR', 'SKEWNESS', 'KURTOSIS', 'HYPERSKEWNESS', 'HYPERFLATNESS', 'MEAN_ABSOLUTE_DEVIATION', 'ENERGY', 'ROOT_MEAN_SQUARED', 'ENTROPY', 'MODE', 'UNIFORMITY', 'UNIFORMITY_PIU', 'P01', 'P10', 'P25', 'P75', 'P90', 'P99', 'INTERQUARTILE_RANGE', 'ROBUST_MEAN_ABSOLUTE_DEVIATION', 'AREA_PIXELS_COUNT', 'AREA_UM2', 'CENTROID_X', 'CENTROID_Y', 'WEIGHTED_CENTROID_Y', 'WEIGHTED_CENTROID_X', 'MASS_DISPLACEMENT', 'COMPACTNESS', 'BBOX_YMIN', 'BBOX_XMIN', 'BBOX_HEIGHT', 'BBOX_WIDTH', 'DIAMETER_EQUAL_AREA', 'EXTENT', 'ASPECT_RATIO', 'MAJOR_AXIS_LENGTH', 'MINOR_AXIS_LENGTH', 'ECCENTRICITY', 'ELONGATION', 'ORIENTATION', 'ROUNDNESS', 'PERIMETER', 'DIAMETER_EQUAL_PERIMETER', 'EDGE_MEAN_INTENSITY', 'EDGE_STDDEV_INTENSITY', 'EDGE_MAX_INTENSITY', 'EDGE_MIN_INTENSITY', 'EDGE_INTEGRATED_INTENSITY', 'CIRCULARITY', 'CONVEX_HULL_AREA', 'SOLIDITY', 'EROSIONS_2_VANISH', 'EROSIONS_2_VANISH_COMPLEMENT', 'FRACT_DIM_BOXCOUNT', 'FRACT_DIM_PERIMETER', 'MIN_FERET_DIAMETER', 'MAX_FERET_DIAMETER', 'MIN_FERET_ANGLE', 'MAX_FERET_ANGLE', 'STAT_FERET_DIAM_MIN', 'STAT_FERET_DIAM_MAX', 'STAT_FERET_DIAM_MEAN', 'STAT_FERET_DIAM_MEDIAN', 'STAT_FERET_DIAM_STDDEV', 'STAT_FERET_DIAM_MODE', 'STAT_MARTIN_DIAM_MIN', 'STAT_MARTIN_DIAM_MAX', 'STAT_MARTIN_DIAM_MEAN', 'STAT_MARTIN_DIAM_MEDIAN', 'STAT_MARTIN_DIAM_STDDEV', 'STAT_MARTIN_DIAM_MODE', 'STAT_NASSENSTEIN_DIAM_MIN', 'STAT_NASSENSTEIN_DIAM_MAX', 'STAT_NASSENSTEIN_DIAM_MEAN', 'STAT_NASSENSTEIN_DIAM_MEDIAN', 'STAT_NASSENSTEIN_DIAM_STDDEV', 'STAT_NASSENSTEIN_DIAM_MODE', 'MAXCHORDS_MAX', 'MAXCHORDS_MAX_ANG', 'MAXCHORDS_MIN', 'MAXCHORDS_MIN_ANG', 'MAXCHORDS_MEDIAN', 'MAXCHORDS_MEAN', 'MAXCHORDS_MODE', 'MAXCHORDS_STDDEV', 'ALLCHORDS_MAX', 'ALLCHORDS_MAX_ANG', 'ALLCHORDS_MIN', 'ALLCHORDS_MIN_ANG', 'ALLCHORDS_MEDIAN', 'ALLCHORDS_MEAN', 'ALLCHORDS_MODE', 'ALLCHORDS_STDDEV', 'EULER_NUMBER', 'EXTREMA_P1_X', 'EXTREMA_P1_Y', 'EXTREMA_P2_X', 'EXTREMA_P2_Y', 'EXTREMA_P3_X', 'EXTREMA_P3_Y', 'EXTREMA_P4_X', 'EXTREMA_P4_Y', 'EXTREMA_P5_X', 'EXTREMA_P5_Y', 'EXTREMA_P6_X', 'EXTREMA_P6_Y', 'EXTREMA_P7_X', 'EXTREMA_P7_Y', 'EXTREMA_P8_X', 'EXTREMA_P8_Y', 'POLYGONALITY_AVE', 'HEXAGONALITY_AVE', 'HEXAGONALITY_STDDEV', 'DIAMETER_MIN_ENCLOSING_CIRCLE', 'DIAMETER_CIRCUMSCRIBING_CIRCLE', 'DIAMETER_INSCRIBING_CIRCLE', 'GEODETIC_LENGTH', 'THICKNESS', 'ROI_RADIUS_MEAN', 'ROI_RADIUS_MAX', 'ROI_RADIUS_MEDIAN', 'NUM_NEIGHBORS', 'PERCENT_TOUCHING', 'CLOSEST_NEIGHBOR1_DIST', 'CLOSEST_NEIGHBOR1_ANG', 'CLOSEST_NEIGHBOR2_DIST', 'CLOSEST_NEIGHBOR2_ANG', 'ANG_BW_NEIGHBORS_MEAN', 'ANG_BW_NEIGHBORS_STDDEV', 'ANG_BW_NEIGHBORS_MODE', 'GLCM_ANGULAR2NDMOMENT_0', 'GLCM_ANGULAR2NDMOMENT_45', 'GLCM_ANGULAR2NDMOMENT_90', 'GLCM_ANGULAR2NDMOMENT_135', 'GLCM_CONTRAST_0', 'GLCM_CONTRAST_45', 'GLCM_CONTRAST_90', 'GLCM_CONTRAST_135', 'GLCM_CORRELATION_0', 'GLCM_CORRELATION_45', 'GLCM_CORRELATION_90', 'GLCM_CORRELATION_135', 'GLCM_DIFFERENCEAVERAGE', 'GLCM_DIFFERENCEENTROPY_0', 'GLCM_DIFFERENCEENTROPY_45', 'GLCM_DIFFERENCEENTROPY_90', 'GLCM_DIFFERENCEENTROPY_135', 'GLCM_DIFFERENCEVARIANCE_0', 'GLCM_DIFFERENCEVARIANCE_45', 'GLCM_DIFFERENCEVARIANCE_90', 'GLCM_DIFFERENCEVARIANCE_135', 'GLCM_ENERGY', 'GLCM_ENTROPY_0', 'GLCM_ENTROPY_45', 'GLCM_ENTROPY_90', 'GLCM_ENTROPY_135', 'GLCM_HOMOGENEITY', 'GLCM_INFOMEAS1_0', 'GLCM_INFOMEAS1_45', 'GLCM_INFOMEAS1_90', 'GLCM_INFOMEAS1_135', 'GLCM_INFOMEAS2_0', 'GLCM_INFOMEAS2_45', 'GLCM_INFOMEAS2_90', 'GLCM_INFOMEAS2_135', 'GLCM_INVERSEDIFFERENCEMOMENT_0', 'GLCM_INVERSEDIFFERENCEMOMENT_45', 'GLCM_INVERSEDIFFERENCEMOMENT_90', 'GLCM_INVERSEDIFFERENCEMOMENT_135', 'GLCM_SUMAVERAGE_0', 'GLCM_SUMAVERAGE_45', 'GLCM_SUMAVERAGE_90', 'GLCM_SUMAVERAGE_135', 'GLCM_SUMENTROPY_0', 'GLCM_SUMENTROPY_45', 'GLCM_SUMENTROPY_90', 'GLCM_SUMENTROPY_135', 'GLCM_SUMVARIANCE_0', 'GLCM_SUMVARIANCE_45', 'GLCM_SUMVARIANCE_90', 'GLCM_SUMVARIANCE_135', 'GLCM_VARIANCE_0', 'GLCM_VARIANCE_45', 'GLCM_VARIANCE_90', 'GLCM_VARIANCE_135', 'GLRLM_SRE_0', 'GLRLM_SRE_45', 'GLRLM_SRE_90', 'GLRLM_SRE_135', 'GLRLM_LRE_0', 'GLRLM_LRE_45', 'GLRLM_LRE_90', 'GLRLM_LRE_135', 'GLRLM_GLN_0', 'GLRLM_GLN_45', 'GLRLM_GLN_90', 'GLRLM_GLN_135', 'GLRLM_GLNN_0', 'GLRLM_GLNN_45', 'GLRLM_GLNN_90', 'GLRLM_GLNN_135', 'GLRLM_RLN_0', 'GLRLM_RLN_45', 'GLRLM_RLN_90', 'GLRLM_RLN_135', 'GLRLM_RLNN_0', 'GLRLM_RLNN_45', 'GLRLM_RLNN_90', 'GLRLM_RLNN_135', 'GLRLM_RP_0', 'GLRLM_RP_45', 'GLRLM_RP_90', 'GLRLM_RP_135', 'GLRLM_GLV_0', 'GLRLM_GLV_45', 'GLRLM_GLV_90', 'GLRLM_GLV_135', 'GLRLM_RV_0', 'GLRLM_RV_45', 'GLRLM_RV_90', 'GLRLM_RV_135', 'GLRLM_RE_0', 'GLRLM_RE_45', 'GLRLM_RE_90', 'GLRLM_RE_135', 'GLRLM_LGLRE_0', 'GLRLM_LGLRE_45', 'GLRLM_LGLRE_90', 'GLRLM_LGLRE_135', 'GLRLM_HGLRE_0', 'GLRLM_HGLRE_45', 'GLRLM_HGLRE_90', 'GLRLM_HGLRE_135', 'GLRLM_SRLGLE_0', 'GLRLM_SRLGLE_45', 'GLRLM_SRLGLE_90', 'GLRLM_SRLGLE_135', 'GLRLM_SRHGLE_0', 'GLRLM_SRHGLE_45', 'GLRLM_SRHGLE_90', 'GLRLM_SRHGLE_135', 'GLRLM_LRLGLE_0', 'GLRLM_LRLGLE_45', 'GLRLM_LRLGLE_90', 'GLRLM_LRLGLE_135', 'GLRLM_LRHGLE_0', 'GLRLM_LRHGLE_45', 'GLRLM_LRHGLE_90', 'GLRLM_LRHGLE_135', 'GLSZM_SAE', 'GLSZM_LAE', 'GLSZM_GLN', 'GLSZM_GLNN', 'GLSZM_SZN', 'GLSZM_SZNN', 'GLSZM_ZP', 'GLSZM_GLV', 'GLSZM_ZV', 'GLSZM_ZE', 'GLSZM_LGLZE', 'GLSZM_HGLZE', 'GLSZM_SALGLE', 'GLSZM_SAHGLE', 'GLSZM_LALGLE', 'GLSZM_LAHGLE', 'GLDM_SDE', 'GLDM_LDE', 'GLDM_GLN', 'GLDM_DN', 'GLDM_DNN', 'GLDM_GLV', 'GLDM_DV', 'GLDM_DE', 'GLDM_LGLE', 'GLDM_HGLE', 'GLDM_SDLGLE', 'GLDM_SDHGLE', 'GLDM_LDLGLE', 'GLDM_LDHGLE', 'NGTDM_COARSENESS', 'NGTDM_CONTRAST', 'NGTDM_BUSYNESS', 'NGTDM_COMPLEXITY', 'NGTDM_STRENGTH', 'ZERNIKE2D_0', 'ZERNIKE2D_1', 'ZERNIKE2D_2', 'ZERNIKE2D_3', 'ZERNIKE2D_4', 'ZERNIKE2D_5', 'ZERNIKE2D_6', 'ZERNIKE2D_7', 'ZERNIKE2D_8', 'ZERNIKE2D_9', 'ZERNIKE2D_10', 'ZERNIKE2D_11', 'ZERNIKE2D_12', 'ZERNIKE2D_13', 'ZERNIKE2D_14', 'ZERNIKE2D_15', 'ZERNIKE2D_16', 'ZERNIKE2D_17', 'ZERNIKE2D_18', 'ZERNIKE2D_19', 'ZERNIKE2D_20', 'ZERNIKE2D_21', 'ZERNIKE2D_22', 'ZERNIKE2D_23', 'ZERNIKE2D_24', 'ZERNIKE2D_25', 'ZERNIKE2D_26', 'ZERNIKE2D_27', 'ZERNIKE2D_28', 'ZERNIKE2D_29', 'FRAC_AT_D_0', 'FRAC_AT_D_1', 'FRAC_AT_D_2', 'FRAC_AT_D_3', 'FRAC_AT_D_4', 'FRAC_AT_D_5', 'FRAC_AT_D_6', 'FRAC_AT_D_7', 'MEAN_FRAC_0', 'MEAN_FRAC_1', 'MEAN_FRAC_2', 'MEAN_FRAC_3', 'MEAN_FRAC_4', 'MEAN_FRAC_5', 'MEAN_FRAC_6', 'MEAN_FRAC_7', 'RADIAL_CV_0', 'RADIAL_CV_1', 'RADIAL_CV_2', 'RADIAL_CV_3', 'RADIAL_CV_4', 'RADIAL_CV_5', 'RADIAL_CV_6', 'RADIAL_CV_7', 'SPAT_MOMENT_00', 'SPAT_MOMENT_01', 'SPAT_MOMENT_02', 'SPAT_MOMENT_03', 'SPAT_MOMENT_10', 'SPAT_MOMENT_11', 'SPAT_MOMENT_12', 'SPAT_MOMENT_20', 'SPAT_MOMENT_21', 'SPAT_MOMENT_30', 'WEIGHTED_SPAT_MOMENT_00', 'WEIGHTED_SPAT_MOMENT_01', 'WEIGHTED_SPAT_MOMENT_02', 'WEIGHTED_SPAT_MOMENT_03', 'WEIGHTED_SPAT_MOMENT_10', 'WEIGHTED_SPAT_MOMENT_11', 'WEIGHTED_SPAT_MOMENT_12', 'WEIGHTED_SPAT_MOMENT_20', 'WEIGHTED_SPAT_MOMENT_21', 'WEIGHTED_SPAT_MOMENT_30', 'CENTRAL_MOMENT_02', 'CENTRAL_MOMENT_03', 'CENTRAL_MOMENT_11', 'CENTRAL_MOMENT_12', 'CENTRAL_MOMENT_20', 'CENTRAL_MOMENT_21', 'CENTRAL_MOMENT_30', 'WEIGHTED_CENTRAL_MOMENT_02', 'WEIGHTED_CENTRAL_MOMENT_03', 'WEIGHTED_CENTRAL_MOMENT_11', 'WEIGHTED_CENTRAL_MOMENT_12', 'WEIGHTED_CENTRAL_MOMENT_20', 'WEIGHTED_CENTRAL_MOMENT_21', 'WEIGHTED_CENTRAL_MOMENT_30', 'NORM_CENTRAL_MOMENT_02', 'NORM_CENTRAL_MOMENT_03', 'NORM_CENTRAL_MOMENT_11', 'NORM_CENTRAL_MOMENT_12', 'NORM_CENTRAL_MOMENT_20', 'NORM_CENTRAL_MOMENT_21', 'NORM_CENTRAL_MOMENT_30', 'NORM_SPAT_MOMENT_00', 'NORM_SPAT_MOMENT_01', 'NORM_SPAT_MOMENT_02', 'NORM_SPAT_MOMENT_03', 'NORM_SPAT_MOMENT_10', 'NORM_SPAT_MOMENT_20', 'NORM_SPAT_MOMENT_30', 'HU_M1', 'HU_M2', 'HU_M3', 'HU_M4', 'HU_M5', 'HU_M6', 'HU_M7', 'WEIGHTED_HU_M1', 'WEIGHTED_HU_M2', 'WEIGHTED_HU_M3', 'WEIGHTED_HU_M4', 'WEIGHTED_HU_M5', 'WEIGHTED_HU_M6', 'WEIGHTED_HU_M7', 'GABOR_0', 'GABOR_1', 'GABOR_2', 'GABOR_3', 'GABOR_4', 'GABOR_5', 'GABOR_6']
Thus, one can also request only specific columns, which should also be faster.
nyx = Nyxus(['ORIENTATION', 'PERIMETER'])
features = nyx.featurize(intensity_image, label_image)
features
| mask_image | intensity_image | label | ORIENTATION | PERIMETER | |
|---|---|---|---|---|---|
| 0 | Segmentation0 | Intensity0 | 1 | 54.267520 | 90.0 |
| 1 | Segmentation0 | Intensity0 | 2 | 85.152921 | 60.0 |
| 2 | Segmentation0 | Intensity0 | 3 | 82.808942 | 101.0 |
| 3 | Segmentation0 | Intensity0 | 4 | 86.016115 | 83.0 |
| 4 | Segmentation0 | Intensity0 | 5 | 86.626543 | 86.0 |
| ... | ... | ... | ... | ... | ... |
| 58 | Segmentation0 | Intensity0 | 59 | 17.474954 | 14.0 |
| 59 | Segmentation0 | Intensity0 | 60 | 27.004816 | 55.0 |
| 60 | Segmentation0 | Intensity0 | 61 | 35.594028 | 48.0 |
| 61 | Segmentation0 | Intensity0 | 62 | 43.113311 | 40.0 |
| 62 | Segmentation0 | Intensity0 | 63 | 16.436543 | 43.0 |
63 rows × 5 columns
Nyxus also defines feature groups in case one is interested in all shape parameters for example:
nyx = Nyxus(['*ALL_MORPHOLOGY*'])
features = nyx.featurize(intensity_image, label_image)
features
| mask_image | intensity_image | label | AREA_PIXELS_COUNT | AREA_UM2 | CENTROID_X | CENTROID_Y | WEIGHTED_CENTROID_Y | WEIGHTED_CENTROID_X | MASS_DISPLACEMENT | ... | ROUNDNESS | PERIMETER | DIAMETER_EQUAL_PERIMETER | EDGE_MEAN_INTENSITY | EDGE_STDDEV_INTENSITY | EDGE_MAX_INTENSITY | EDGE_MIN_INTENSITY | CIRCULARITY | CONVEX_HULL_AREA | SOLIDITY | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | Segmentation0 | Intensity0 | 1 | 618.0 | 618.0 | 13.996764 | 19.925566 | 20.964692 | 14.569964 | 1.186736 | ... | 0.556444 | 90.0 | 28.647890 | 89.511111 | 54.640242 | 232.0 | 40.0 | 0.979167 | 723.0 | 0.854772 |
| 1 | Segmentation0 | Intensity0 | 2 | 277.0 | 277.0 | 5.386282 | 62.841155 | 64.028221 | 5.826781 | 1.266162 | ... | 0.538386 | 60.0 | 19.098593 | 108.400000 | 56.037276 | 200.0 | 48.0 | 0.983317 | 404.5 | 0.684796 |
| 2 | Segmentation0 | Intensity0 | 3 | 851.0 | 851.0 | 13.683901 | 108.360752 | 109.423605 | 14.046006 | 1.122842 | ... | 0.955491 | 101.0 | 32.149299 | 99.881188 | 67.339036 | 240.0 | 40.0 | 1.023878 | 1007.5 | 0.844665 |
| 3 | Segmentation0 | Intensity0 | 4 | 587.0 | 587.0 | 10.768313 | 154.402044 | 155.352659 | 11.091610 | 1.004086 | ... | 0.897266 | 83.0 | 26.419721 | 95.807229 | 66.335154 | 248.0 | 24.0 | 1.034775 | 699.0 | 0.839771 |
| 4 | Segmentation0 | Intensity0 | 5 | 585.0 | 585.0 | 14.471795 | 245.709402 | 247.626062 | 14.553933 | 1.918420 | ... | 0.652867 | 86.0 | 27.374650 | 133.209302 | 77.210349 | 240.0 | 40.0 | 0.996975 | 1265.0 | 0.462451 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 58 | Segmentation0 | Intensity0 | 59 | 26.0 | 26.0 | 243.000000 | 76.500000 | 77.497093 | 243.941860 | 1.371603 | ... | 0.831872 | 14.0 | 4.456338 | 95.428571 | 7.334998 | 112.0 | 88.0 | 1.291111 | 334.0 | 0.077844 |
| 59 | Segmentation0 | Intensity0 | 60 | 166.0 | 166.0 | 250.192771 | 127.439759 | 128.530223 | 251.759279 | 1.908680 | ... | 0.285586 | 55.0 | 17.507044 | 119.127273 | 66.571892 | 216.0 | 48.0 | 0.830417 | 1251.5 | 0.132641 |
| 60 | Segmentation0 | Intensity0 | 61 | 146.0 | 146.0 | 250.089041 | 178.952055 | 179.750499 | 251.684232 | 1.783857 | ... | 0.346108 | 48.0 | 15.278875 | 115.166667 | 71.587273 | 248.0 | 40.0 | 0.892360 | 1038.0 | 0.140655 |
| 61 | Segmentation0 | Intensity0 | 62 | 108.0 | 108.0 | 250.518519 | 234.500000 | 235.496648 | 252.100559 | 1.869802 | ... | 0.360323 | 40.0 | 12.732395 | 119.600000 | 75.242105 | 248.0 | 40.0 | 0.920994 | 813.0 | 0.132841 |
| 62 | Segmentation0 | Intensity0 | 63 | 103.0 | 103.0 | 250.912621 | 73.990291 | 74.896894 | 252.377640 | 1.722849 | ... | 0.274059 | 43.0 | 13.687325 | 117.395349 | 64.420545 | 224.0 | 48.0 | 0.836672 | 1347.5 | 0.076438 |
63 rows × 32 columns
Exercise#
Make a table with only solidity, circularity and roundness.