M1-09 frozen feature manifest (read-only lookup)
Reference · The exact 107 features of TRACE-CT’s frozen M1-09 manifest — for lookup and verification, not a memorisation objective. Learn the families (Feature families and their assumptions); look the names up here.
Source (read-only): TRACE-CT configs/rider-m1-09-feature-manifest.json,
manifest_sha256 d236c898d85b4241482cdd20c3e740e3576dd002e28877fd2e237a494332c5c1,
resolved from pinned PyRadiomics 3.1.1.dev111+g8ed579383
(commit 8ed579383b44806651c463d5e691f3b2b57522ab).
Scope: non-deprecated Original 3D features only. Excluded by design:
shape2D; all filtered image types (Wavelet, LoG, Square, SquareRoot,
Logarithm, Exponential, Gradient, LBP-2D/3D); voxel feature maps; deprecated
features; diagnostics/provenance fields. This exact set equals the pinned
build’s default-enabled non-deprecated 3D features (firstorder drops
StandardDeviation; shape drops Compactness1/2, SphericalDisproportion).
Canonical names carry the image type prefix: original_<class>_<Feature>.
firstorder (18)
original_firstorder_10Percentile · 90Percentile · Energy · Entropy ·
InterquartileRange · Kurtosis · Maximum · MeanAbsoluteDeviation ·
Mean · Median · Minimum · Range · RobustMeanAbsoluteDeviation ·
RootMeanSquared · Skewness · TotalEnergy · Uniformity · Variance
shape (14)
original_shape_Elongation · Flatness · LeastAxisLength ·
MajorAxisLength · Maximum2DDiameterColumn · Maximum2DDiameterRow ·
Maximum2DDiameterSlice · Maximum3DDiameter · MeshVolume ·
MinorAxisLength · Sphericity · SurfaceArea · SurfaceVolumeRatio ·
VoxelVolume
glcm (24)
original_glcm_Autocorrelation · ClusterProminence · ClusterShade ·
ClusterTendency · Contrast · Correlation · DifferenceAverage ·
DifferenceEntropy · DifferenceVariance · Id · Idm · Idmn · Idn ·
Imc1 · Imc2 · InverseVariance · JointAverage · JointEnergy ·
JointEntropy · MCC · MaximumProbability · SumAverage · SumEntropy ·
SumSquares
glrlm (16)
original_glrlm_GrayLevelNonUniformity · GrayLevelNonUniformityNormalized ·
GrayLevelVariance · HighGrayLevelRunEmphasis · LongRunEmphasis ·
LongRunHighGrayLevelEmphasis · LongRunLowGrayLevelEmphasis ·
LowGrayLevelRunEmphasis · RunEntropy · RunLengthNonUniformity ·
RunLengthNonUniformityNormalized · RunPercentage · RunVariance ·
ShortRunEmphasis · ShortRunHighGrayLevelEmphasis ·
ShortRunLowGrayLevelEmphasis
glszm (16)
original_glszm_GrayLevelNonUniformity · GrayLevelNonUniformityNormalized ·
GrayLevelVariance · HighGrayLevelZoneEmphasis · LargeAreaEmphasis ·
LargeAreaHighGrayLevelEmphasis · LargeAreaLowGrayLevelEmphasis ·
LowGrayLevelZoneEmphasis · SizeZoneNonUniformity ·
SizeZoneNonUniformityNormalized · SmallAreaEmphasis ·
SmallAreaHighGrayLevelEmphasis · SmallAreaLowGrayLevelEmphasis ·
ZoneEntropy · ZonePercentage · ZoneVariance
gldm (14)
original_gldm_DependenceEntropy · DependenceNonUniformity ·
DependenceNonUniformityNormalized · DependenceVariance ·
GrayLevelNonUniformity · GrayLevelVariance · HighGrayLevelEmphasis ·
LargeDependenceEmphasis · LargeDependenceHighGrayLevelEmphasis ·
LargeDependenceLowGrayLevelEmphasis · LowGrayLevelEmphasis ·
SmallDependenceEmphasis · SmallDependenceHighGrayLevelEmphasis ·
SmallDependenceLowGrayLevelEmphasis
ngtdm (5)
original_ngtdm_Busyness · Coarseness · Complexity · Contrast ·
Strength
Family summary
| Family | Count | Starts from |
|---|---|---|
| firstorder | 18 | ROI voxel-intensity distribution (raw values for Mean/Variance/…; discretised histogram for Entropy/Uniformity) |
| shape | 14 | mask only |
| glcm | 24 | co-occurrence matrix (discretised ROI) |
| glrlm | 16 | run-length matrix |
| glszm | 16 | size-zone matrix |
| gldm | 14 | dependence matrix |
| ngtdm | 5 | neighbourhood grey-tone differences |
| total | 107 |
Status reminder: this manifest is part of the frozen design; this lookup intentionally contains no aggregate result table. See the TRACE-CT learning map for the live mapping and the project’s execution status.
© 2026 Adrian Tkacz · BioMedical-IT
Original text and figures are licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), unless otherwise noted. Please credit Adrian Tkacz / BioMedical-IT and link to the original source. Third-party materials retain their respective rights and licenses.