Skip to main content

Table 1 Summary of histomorphometric features extracted from TMA

From: Nuclear shape, architecture and orientation features from H&E images are able to predict recurrence in node-negative gastric adenocarcinoma

Feature type No. Description
Nuclear shape 100 Area ratio, distance ratio, SD of distance, distance ratio, perimeter ratio, variance of distance, fractal dimension, smoothness, invariant moment 1–7, Fourier descriptor 1–10: min/max, mean, SD, median
Nuclear texture 30 Contrast, energy, entropy, inverse variance, invariant moment: mean, SD from each channel
Nuclear orientation map 39 Contrast energy, contrast inverse moment, contrast average, contrast variance, contrast entropy, intensity average, intensity variance, intensity entropy, entropy, energy, correlation, information measure 1, information measure 2: mean, SD, range
VD 12 Perimeter, chord, area: SD, min/max, disorder, average
DT 8 Side length, triangle area: min/max, mean, standard deviation, median, disorder
In total 189  
  1. SD standard deviation, VD Voronoi diagram, DT Delaunay triangulation