Skip to main content

Table 1 Statistics of samples, volume (presented by the LIDC-IDRI dataset), and accuracy (with 95% confidence intervals) of classification using the two types of images on the training, validation, and test datasets

From: Decoding intra-tumoral spatial heterogeneity on radiological images using the Hilbert curve

  Training Validation Test
Dataset
 Benign 428 52 52
 Malignant 321 40 40
 Volume (avg) 1221.05 985.33 1069.61
Accuracy (95% CI)
 Original CT images 95.69% (94.29–97.09%) 75.05% (66.21–83.89%) 73.22% (64.18–82.26%)
 Hilbert matrix images 93.45% (91.86–95.04%) 86.36% (69.35–93.37%) 85.54% (78.35–92.73%)
  1. CI confidence intervals