Skip to main content

Table 1 Datasets used in the experiments

From: The effect of preprocessing filters on predictive performance in radiomics

Dataset Modality N (excluded) In-plane resolution (mm) Slice thickness (m)
CRLM CT 76 (1) 0.7 (0.6–0.9) 5.0 (1.0–8.0)
Desmoid MRI 195 (8) 0.7 (0.2–1.8) 5.0 (1.0–10.0)
GIST CT 244 (2) 0.8 (0.6–1.0) 3.0 (0.6–6.0)
HN CT 134 (1) 1.0 (1.0–1.1) 3.0 (1.5–3.0)
Lipo MRI 113 (2) 0.7 (0.2–1.4) 5.5 (1.0–9.1)
Liver MRI 186 (0) 0.8 (0.6–1.6) 7.7 (1.0–11.0)
Melanoma CT 97 (6) 0.7 (0.5–1.0) 1.2 (0.6–2.0)
  1. N denotes the number of samples, with the number of scans removed from the original dataset in parenthesis (excluded); for example, there were 203 scans in the Desmoid dataset, 8 of which have been removed. In-plane resolution and slice thickness are reported as median (range). CT Computed tomography, MRI Magnetic resonance imaging. For the datasets, see references [9, 10]