Skip to main content
. 2015 Oct 25;2015:764383. doi: 10.1155/2015/764383

Table 2.

Results of the reproducibility test for the automatically trained kNN algorithm. Volume estimates of the scan and rescan sessions in the case of an input with three and two contrast image types.

Subject 1 Subject 2 Subject 3
Scan (cc) Rescan (cc) Δ (%) Scan (cc) Rescan (cc) Δ (%) Scan (cc) Rescan (cc) Δ (%)
kNN
(T1w, T2w, and FLAIR)
Caudate 8.28 8.18 1.2 6.92 7.02 1.4 7.11 7.08 0.4
Thalamus 13.58 14.02 3.2 12.87 12.82 0.4 13.98 14.31 2.3
Pallidum 2.61 2.33 11.3 2.42 2.26 6.8 3.04 2.99 1.7
Putamen 10.31 10.60 2.8 11.54 11.42 1.0 13.06 12.84 1.7

kNN
(T1w, FLAIR)
Caudate 9.17 8.92 2.8 7.78 7.97 2.4 8.18 8.17 0.1
Thalamus 13.49 13.62 1.0 13.04 13.10 0.5 14.42 14.76 2.3
Pallidum 2.41 2.17 10.5 2.50 2.41 3.7 2.83 2.76 2.5
Putamen 9.92 10.39 4.6 11.16 11.24 0.7 12.55 12.40 1.2