Skip to main content
. 2021 Mar 22;11:6482. doi: 10.1038/s41598-021-85758-6

Table 5.

Number of spectra in each class for k-means on full dataset (n = 203).

Dataset Cluster 1 (healthy) Cluster 2 (tumor)
FP 88 115
FPHW 86 117
HW 87 116

This remains consistent over multiple re-runs of the algorithm.