Fig. 6: Comparison of cell line classification performance using different imaging modalities.

The results from passage 0, passage 1, and passage 2 are shown in (a, d), (b, e), and (c, f), respectively. a–c Classification performance for each passage using individual imaging modalities (i.e., 2PF, 3PF, THG) and combinations of imaging modalities (i.e., SLAM, FLIM, SLAM + FLIM). Each dot in the plots represents the result of one-fold of the 10-fold Monte Carlo cross-validation. d–f Balanced accuracies and impurity scores of all experiments are shown in the bar plots. The error bars indicate the standard deviations. Welch’s unequal variances t-tests were used for the statistical comparison of classification performance between different imaging modalities.