Fig. 6: CITE-On cell detection performance compared to state-of-the-art methods. | Nature Communications

Fig. 6: CITE-On cell detection performance compared to state-of-the-art methods.

From: A deep-learning approach for online cell identification and trace extraction in functional two-photon calcium imaging

Fig. 6

a, b Precision (left), Recall (middle), and F-1 score (right) in cell detection for CITE-On and other methods (for other methods plotted data are reported from ref. 22). CITE-On performance is evaluated on ABOsup (a, N = 9 t-series), ABOdeep (b, N = 10 t-series). CITE-On performance is calculated using our consensus ground truth (“ground truth from this work”, left of the vertical dotted line) or using the ground truth reported in Soltanian-Zadeh et al.22 (right of the vertical dotted line). CITE-On performance is shown in bloxplots, the performance of other methods is shown as mean ± s.d from ref. 22. The orange line in all boxplots is the median, the bounds of the boxes are the 75th and 25th percentiles (i.e., the interquartile range (IQR)), and the whiskers correspond to the highest value or lowest value of the distribution. If the lowest or highest values are outliers (i.e., >1.5 *IQR from the bounds of the boxes) the whiskers correspond to 1.5 *IQR. Outliers are represented as black diamonds.

Back to article page