Fig. 5: Stability of image restoration by DeepCristae.
From: DeepCristae, a CNN for the restoration of mitochondria cristae in live microscopy images
Assessment of the stability of DeepCristae by studying the consistency between its predictions obtained with different training. To that end, 10 DeepCristae neural networks were trained with different training data, each one generated with our patch generation method applied to the 24 training images of \({D}_{{synt}}\). Note that for this experiment, all networks were initialized with the same weights. a Quantitative comparison of the 10 DeepCristae models. Metrics were computed on the test set of \({D}_{{synt}}\). Data are expressed as mean ± standard deviation. b From left to right: predictions of three DeepCristae networks on two images, the average prediction over the 10 trainings and the corresponding pixel-wise normalized standard deviation. Pixel size: 25 nm. Scale bar: 1 μm. c–f Comparison of normalized intensity line profiles along a mitochondrion in (b) between the 10 trainings. The yellow line, indicated in the corresponding colored inset in (b) serves to identify the fluorescence profile.
