Additional file 7 of Application of convolutional neural networks towards nuclei segmentation in localization-based super-resolution fluorescence microscopy images

Christopher A. Mela & Yang Liu
Additional file 7: Figure S7. Improper noise model can result in nuclei deletion when denoising. When conducting denoising using an improperly trained UNet noise model (trained only on dense noise), less noisy super-resolution images from our colon tissue dataset (A), which also contain less densely labeled nuclei, sometimes suffered from nuclei deletion (C) due to the networks inability to accurately distinguish noise from cell data (B). The noise probability map (B) from the UNet model...
This data repository is not currently reporting usage information. For information on how your repository can submit usage information, please see our documentation.