Refine
Has Fulltext
- yes (6)
Is part of the Bibliography
- yes (6)
Document Type
- Journal article (5)
- Doctoral Thesis (1)
Language
- English (6)
Keywords
- dSTORM (3)
- AI (1)
- BDNF stimulation (1)
- Bildverarbeitung (1)
- Compressed Sensing (1)
- Datenanalyse (1)
- FLIMbee (1)
- Künstliche Intelligenz (1)
- Lifetime Imaging (1)
- Mikroskopie (1)
- SARS-CoV-2 (1)
- SMLM (1)
- acid sphingomyelinase (1)
- biological fluorescence (1)
- ceramidase (1)
- ceramides (1)
- compressed sensing (1)
- deep learning–artificial neural network (DL-ANN) (1)
- dynamics of ribosomal assembly (1)
- fluorescence imaging (1)
- fluoxetine (1)
- imaging the immune system (1)
- infectious diseases (1)
- microtubule cytoskeleton (1)
- presynaptic ER dynamics (1)
- single molecule localization microscopy (1)
- spinal muscular atrophy (1)
- super-resolution (1)
- super-resolution microscopy (1)
Institute
- Theodor-Boveri-Institut für Biowissenschaften (5)
- Center for Computational and Theoretical Biology (2)
- Institut für Klinische Neurobiologie (1)
- Institut für Organische Chemie (1)
- Institut für Theoretische Physik und Astrophysik (1)
- Institut für Virologie und Immunbiologie (1)
- Medizinische Klinik und Poliklinik II (1)
EU-Project number / Contract (GA) number
- 835102) (1)
Single-molecule super-resolution microscopy (SMLM) techniques like dSTORM can reveal biological structures down to the nanometer scale. The achievable resolution is not only defined by the localization precision of individual fluorescent molecules, but also by their density, which becomes a limiting factor e.g., in expansion microscopy. Artificial deep neural networks can learn to reconstruct dense super-resolved structures such as microtubules from a sparse, noisy set of data points. This approach requires a robust method to assess the quality of a predicted density image and to quantitatively compare it to a ground truth image. Such a quality measure needs to be differentiable to be applied as loss function in deep learning. We developed a new trainable quality measure based on Fourier Ring Correlation (FRC) and used it to train deep neural networks to map a small number of sampling points to an underlying density. Smooth ground truth images of microtubules were generated from localization coordinates using an anisotropic Gaussian kernel density estimator. We show that the FRC criterion ideally complements the existing state-of-the-art multiscale structural similarity index, since both are interpretable and there is no trade-off between them during optimization. The TensorFlow implementation of our FRC metric can easily be integrated into existing deep learning workflows.