Showing papers by "Olaf Ronneberger published in 2015"

U-Net: Convolutional Networks for Biomedical Image Segmentation

Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

U-Net: Convolutional Networks for Biomedical Image Segmentation

Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at this http URL .

B cell antigen receptors of the IgM and IgD classes are clustered in different protein islands that are altered during B cell activation.

Abstract: The B cell antigen receptors (BCRs) play an important role in the clonal selection of B cells and their differentiation into antibody-secreting plasma cells. Mature B cells have both immunoglobulin M (IgM) and IgD types of BCRs, which have identical antigen-binding sites and are both associated with the signaling subunits Igα and Igβ, but differ in their membrane-bound heavy chain isoforms. By two-color direct stochastic optical reconstruction microscopy (dSTORM), we showed that IgM-BCRs and IgD-BCRs reside in the plasma membrane in different protein islands with average sizes of 150 and 240 nm, respectively. Upon B cell activation, the BCR protein islands became smaller and more dispersed such that the IgM-BCRs and IgD-BCRs were found in close proximity to each other. Moreover, specific stimulation of one class of BCR had minimal effects on the organization of the other. These conclusions were supported by the findings from two-marker transmission electron microscopy and proximity ligation assays. Together, these data provide evidence for a preformed multimeric organization of BCRs on the plasma membrane that is remodeled after B cell activation.

Cell segmentation and tracking in phase contrast images using graph cut with asymmetric boundary costs

Abstract: We propose a new robust, effective, and surprisingly simple approach for the segmentation of cells in phase contrast microscopy images. The key feature of our algorithm is that it strongly favors dark-to-bright transitions at the boundaries of the (arbitrarily shaped) segmentation mask. The segmentation mask can be effectively found by a fast min-cut approach. The small but essential difference to standard min-cut based approaches is that our graph contains directed edges with asymmetric edge weights. Combined with a simple region propagation our approach yields better segmentation results on the ISBI Cell Tracking Challenge 2014 dataset than the top ranked methods. We provide an easy-to-use open-source implementation for ImageJ/Fiji and Matlab on our homepage.

The polarity protein Inturned links NPHP4 to Daam1 to control the subapical actin network in multiciliated cells.

Abstract: Motile cilia polarization requires intracellular anchorage to the cytoskeleton; however, the molecular machinery that supports this process remains elusive. We report that Inturned plays a central role in coordinating the interaction between cilia-associated proteins and actin-nucleation factors. We observed that knockdown of nphp4 in multiciliated cells of the Xenopus laevis epidermis compromised ciliogenesis and directional fluid flow. Depletion of nphp4 disrupted the subapical actin layer. Comparison to the structural defects caused by inturned depletion revealed striking similarities. Furthermore, coimmunoprecipitation assays demonstrated that the two proteins interact with each other and that Inturned mediates the formation of ternary protein complexes between NPHP4 and DAAM1. Knockdown of daam1, but not formin-2, resulted in similar disruption of the subapical actin web, whereas nphp4 depletion prevented the association of Inturned with the basal bodies. Thus, Inturned appears to function as an adaptor protein that couples cilia-associated molecules to actin-modifying proteins to rearrange the local actin cytoskeleton.

The Rac1 regulator ELMO controls basal body migration and docking in multiciliated cells through interaction with Ezrin

Abstract: Cilia are microtubule-based organelles that are present on most cells and are required for normal tissue development and function. Defective cilia cause complex syndromes with multiple organ manifestations termed ciliopathies. A crucial step during ciliogenesis in multiciliated cells (MCCs) is the association of future basal bodies with the apical plasma membrane, followed by their correct spacing and planar orientation. Here, we report a novel role for ELMO-DOCK1, which is a bipartite guanine nucleotide exchange factor complex for the small GTPase Rac1, and for the membrane-cytoskeletal linker Ezrin, in regulating centriole/basal body migration, docking and spacing. Downregulation of each component results in ciliopathy-related phenotypes in zebrafish and disrupted ciliogenesis in Xenopus epidermal MCCs. Subcellular analysis revealed a striking impairment of basal body docking and spacing, which is likely to account for the observed phenotypes. These results are substantiated by showing a genetic interaction between elmo1 and ezrin b. Finally, we provide biochemical evidence that the ELMO-DOCK1-Rac1 complex influences Ezrin phosphorylation and thereby probably serves as an important molecular switch. Collectively, we demonstrate that the ELMO-Ezrin complex orchestrates ciliary basal body migration, docking and positioning in vivo.

Amotl2a interacts with the Hippo effector Yap1 and the Wnt/β-catenin effector Lef1 to control tissue size in zebrafish

Abstract: During development, proliferation must be tightly controlled for organs to reach their appropriate size. While the Hippo signaling pathway plays a major role in organ growth control, how it senses and responds to increased cell density is still unclear. In this study, we use the zebrafish lateral line primordium (LLP), a group of migrating epithelial cells that form sensory organs, to understand how tissue growth is controlled during organ formation. Loss of the cell junction-associated Motin protein Amotl2a leads to overproliferation and bigger LLP, affecting the final pattern of sensory organs. Amotl2a function in the LLP is mediated together by the Hippo pathway effector Yap1 and the Wnt/β-catenin effector Lef1. Our results implicate for the first time the Hippo pathway in size regulation in the LL system. We further provide evidence that the Hippo/Motin interaction is essential to limit tissue size during development. DOI: http://dx.doi.org/10.7554/eLife.08201.001

Spontaneous and electric field–controlled front–rear polarization of human keratinocytes

Abstract: It has long been known that electrical fields (EFs) are able to influence the direction of migrating cells, a process commonly referred to as electrotaxis or galvanotaxis. Most studies have focused on migrating cells equipped with an existing polarity before EF application, making it difficult to delineate EF-specific pathways. Here we study the initial events in front-rear organization of spreading keratinocytes to dissect the molecular requirements for random and EF-controlled polarization. We find that Arp2/3-dependent protrusive forces and Rac1/Cdc42 activity were generally required for both forms of polarization but were dispensable for controlling the direction of EF-controlled polarization. By contrast, we found a crucial role for extracellular pH as well as G protein coupled-receptor (GPCR) or purinergic signaling in the control of directionality. The normal direction of polarization toward the cathode was reverted by lowering extracellular pH. Polarization toward the anode was also seen at neutral pH when GPCR or purinergic signaling was inhibited. However, the stepwise increase of extracellular pH in this scenario led to restoration of cathodal polarization. Overall our work puts forward a model in which the EF uses distinct polarization pathways. The cathodal pathway involves GPCR/purinergic signaling and is dominant over the anodal pathway at neutral pH.

The Rac1 regulator ELMO controls basal body migration and docking in multiciliated cells through interaction with Ezrin

Abstract: Cilia are microtubule-based organelles that are present on most cells and are required for normal tissue development and function. Defective cilia cause complex syndromes with multiple organ manifestations termed ciliopathies. A crucial step during ciliogenesis in multiciliated cells (MCCs) is the association of future basal bodies with the apical plasma membrane, followed by their correct spacing and planar orientation. Here, we report a novel role for ELMO-DOCK1, which is a bipartite guanine nucleotide exchange factor complex for the small GTPase Rac1, and for the membrane-cytoskeletal linker Ezrin, in regulating centriole/basal body migration, docking and spacing. Downregulation of each component results in ciliopathy-related phenotypes in zebrafish and disrupted ciliogenesis in Xenopus epidermal MCCs. Subcellular analysis revealed a striking impairment of basal body docking and spacing, which is likely to account for the observed phenotypes. These results are substantiated by showing a genetic interaction between elmo1 and ezrin b. Finally, we provide biochemical evidence that the ELMO-DOCK1-Rac1 complex influences Ezrin phosphorylation and thereby probably serves as an important molecular switch. Collectively, we demonstrate that the ELMO-Ezrin complex orchestrates ciliary basal body migration, docking and positioning in vivo.

U-Net: Convolutional Networks for Biomedical Image Segmentation

Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .