Verena Kaynig

Fiji: an open-source platform for biological-image analysis

Fiji is a distribution of the popular open-source software ImageJ focused on biological-image analysis. Fiji uses modern software engineering practices to combine powerful software libraries with a broad range of scripting languages to enable rapid prototyping of image-processing algorithms. Fiji facilitates the transformation of new algorithms into ImageJ plugins that can be shared with end users through an integrated update system. We propose Fiji as a platform for productive collaboration between computer science and biology research communities.

Saturated Reconstruction of a Volume of Neocortex

We describe automated technologies to probe the structure of neural tissue at nanometer resolution and use them to generate a saturated reconstruction of a sub-volume of mouse neocortex in which all cellular objects (axons, dendrites, and glia) and many sub-cellular components (synapses, synaptic vesicles, spines, spine apparati, postsynaptic densities, and mitochondria) are rendered and itemized in a database. We explore these data to study physical properties of brain tissue. For example, by tracing the trajectories of all excitatory axons and noting their juxtapositions, both synaptic and non-synaptic, with every dendritic spine we refute the idea that physical proximity is sufficient to predict synaptic connectivity (the so-called Peters rule). This online minable database provides general access to the intrinsic complexity of the neocortex and enables further data-driven inquiries.

Neuron geometry extraction by perceptual grouping in ssTEM images

In the field of neuroanatomy, automatic segmentation of electron microscopy images is becoming one of the main limiting factors in getting new insights into the functional structure of the brain. We propose a novel framework for the segmentation of thin elongated structures like membranes in a neuroanatomy setting. The probability output of a random forest classifier is used in a regular cost function, which enforces gap completion via perceptual grouping constraints. The global solution is efficiently found by graph cut optimization. We demonstrate substantial qualitative and quantitative improvement over state-of the art segmentations on two considerably different stacks of ssTEM images as well as in segmentations of streets in satellite imagery. We demonstrate that the superior performance of our method yields fully automatic 3D reconstructions of dendrites from ssTEM data.

Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification

Summary: State‐of‐the‐art light and electron microscopes are capable of acquiring large image datasets, but quantitatively evaluating the data often involves manually annotating structures of interest. This process is time‐consuming and often a major bottleneck in the evaluation pipeline. To overcome this problem, we have introduced the Trainable Weka Segmentation (TWS), a machine learning tool that leverages a limited number of manual annotations in order to train a classifier and segment the remaining data automatically. In addition, TWS can provide unsupervised segmentation learning schemes (clustering) and can be customized to employ user‐designed image features or classifiers. Availability and Implementation: TWS is distributed as open‐source software as part of the Fiji image processing distribution of ImageJ at http://imagej.net/Trainable_Weka_Segmentation. Contact: ignacio.arganda@ehu.eus Supplementary information: Supplementary data are available at Bioinformatics online.

Large-scale automatic reconstruction of neuronal processes from electron microscopy images.

Automated sample preparation and electron microscopy enables acquisition of very large image data sets. These technical advances are of special importance to the field of neuroanatomy, as 3D reconstructions of neuronal processes at the nm scale can provide new insight into the fine grained structure of the brain. Segmentation of large-scale electron microscopy data is the main bottleneck in the analysis of these data sets. In this paper we present a pipeline that provides state-of-the art reconstruction performance while scaling to data sets in the GB-TB range. First, we train a random forest classifier on interactive sparse user annotations. The classifier output is combined with an anisotropic smoothing prior in a Conditional Random Field framework to generate multiple segmentation hypotheses per image. These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion. We provide qualitative and quantitative evaluation of the automatic segmentation and demonstrate large-scale 3D reconstructions of neuronal processes from a 27,000 μm(3) volume of brain tissue over a cube of 30 μm in each dimension corresponding to 1000 consecutive image sections. We also introduce Mojo, a proofreading tool including semi-automated correction of merge errors based on sparse user scribbles.

Fully automatic stitching and distortion correction of transmission electron microscope images

In electron microscopy, a large field of view is commonly captured by taking several images of a sample region and then by stitching these images together. Non-linear lens distortions induced by the electromagnetic lenses of the microscope render a seamless stitching with linear transformations impossible. This problem is aggravated by large CCD cameras, as they are commonly in use nowadays. We propose a new calibration method based on ridge regression that compensates non-linear lens distortions, while ensuring that the geometry of the image is preserved. Our method estimates the distortion correction from overlapping image areas using automatically extracted correspondence points. Therefore, the estimation of the correction transform does not require any special calibration samples. We evaluate our method on simulated ground truth data as well as on real electron microscopy data. Our experiments demonstrate that the lens calibration robustly corrects large distortions with an average stitching error exceeding 10 pixels to sub-pixel accuracy within two iteration steps.

Geometrical consistent 3D tracing of neuronal processes in ssTEM data

In neuroanatomy, automatic geometry extraction of neurons from electron microscopy images is becoming one of the main limiting factors in getting new insights into the functional structure of the brain. We propose a novel framework for tracing neuronal processes over serial sections for 3d reconstructions. The automatic processing pipeline combines the probabilistic output of a random forest classifier with geometrical consistency constraints which take the geometry of whole sections into account. Our experiments demonstrate significant improvement over grouping by Euclidean distance, reducing the split and merge error per object by a factor of two.

Probabilistic image registration and anomaly detection by nonlinear warping

Automatic, defect tolerant registration of transmission electron microscopy (TEM) images poses an important and challenging problem for biomedical image analysis, e.g. in computational neuroanatomy. In this paper we demonstrate a fully automatic stitching and distortion correction method for TEM images and propose a probabilistic approach for image registration. The technique identifies image defects due to sample preparation and image acquisition by outlier detection. A polynomial kernel expansion is used to estimate a non-linear image transformation based on intensities and spatial features. Corresponding points in the images are not determined beforehand, but they are estimated via an EM-algorithm during the registration process which is preferable in the case of (noisy) TEM images. Our registration model is successfully applied to two large image stacks of serial section TEM images acquired from brain tissue samples in a computational neuroanatomy project and shows significant improvement over existing image registration methods on these large datasets.

Visualization in Connectomics

Connectomics is a branch of neuroscience that attempts to create a connectome, i.e., a complete map of the neuronal system and all connections between neuronal structures. This representation can be used to understand how functional brain states emerge from their underlying anatomical structures and how dysfunction and neuronal diseases arise. We review the current state-of-the-art of visualization and image processing techniques in the field of connectomics and describe a number of challenges. After a brief summary of the biological background and an overview of relevant imaging modalities, we review current techniques to extract connectivity information from image data at macro-, meso- and microscales. We also discuss data integration and neural network modeling, as well as the visualization, analysis and comparison of brain networks.

Imaging a 1 mm 3 Volume of Rat Cortex Using a MultiBeam SEM

The rodent brain is organized with length scales spanning centimeters to nanometers --6 orders of magnitude [1]. At the centimeter scale, the brain consist of lobes of cortex, the cerebellum, the brainstem and the spinal cord. The millimeter scale have neurons arranged in columns, layers, or otherwise clustered. Recent technological imaging advances allow the generation of neuronal datasets spanning the spatial range from nanometers to 100s of microns [2,3]. Collecting a 1 mm volume dataset of brain tissue at 4 nm x-y resolution using the fastest signal-beam SEM would require ~6 years. To move to the next length and volume scale of neuronal circuits requires several technological advances. The multibeam scanning electron microscope (mSEM) represents a transformative imaging technology that enables neuroscientists to tackle millimeter scale cortical circuit problems. In this work we describe a workflow from tissue harvest to imaging that will generate a 2 petabyte dataset (> 300,000,000 images) of rat visual cortex imaged at a 4nm x 4nm x-y (Nyquist sampling of membranes) and 30nm section thickness in less than 6 months.