Christoph Sommer

Ilastik: Interactive learning and segmentation toolkit

Segmentation is the process of partitioning digital images into meaningful regions. The analysis of biological high content images often requires segmentation as a first step. We propose ilastik as an easy-to-use tool which allows the user without expertise in image processing to perform segmentation and classification in a unified way. ilastik learns from labels provided by the user through a convenient mouse interface. Based on these labels, ilastik infers a problem specific segmentation. A random forest classifier is used in the learning step, in which each pixels neighborhood is characterized by a set of generic (nonlinear) features. ilastik supports up to three spatial plus one spectral dimension and makes use of all dimensions in the feature calculation. ilastik provides realtime feedback that enables the user to interactively refine the segmentation result and hence further fine-tune the classifier. An uncertainty measure guides the user to ambiguous regions in the images. Real time performance is achieved by multi-threading which fully exploits the capabilities of modern multi-core machines. Once a classifier has been trained on a set of representative images, it can be exported and used to automatically process a very large number of images (e.g. using the CellProfiler pipeline). ilastik is an open source project and released under the BSD license at www.ilastik.org.

Fluorogenic probes for live-cell imaging of the cytoskeleton

We introduce far-red, fluorogenic probes that combine minimal cytotoxicity with excellent brightness and photostability for fluorescence imaging of actin and tubulin in living cells. Applied in stimulated emission depletion (STED) microscopy, they reveal the ninefold symmetry of the centrosome and the spatial organization of actin in the axon of cultured rat neurons with a resolution unprecedented for imaging cytoskeletal structures in living cells.

Visualizing a Homogeneous Blend in Bulk Heterojunction Polymer Solar Cells by Analytical Electron Microscopy

To increase efficiency of bulk heterojunctions for photovoltaic devices, the functional morphology of active layers has to be understood, requiring visualization and discrimination of materials with very similar characteristics. Here we combine high-resolution spectroscopic imaging using an analytical transmission electron microscope with nonlinear multivariate statistical analysis for classification of multispectral image data. We obtain a visual representation showing homogeneous phases of donor and acceptor, connected by a third composite phase, depending in its extent on the way the heterojunction is fabricated. For the first time we can correlate variations in nanoscale morphology determined by material contrast with measured solar cell efficiency. In particular we visualize a homogeneously blended phase, previously discussed to diminish charge separation in solar cell devices.

Automated Detection and Segmentation of Synaptic Contacts in Nearly Isotropic Serial Electron Microscopy Images

We describe a protocol for fully automated detection and segmentation of asymmetric, presumed excitatory, synapses in serial electron microscopy images of the adult mammalian cerebral cortex, taken with the focused ion beam, scanning electron microscope (FIB/SEM). The procedure is based on interactive machine learning and only requires a few labeled synapses for training. The statistical learning is performed on geometrical features of 3D neighborhoods of each voxel and can fully exploit the high z-resolution of the data. On a quantitative validation dataset of 111 synapses in 409 images of 1948×1342 pixels with manual annotations by three independent experts the error rate of the algorithm was found to be comparable to that of the experts (0.92 recall at 0.89 precision). Our software offers a convenient interface for labeling the training data and the possibility to visualize and proofread the results in 3D. The source code, the test dataset and the ground truth annotation are freely available on the website http://www.ilastik.org/synapse-detection.

From experimental setup to bioinformatics: An RNAi screening platform to identify host factors involved in HIV-1 replication

RNA interference (RNAi) has emerged as a powerful technique for studying loss‐of‐function phenotypes by specific down‐regulation of gene expression, allowing the investigation of virus‐host interactions by large‐scale high‐throughput RNAi screens. Here we present a robust and sensitive small interfering RNA screening platform consisting of an experimental setup, single‐cell image and statistical analysis as well as bioinformatics. The workflow has been established to elucidate host gene functions exploited by viruses, monitoring both suppression and enhancement of viral replication simultaneously by fluorescence microscopy. The platform comprises a two‐stage procedure in which potential host factors are first identified in a primary screen and afterwards re‐tested in a validation screen to confirm true positive hits. Subsequent bioinformatics allows the identification of cellular genes participating in metabolic pathways and cellular networks utilised by viruses for efficient infection. Our workflow has been used to investigate host factor usage by the human immunodeficiency virus‐1 (HIV‐1), but can also be adapted to other viruses. Importantly, we expect that the description of the platform will guide further screening approaches for virus‐host interactions. The ViroQuant‐CellNetworks RNAi Screening core facility is an integral part of the recently founded BioQuant centre for systems biology at the University of Heidelberg and will provide service to external users in the near future.

Efficacy and mechanism of action of volasertib, a potent and selective inhibitor of Polo-like kinases, in preclinical models of acute myeloid leukemia

Polo-like kinase 1 (Plk1), a member of the Polo-like kinase family of serine/threonine kinases, is a key regulator of multiple steps in mitosis. Here we report on the pharmacological profile of volasertib, a potent and selective Plk inhibitor, in multiple preclinical models of acute myeloid leukemia (AML) including established cell lines, bone marrow samples from AML patients in short-term culture, and subcutaneous as well as disseminated in vivo models in immune-deficient mice. Our results indicate that volasertib is highly efficacious as a single agent and in combination with established and emerging AML drugs, including the antimetabolite cytarabine, hypomethylating agents (decitabine, azacitidine), and quizartinib, a signal transduction inhibitor targeting FLT3. Collectively, these preclinical data support the use of volasertib as a new therapeutic approach for the treatment of AML patients, and provide a foundation for combination approaches that may further improve and prolong clinical responses.

Automated segmentation of synapses in 3D EM data

This contribution presents a method for automatic detection of excitatory, asymmetric synapses and segmentation of synaptic junctional complexes in stacks of serial electron microscopy images with nearly isotropic resolution. The method uses a Random Forest classifier in the space of generic image features, computed directly in the 3D neighborhoods of each pixel, and an additional step of interactive probability maps thresholding. On the test dataset, the algorithm missed considerably less synapses than the human expert during the ground truth creation, while maintaining an equivalent false positive rate. The algorithm is implemented as an extension to the Interactive Learning and Segmentation Toolkit “ilastik” and is freely available on our website (www.ilastik.org/synapse-detection).

Learning of optimal illumination for material classification

We present a method to classify materials in illumination series data. An illumination series is acquired using a device which is capable to generate arbitrary lighting environments covering nearly the whole space of the upper hemisphere. The individual images of the illumination series span a high-dimensional feature space. Using a random forest classifier different materials, which vary in appearance (which itself depends on the patterns of incoming illumination), can be distinguished reliably. The associated Gini feature importance allows for determining the features which are most relevant for the classification result. By linking the features to illumination patterns a proposition about optimal lighting for defect detection can be made, which yields valuable information for the selection and placement of light sources.

A Framework for Interactive Visualization and Classification of Dynamical Processes at the Water Surface

A framework for the visualization and classification of multi-channel spatio-temporal data from water wave imaging is presented. Our interactive visualization tool, WaveVis, allows a detailed study of the water surface shape in reference to additional data streams, like thermographic images or classification results. This facilitates an intuitive and effective inspection of huge amounts of data. WaveVis was used to select representative training examples of events for a supervised learning approach and to evaluate the results of the classification. The interactive classification and segmentation software ilastik was used to train a Random Forest classifier. The benefit of the combination of both programs is demonstrated for two applications, the estimation of the rain rate from the segmentation of impact craters, and the detection of small scale breaking waves. The classification of the impact crater of raindrops on the water surface worked very well, whereas the detection of the breaking waves was satisfactory only under certain experimental conditions. Nevertheless, the combination of WaveVis and ilastik proved to be valuable in both cases.

Interactive Learning for the Analysis of Biomedical and Industrial Imagery

In der vorliegenden Dissertation werden Methoden des uberwachten Lernens untersucht und auf die Analyse und die Segmentierung digitaler Bilddaten angewendet, die aus diversen Forschungsgebieten stammen. Die Segmentierung und die Klassifikation spielen eine wichtige Rolle in der biomedizinischen und industriellen Bildverarbeitung, haufig basiert darauf weitere Erkennung und Quantifikation. Viele problemspezifische Ansatze existieren fur die unterschiedlichsten Fragestellungen und nutzen meist spezifisches Vorwissen aus den jeweiligen Bilddaten aus. In dieser Arbeit wird ein uberwachtes Lernverfahren vorgestellt, das mehrere Objekte und deren Klassen gleichzeitig segmentieren und unterscheiden kann. Die Methode ist generell genug um einen wichtigen Bereich von Anwendungen abzudecken, fur deren Losung lokale Merkmale eine Rolle spielen. Segmentierungsergebnisse dieses Ansatzes werden auf verschiedenen Datensatzen mit unterschiedlichen Problemstellungen gezeigt. Die Resultate unterstreichen die Anwendbarkeit der Lernmethode fur viele biomedizinische und industrielle Anwendungen, ohne dass explizite Kenntnisse der Bildverarbeitung und Programmierung vorausgesetzt werden mussen. Der Ansatz basiert auf generellen Merkmalsklassen, die es erlauben lokal Strukturen wie Farbe, Textur und Kanten zu beschreiben. Zu diesem Zweck wurde eine interaktive Software implementiert, welche, fur gewohnliche Bildgrosen, in Echtzeit arbeitet und es somit einem Domanenexperten erlaubt Segmentierungs- und Klassifikationsaufgaben interaktiv zu bearbeiten. Dafur sind keine Kenntnisse in der Bildverarbeitung notig, da sich die Benutzerinteraktion auf intuitives Markieren mit einem Pinselwerkzeug beschrankt. Das interaktiv trainierte System kann dann ohne weitere Benutzerinteraktion auf viele neue Bilder angewendet werden. Der Ansatz ist auf Segmentierungsprobleme beschrankt, fur deren Losung lokale diskriminative Merkmale ausreichen. Innerhalb dieser Einschrankung zeigt der Algorithmus jedoch erstaunlich gute Resultate, die in einer applikationsspezifischen Prozedur weiter verbessert werden konnen. Das Verfahren unterstutzt bis zu vierdimensionale, multispektrale Bilddaten in vereinheitlichter Weise. Um die Anwendbar- und Ubertragbarkeit der Methode weiter zu illustrieren wurden mehrere echte Anwendungsfalle, kommend aus verschiedenen bildgebenden Bereichen, untersucht. Darunter sind u. A. die Segmentierung von Tumorgewebe, aufgenommen mittelsWeitfeldmikroskopie, die Quantifikation von Zellwanderungen in konfokalmikroskopischen Aufnahmen fur die Untersuchung der adulten Neurogenese, die Segmentierung von Blutgefasen in der Retina des Auges, das Verfolgen von Kupferdrahten in einer Anwendung zur Produktauthentifikation und die Qualitatskontrolle von Mikroskopiebildern im Kontext von Hochdurchsatz-Experimenten. Desweiteren wurde eine neue Klassifikationsmethode basierend auf globalen Frequenzschatzungen fur die Prozesskontrolle des Papieranlegers an Druckmaschinen entwickelt.