Research project

SFB 796, TP A4: Automated multi-dimensional, high-content image-analysis for fluorescence-microscopy

For the understanding of reprogramming of host cells by microbial effectors, the analyses of microscopic images are of central importance. Often, effector-induced alterations are scored by analyses of micrographs. However, the interpretation of micrographs and especially the quantitative analyses of alterations in cellular phenotypes is an extremely repetitive and time-consuming task, prone to biased interpretation and difficult to reproduce between different laboratories. These problems define the need for novel tools for automated image analysis. In this project, we propose the research, development and exploration of novel machine vision tools and intuitive user interfaces for the automated image analysis (IA) of micrographs from conventional and confocal fluorescence microscopy. These tools will include self-learning components to train the crucial segmentation step of depicted objects. Furthermore, we will investigate rule-based analysis for the interpretation of detected objects towards an automated analysis for a range of different fluorescence-based biomedical challenges. A convenient user interface will bridge the so-called 'semantic gap' between the user and the machine, and will allow experimental scientists to define parameters for automated analysis without the need to develop scripts as required in most software currently used. The proposed project should follow two directions: A. The new IA tools will be utilized for the rapid and automated analysis of the role of microbial effectors to host cell manipulation studied by groups in the SFB. These analyses will be unbiased, leading to scoring of user-defined parameters for a large number of samples. The IA tools will be evaluated with known Salmonella-induced phenotypes such as intracellular bacterial proliferation, positioning of the pathogen-containing compartment or alteration of the cytoskeleton. After initial evaluation and possible corrections and enhancements, the IA tools will subsequently be applied to other projects demanding similar quantitative analyses, for example FRAP and FRET analyses of viral interference with STAT5 (Ensser, B1), the high-throughput analyses of viral genome replication in the nucleus of host cells (Stamminger, B3), or the imaging-based quantification of secretory blocks in plant cells by bacterial effectors (Börnke, C5). B. The IA tools will be developed towards broader application in cell biology and cellular microbiology. The self-learning approach for image segmentation together with the rule-based analysis should enable a reproducible, objective, automated image analysis after of a short period of defining parameters and training. Future additions should lead to the automated control of microscopy to enable 'seek and find' operations of user-defined phenotypes.

Project manager:
PD Dr.-Ing. Thomas Wittenberg

Project participants:
Christian Held, Veit Wiesmann, Franz Daniela, Dach Claudia

Keywords:
fluorescence microscopy; image segmentation; optimization

Duration: 1.1.2009 - 31.12.2016

Sponsored by:
Deutsche Forschungsgemeinschaft

Mitwirkende Institutionen:
Fraunhofer Institut für Integrierte Schaltungen IIS

Contact:
Wittenberg, Thomas
Phone 09131/85-25396, Fax 09131/85-29931, E-Mail: thomas.wittenberg@fau.de

Publications

Held, Christian ; Nattkemper, Tim ; Palmisano, Ralf ; Wittenberg, Thomas: Approaches to automatic parameter fitting in a microscopy image segmentation pipeline: An exploratory parameter space analysis. In: J Pathol Inform 4 (2013), No. 5
[doi>10.4103/2153-3539.109831]

Held, Christian ; Wenzel, Jens ; Wiesmann, Veit ; Palmisano, Ralf ; Lang, Roland ; Wittenberg, Thomas: Enhancing automated micrograph-based evaluation of LPS-stimulated macrophage spreading. In: Cytometry A 83 (2013), No. 4, pp 409-18
[doi>10.1002/cyto.a.22248]

Wiesmann, Veit ; Sauer, Tobias ; Held, Christian ; Palmisano, Ralf ; Wittenberg, Thomas: Cell Simulation for Validation of Cell Micrograph Evaluation Algorithms. In: DGBMT ; Dössel, Olaf (Ed.) : Biomedical Engineering / Biomedizinische Technik. (Biomedical Engineering / Biomedizinische Technik. Graz 19.-21.9.2013). Vol. 58 (Suppl. 1). Berlin : DeGruyter, 2013, pp online. (Biomedical Engineering / Biomedizinische Technik.)

Franz, Daniela ; Wiesmann, Veit ; Stamminger, Marc ; Wittenberg, Thomas: Cell-Shape Wizard – A Concept for User-Guidance for Active Shape Segmentation in Fluorescence Cell Micrographs. In: Biomedical Engineering / Biomedizinische Technik 59 (2014), No. s1, pp 877-880

Wiesmann, Veit ; Bergler, Matthias ; Palmisano, Ralf ; Prinzen, Martin ; Franz, Daniela ; Wittenberg, Thomas: Enhanced Fluorescent Cell Simulation using Texture Mapping and Statistical Shape Model. In: Biomedical Engineering / Biomedizinische Technik 59 (2014), No. s1, pp S964-S967

Franz, Daniela ; Hofer, Mathias ; Pfeifle, Matthias ; Pirlich, Markus ; Stamminger, Marc ; Wittenberg, Thomas: A Wizard-Based Segmentation Approach for Cochlear Implant Planning. In: BVM (Ed.) : Informatik Aktuell (Bildverarbeitung für die Medizin Aachen 16.-18.3.2014). Heidelberg : Springer, 2014, pp 258-263.

Krappe, Sebastian ; Benz, Michaela ; Wittenberg, Thomas ; Haferlach, Torsten ; Münzenmayer, Christian: Automated classification of bone marrow cells in microscopic images for diagnosis of leukemia: A comparison of two classification schemes with respect to the segmentation quality. In: Proc. SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis (Ed.) : Proc. SPIE 9414, (Medical Imaging 2015: Computer-Aided Diagnosis Orlando Feb. 21 - 26, 2015). Vol. 9414. 2015. - ISBN 9781628415049
[doi>10.1117/12.2081946]

Wiesmann, Veit ; Reimer, Dorothea ; Franz, Daniela ; Hüttmayer, Hanna ; Mielenz, Dirk ; Wittenberg, Thomas: Automated high-throughput analysis of B cell spreading on immobilized antibodies with whole slide imaging. In: Current Directions in Biomedical Engineering (2015), No. 1, pp 224–227
[doi>10.1515/CDBME-2015-0056]

Krappe, Sebastian# ; Münzenmayer, Christian ; Evert, Amrei ; Koyuncu, Can ; Cetin, Enis ; Haferlach, Torsten ; Wittenberg, Thomas ; Held, Christian: Dynamic programming for the segmentation of bone marrow cells. In: Handels, Heinz ; Deserno, Thomas ; Meinzer, Hans-Peter ; Tolxdorff, Thomas (Ed.) : Bildverarbeitung für die Medizin 2015 (Bildverarbeitung für die Medizin 2015 Lübeck 15.-17.3.2015). Heidelberg : Springer, 2015, pp 359-364. (Informatik Aktuell) - ISBN 978-3-662-46223-2
[doi>10.1007/978-3-662-46224-9_62]

Franz, Daniela ; Syré, Liane ; Bischoff, Barbara ; Hastreiter, Peter ; Wittenberg, Thomas: Preoperative Planning of Neurovascular Compression Syndrome Surgery based on an Interactive Wizard-Based Segmentation Approach – Extended Evaluation Results. In: Hahn, Horst K. ; Kikinis, Ron ; Klein, Jan ; Nabavi, Arya ; Weber, Stefan (Ed.) : 2015 CURAC -Tagungsband (14. Jahrestagung der Deutschen Gesellschaft für Computer- und Roboterassistierte Chirurgie e.V. Bremen 17.-19.9.2015). 1. Edition 2015, pp 295-200. - ISBN 978-3-00-050359-7

Wiesmann, Veit ; Franz, Daniela ; Held, Christian ; Münzenmayer, Christian ; Palmisano, Ralf ; Wittenberg, Thomas: Review of free software tools for image analysis of fluorescence cell micrographs. In: Journal of Microscopy (2015), No. 257, pp 39–53
[doi>10.1111/jmi.12184]

Franz, Daniela ; Huettmayer, Hanna ; Stamminger, Marc ; Wiesmann, Veit ; Wittenberg, Thomas: The Cell-Shape-Wizard - User Guidance for Active Contour-based Cell Segmentation. In: BVM (Ed.) : Bildverarbeitung in der Medizin (BVM 2015 Lübeck 15.-17.03.2015). 2015, pp to appear.

Franz, Daniela ; Syré, Liane ; Paulus, Dietrich ; Bischoff, Barbara ; Wittenberg, Thomas ; Hastreiter, Peter: The SIP-NVC-Wizard. In: Handels, Heinz ; Deserno, Thomas ; Meinzer, Hans-Peter ; Tolxdorff, Thomas (Ed.) : Bildverarbeitung für die Medizin 2015 (Bildverarbeitung für die Medizin 2015 Lübeck 15.-17.3.2015). Heidelberg : Springer, 2015, pp 65-70. (Informatik Aktuell) - ISBN 978-3-662-46223-2
[doi>10.1007/978-3-662-46224-9_13]