Centre for Biological Signalling Studies

Dr. Thorsten Falk

Dr. Thorsten Falk

Department of Computer Sciences
Core Facility Image Analysis

+49 761 203 8274

The Image Analysis Lab provides latest research in image processing, pattern recognition and machine learning to partners from biology and medicine. In close cooperation with the Computer Vision Lab of Prof. Brox we try to teach the computer to see and understand visual patterns in bio-medical image data on scales ranging from centimeters to nanometers in 2D, 3D and over time. For this we employ and adapt classical ideas from image processing and pattern recognition and combine them with learning approaches like deep neural networks. Our challenge is to transfer state-of-the art image analysis to intuitive and general end-to-end-solutions that do not require consultation of experts in computer science.

We complement integrative high-throughput experiments, by employing the spatio-temporal context, allowing cell-accurate localization of organelles, gene activation patterns, proteins or distinction of subtle phenotypes on cellular, organ and organism scale. Mapping recorded images to virtual atlases enables comparison of different individuals or populations. Additionally, we research on fundamental building blocks for image processing pipelines including image alignment (registration), enhancement (high dynamic range fusion, deconvolution, attenuation correction, ...), segmentation and classification.


10 selected publications:

  • U-Net: deep learning for cell counting, detection, and morphometry.
    Falk T, Mai D, Bensch R, Çiçek Ö, Abdulkadir A, Marrakchi Y, Böhm A, Deubner J, Jäckel Z, Seiwald K, Dovzhenko A, Tietz O, Dal Bosco C, Walsh S, Saltukoglu D, Tay TL, Prinz M, Palme K, Simons M, Diester I, Brox T, Ronneberger O.
    Nat Methods. 2019 Jan;16(1):67-70.
  • ISOO_DL: Instance segmentation of overlapping biological objects using deep learning.
    Böhm A, Ücker A, Jäger T, Ronneberger O, Falk T.
    Proc Of ISBI, 2018, 1225–1229.
  • A 3D digital atlas of the Nicotiana tabacum root tip and its use to investigate changes in the root apical meristem induced by the Agrobacterium 6b oncogene.
    Pasternak T, Haser T, Falk T, Ronneberger O, Palme K, Otten L.
    Plant J. 2017 Oct;92(1):31-42.
  • From Voxels to Models – Towards quantification in 3-D confocal microscopy.
    Falk T.
    Dissertation, Albert-Ludwigs-Universität Freiburg i. Brsg., 2016.
  • The iRoCS Toolbox – 3D analysis of the plant root apical meristem at cellular resolution.
    Schmidt T, Pasternak T, Liu K, Blein T, Aubry-Hivet D, Dovzhenko A, Duerr J, Teale W, Ditengou FA, Burkhardt H, Ronneberger O, Palme K.
    Plant J 2014; 77(5), 806–814.
  • Rotation-Invariant HOG Descriptors using Fourier Analysis in Polar and Spherical Coordinates.
    Liu K, Skibbe H, Schmidt T, Blein T, Palme K, Brox T, Ronneberger O.
    IJCV 2014;106(3),342–364.
  • Variational attenuation correction in two-view confocal microscopy.
    Schmidt T, Dürr J, Keuper M, Blein T, Palme K, Ronneberger O.
    BMC Bioinformatics. 2013 Dec 18;14:366.
  • Fast Rotation Invariant 3D Feature Computation utilizing Efficient Local Neighborhood Operators.
    Skibbe H, Reisert M, Schmidt T, Brox T, Ronneberger O, Burkhardt H.
    IEEE Trans Pattern Anal Mach Intell.
    2012 Aug;34(8):1563-75.
  • ViBE-Z: A Framework for 3D Virtual Colocalization Analysis in Zebrafish Larval Brains.
    Ronneberger O, Liu K, Rath M, Rueβ D, Mueller T, Skibbe H, Drayer B, Schmidt T, Filippi A, Nitschke R, Brox T, Burkhardt H, Driever W.
    Nat Methods. 2012 Jun 17;9(7):735-42.
  • Inversin relays Frizzled-8 signals to promote proximal pronephros development.
    Lienkamp S, Ganner A, Boehlke C, Schmidt T, Arnold SJ, Schäfer T, Romaker D, Schuler J, Hoff S, Powelske C, Eifler A, Krönig C, Bullerkotte A, Nitschke R, Kuehn EW, Kim E, Burkhardt H, Brox T, Ronneberger O, Gloy J, Walz G.
    Proc Natl Acad Sci U S A. 2010 Nov 23;107(47):20388-93