Anna Kreshuk

Last updated

Anna Kreshuk
Alma mater
Known for Ilastik
Scientific career
Fields
Institutions
Thesis Automated Analysis of Biomedical Data from Low to High Resolution  (2012)
Doctoral advisor Fred Hamprecht
Website Kreshuk Lab

Anna Kreshuk is a group leader at the European Molecular Biology Laboratory in Heidelberg, Germany. She joined the Cell Biology and Biophysics Unit in July 2018, where her group employs machine learning to develop automated methods to help biologists speed up image analysis. [1] [2]

Contents

Education

Kreshuk studied mathematics at the Lomonosov Moscow State University, finishing with a diploma in 2003. Before starting her Ph.D. studies, Kreshuk worked at CERN (2004–2007) [3] [4] [5] and the GSI Helmholtz Centre for Heavy Ion Research (2007–2008) as a scientific programmer. From 2008 to 2011, she earned her Ph.D. in computer science, working at the Heidelberg Collaboratory for Image Processing (HCI) at the Heidelberg University, supervised by Prof Dr Fred Hamprecht. [6]

Career and research

From 2012 to 2018, Kreshuk was employed at the Heidelberg Collaboratory for Image Processing (HCI) at the Heidelberg University, while pursuing her postgraduate studies. [7] [8]

Since 2018, Kreshuk has been a group leader at the European Molecular Biology Laboratory in Heidelberg, Germany. [1]

Her research group has developed a toolkit for interactive learning and segmentation (Ilastik) to bring machine learning-based methods to members of the life science community without computer vision expertise. [9] [10] [11]

Ilastik's algorithms are versatile and user-friendly, capable of addressing a broad range of image analysis issues. However, complex bioimage datasets often necessitate a more customized approach. Therefore, Kreshuk's team is especially focused on resolving intricate segmentation problems for 3D and large-scale light microscopy or electron microscopy (LM or EM). Recently, they've crafted techniques and tools for segmenting all cells and nuclei in a juvenile worm of the species Platynereis dumerilii (EM), [12] as well as in various plant organs and tissues (LM). [13]

Kreshuk is a well-known computer scientist. Hence, she is frequently invited to workshops, [14] seminars, [15]

Awards and honours

Related Research Articles

<span class="mw-page-title-main">Scanning electron microscope</span> Electron microscope where a small beam is scanned across a sample

A scanning electron microscope (SEM) is a type of electron microscope that produces images of a sample by scanning the surface with a focused beam of electrons. The electrons interact with atoms in the sample, producing various signals that contain information about the surface topography and composition of the sample. The electron beam is scanned in a raster scan pattern, and the position of the beam is combined with the intensity of the detected signal to produce an image. In the most common SEM mode, secondary electrons emitted by atoms excited by the electron beam are detected using a secondary electron detector. The number of secondary electrons that can be detected, and thus the signal intensity, depends, among other things, on specimen topography. Some SEMs can achieve resolutions better than 1 nanometer.

<span class="mw-page-title-main">Structural biology</span> Study of molecular structures in biology

Structural biology, as defined by the Journal of Structural Biology, deals with structural analysis of living material at every level of organization. Early structural biologists throughout the 19th and early 20th centuries were primarily only able to study structures to the limit of the naked eye's visual acuity and through magnifying glasses and light microscopes.

Image analysis or imagery analysis is the extraction of meaningful information from images; mainly from digital images by means of digital image processing techniques. Image analysis tasks can be as simple as reading bar coded tags or as sophisticated as identifying a person from their face.

<span class="mw-page-title-main">X-ray microscope</span> Type of microscope that uses X-rays

An X-ray microscope uses electromagnetic radiation in the X-ray band to produce magnified images of objects. Since X-rays penetrate most objects, there is no need to specially prepare them for X-ray microscopy observations.

<span class="mw-page-title-main">Transmission electron cryomicroscopy</span>

Transmission electron cryomicroscopy (CryoTEM), commonly known as cryo-EM, is a form of cryogenic electron microscopy, more specifically a type of transmission electron microscopy (TEM) where the sample is studied at cryogenic temperatures. Cryo-EM, specifically 3-dimensional electron microscopy (3DEM), is gaining popularity in structural biology.

Jason Swedlow is an American-born cell biologist and light microscopist who is Professor of Quantitative Cell Biology at the School of Life Sciences, University of Dundee, Scotland. He is a co-founder of the Open Microscopy Environment and Glencoe Software. In 2021, he joined Wellcome Leap as a Program Director.

Connectomics is the production and study of connectomes: comprehensive maps of connections within an organism's nervous system. More generally, it can be thought of as the study of neuronal wiring diagrams with a focus on how structural connectivity, individual synapses, cellular morphology, and cellular ultrastructure contribute to the make up of a network. The nervous system is a network made of billions of connections and these connections are responsible for our thoughts, emotions, actions, memories, function and dysfunction. Therefore, the study of connectomics aims to advance our understanding of mental health and cognition by understanding how cells in the nervous system are connected and communicate. Because these structures are extremely complex, methods within this field use a high-throughput application of functional and structural neural imaging, most commonly magnetic resonance imaging (MRI), electron microscopy, and histological techniques in order to increase the speed, efficiency, and resolution of these nervous system maps. To date, tens of large scale datasets have been collected spanning the nervous system including the various areas of cortex, cerebellum, the retina, the peripheral nervous system and neuromuscular junctions.

Bioimage informatics is a subfield of bioinformatics and computational biology. It focuses on the use of computational techniques to analyze bioimages, especially cellular and molecular images, at large scale and high throughput. The goal is to obtain useful knowledge out of complicated and heterogeneous image and related metadata.

<span class="mw-page-title-main">Vertico spatially modulated illumination</span>

Vertico spatially modulated illumination (Vertico-SMI) is the fastest light microscope for the 3D analysis of complete cells in the nanometer range. It is based on two technologies developed in 1996, SMI and SPDM. The effective optical resolution of this optical nanoscope has reached the vicinity of 5 nm in 2D and 40 nm in 3D, greatly surpassing the λ/2 resolution limit applying to standard microscopy using transmission or reflection of natural light according to the Abbe resolution limit That limit had been determined by Ernst Abbe in 1873 and governs the achievable resolution limit of microscopes using conventional techniques.

Biology data visualization is a branch of bioinformatics concerned with the application of computer graphics, scientific visualization, and information visualization to different areas of the life sciences. This includes visualization of sequences, genomes, alignments, phylogenies, macromolecular structures, systems biology, microscopy, and magnetic resonance imaging data. Software tools used for visualizing biological data range from simple, standalone programs to complex, integrated systems.

Serial block-face scanning electron microscopy is a method to generate high resolution three-dimensional images from small samples. The technique was developed for brain tissue, but it is widely applicable for any biological samples. A serial block-face scanning electron microscope consists of an ultramicrotome mounted inside the vacuum chamber of a scanning electron microscope. Samples are prepared by methods similar to that in transmission electron microscopy (TEM), typically by fixing the sample with aldehyde, staining with heavy metals such as osmium and uranium then embedding in an epoxy resin. The surface of the block of resin-embedded sample is imaged by detection of back-scattered electrons. Following imaging the ultramicrotome is used to cut a thin section from the face of the block. After the section is cut, the sample block is raised back to the focal plane and imaged again. This sequence of sample imaging, section cutting and block raising can acquire many thousands of images in perfect alignment in an automated fashion. Practical serial block-face scanning electron microscopy was invented in 2004 by Winfried Denk at the Max-Planck-Institute in Heidelberg and is commercially available from Gatan Inc., Thermo Fisher Scientific (VolumeScope) and ConnectomX.

<span class="mw-page-title-main">Robert F. Murphy (computational biologist)</span>

Robert F. Murphy is Ray and Stephanie Lane Professor of Computational Biology Emeritus and Director of the M.S. Program in Automated Science at Carnegie Mellon University. Prior to his retirement in May 2021, he was the Ray and Stephanie Lane Professor of Computational Biology as well as Professor of Biological Sciences, Biomedical Engineering, and Machine Learning. He was founding Director of the Center for Bioimage Informatics at Carnegie Mellon and founded the Joint CMU-Pitt Ph.D. Program in Computational Biology. He also founded the Computational Biology Department at Carnegie Mellon University and served as its head from 2009 to 2020.

<span class="mw-page-title-main">IMOD (software)</span>

IMOD is an open-source, cross-platform suite of modeling, display and image processing programs used for 3D reconstruction and modeling of microscopy images with a special emphasis on electron microscopy data. IMOD has been used across a range of scales from macromolecule structures to organelles to whole cells and can also be used for optical sections. IMOD includes tools for image reconstruction, image segmentation, 3D mesh modeling and analysis of 2D and 3D data.

<span class="mw-page-title-main">Amira (software)</span> Software platform for 3D and 4D data visualization

Amira is a software platform for visualization, processing, and analysis of 3D and 4D data. It is being actively developed by Thermo Fisher Scientific in collaboration with the Zuse Institute Berlin (ZIB), and commercially distributed by Thermo Fisher Scientific — together with its sister software Avizo.

CellCognition is a free open-source computational framework for quantitative analysis of high-throughput fluorescence microscopy (time-lapse) images in the field of bioimage informatics and systems microscopy. The CellCognition framework uses image processing, computer vision and machine learning techniques for single-cell tracking and classification of cell morphologies. This enables measurements of temporal progression of cell phases, modeling of cellular dynamics and generation of phenotype map.

Ilastik is a user-friendly free open source software for image classification and segmentation. No previous experience in image processing is required to run the software.

Neural circuit reconstruction is the reconstruction of the detailed circuitry of the nervous system of an animal. It is sometimes called EM reconstruction since the main method used is the electron microscope (EM). This field is a close relative of reverse engineering of human-made devices, and is part of the field of connectomics, which in turn is a sub-field of neuroanatomy.

<span class="mw-page-title-main">Cryogenic electron microscopy</span> Form of transmission electron microscopy (TEM)

Cryogenic electron microscopy (cryoEM) is a cryomicroscopy technique applied on samples cooled to cryogenic temperatures. For biological specimens, the structure is preserved by embedding in an environment of vitreous ice. An aqueous sample solution is applied to a grid-mesh and plunge-frozen in liquid ethane or a mixture of liquid ethane and propane. While development of the technique began in the 1970s, recent advances in detector technology and software algorithms have allowed for the determination of biomolecular structures at near-atomic resolution. This has attracted wide attention to the approach as an alternative to X-ray crystallography or NMR spectroscopy for macromolecular structure determination without the need for crystallization.

U-Net is a convolutional neural network that was developed for biomedical image segmentation at the Computer Science Department of the University of Freiburg. The network is based on a fully convolutional neural network whose architecture was modified and extended to work with fewer training images and to yield more precise segmentation. Segmentation of a 512 × 512 image takes less than a second on a modern GPU.

Julia Mahamid is a cell biologist, structural biologist, and electron microscopist at the European Molecular Biology Laboratory in Heidelberg, Germany, who utilizes biomolecular condensates and advanced cellular cryo-electron tomography to enhance the comprehension of the functional organization of the cytoplasm. She leads the Mahamid Group.

References

  1. 1 2 "Welcome: Anna Kreshuk". 20 April 2018.
  2. "Kreshuk Group – Machine learning for bioimage analysis".
  3. Kreshuk, Anna; Brun, R.; Antchevam, I.; Moneta, Lorenzo (2008). "ROOT Statistical Software". doi:10.5170/CERN-2008-001.179.
  4. Brun, R.; Canal, P.; Frank, M.; Kreshuk, A.; Linev, S.; Russo, P.; Rademakers, F. (2008). "Developments in ROOT I/O and trees". Journal of Physics: Conference Series. 119 (4): 042006. arXiv: 0901.0886 . Bibcode:2008JPhCS.119d2006B. doi:10.1088/1742-6596/119/4/042006.
  5. Antcheva, I.; Ballintijn, M.; Bellenot, B.; Biskup, M.; Brun, R.; Buncic, N.; Canal, Ph.; Casadei, D.; Couet, O.; Fine, V.; Franco, L.; Ganis, G.; Gheata, A.; Maline, D. Gonzalez; Goto, M.; Iwaszkiewicz, J.; Kreshuk, A.; Segura, D. Marcos; Maunder, R.; Moneta, L.; Naumann, A.; Offermann, E.; Onuchin, V.; Panacek, S.; Rademakers, F.; Russo, P.; Tadel, M. (2009). "ROOT — A C++ framework for petabyte data storage, statistical analysis and visualization". Computer Physics Communications. 180 (12): 2499–2512. arXiv: 1508.07749 . Bibcode:2009CoPhC.180.2499A. doi:10.1016/j.cpc.2009.08.005. S2CID   2616728.
  6. Kreshuk, Anna; Straehle, Christoph N.; Sommer, Christoph; Koethe, Ullrich; Cantoni, Marco; Knott, Graham; Hamprecht, Fred A. (2011). "Automated Detection and Segmentation of Synaptic Contacts in Nearly Isotropic Serial Electron Microscopy Images". PLOS ONE. 6 (10): e24899. Bibcode:2011PLoSO...624899K. doi: 10.1371/journal.pone.0024899 . PMC   3198725 . PMID   22031814.
  7. Kreshuk, Anna; Koethe, Ullrich; Pax, Elizabeth; Bock, Davi D.; Hamprecht, Fred A. (2014). "Automated Detection of Synapses in Serial Section Transmission Electron Microscopy Image Stacks". PLOS ONE. 9 (2): e87351. Bibcode:2014PLoSO...987351K. doi: 10.1371/journal.pone.0087351 . PMC   3916342 . PMID   24516550.
  8. Krasowski, N. E.; Beier, T.; Knott, G. W.; Kothe, U.; Hamprecht, F. A.; Kreshuk, A. (2018). "Neuron Segmentation with High-Level Biological Priors". IEEE Transactions on Medical Imaging. 37 (4): 829–839. doi:10.1109/TMI.2017.2712360. PMID   28600240. S2CID   4560617.
  9. The interactive learning and segmentation toolkit ilastik.org
  10. Berg, Stuart; Kutra, Dominik; Kroeger, Thorben; Straehle, Christoph N.; Kausler, Bernhard X.; Haubold, Carsten; Schiegg, Martin; Ales, Janez; Beier, Thorsten; Rudy, Markus; Eren, Kemal; Cervantes, Jaime I.; Xu, Buote; Beuttenmueller, Fynn; Wolny, Adrian; Zhang, Chong; Koethe, Ullrich; Hamprecht, Fred A.; Kreshuk, Anna (2019). "Ilastik: Interactive machine learning for (Bio)image analysis". Nature Methods. 16 (12): 1226–1232. doi:10.1038/s41592-019-0582-9. PMID   31570887. S2CID   203609613.
  11. Eisenstein, Michael (2023). "AI under the microscope: The algorithms powering the search for cells". Nature. 623 (7989): 1095–1097. Bibcode:2023Natur.623.1095E. doi: 10.1038/d41586-023-03722-y . PMID   38012372.
  12. Vergara, Hernando M.; Pape, Constantin; Meechan, Kimberly I.; Zinchenko, Valentyna; Genoud, Christel; Wanner, Adrian A.; Mutemi, Kevin Nzumbi; Titze, Benjamin; Templin, Rachel M.; Bertucci, Paola Y.; Simakov, Oleg; Dürichen, Wiebke; Machado, Pedro; Savage, Emily L.; Schermelleh, Lothar; Schwab, Yannick; Friedrich, Rainer W.; Kreshuk, Anna; Tischer, Christian; Arendt, Detlev (2021). "Whole-body integration of gene expression and single-cell morphology". Cell. 184 (18): 4819–4837.e22. doi:10.1016/j.cell.2021.07.017. PMC   8445025 . PMID   34380046.
  13. Wolny, Adrian; Cerrone, Lorenzo; Vijayan, Athul; Tofanelli, Rachele; Barro, Amaya Vilches; Louveaux, Marion; Wenzl, Christian; Strauss, Sören; Wilson-Sánchez, David; Lymbouridou, Rena; Steigleder, Susanne S.; Pape, Constantin; Bailoni, Alberto; Duran-Nebreda, Salva; Bassel, George W.; Lohmann, Jan U.; Tsiantis, Miltos; Hamprecht, Fred A.; Schneitz, Kay; Maizel, Alexis; Kreshuk, Anna (2020). "Accurate and versatile 3D segmentation of plant tissues at cellular resolution". eLife. 9. doi: 10.7554/eLife.57613 . PMC   7447435 . PMID   32723478.
  14. "Deep learning for image analysis – Course and Conference Office".
  15. "Biophysics & Development Seminar: Anna Kreshuk, EMBL".
  16. "Hybrid Technologies for Structural Cell Biology at Near-Atomic Resolution".