Conference papers

  • I. Smal, N. Carranza-Herrezuelo, S. Klein, W. Niessen and E. Meijering. Trans-Dimensional MCMC Methods for Fully Automatic Motion Analysis in Tagged MRI, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2011 (Toronto, Canada, September 18-22, 2011), G. Fichtinger, A. Martel, and T. Peters (Eds.): MICCAI 2011, Part I, LNCS 6891, pp. 573--580. Springer, Heidelberg (2011) (Abstract, pdf)


    • Download preprint [xxxkB]
    Tagged magnetic resonance imaging (tMRI) is a well-known noninvasive method allowing quantitative analysis of regional heart dynamics. Its clinical use has so far been limited, in part due to the lack of robustness and accuracy of existing tag tracking algorithms in dealing with low (and intrinsically time-varying) image quality. In this paper, we propose a novel probabilistic method for tag tracking, implemented by means of Bayesian particle filtering and a trans-dimensional Markov chain Monte Carlo (MCMC) approach, which efficiently combines information about the imaging process and tag appearance with prior knowledge about the heart dynamics obtained by means of non-rigid image registration. Experiments using synthetic image data (with ground truth) and real data (with expert manual annotation) from preclinical (small animal) and clinical (human) studies confirm that the proposed method yields higher consistency, accuracy, and intrinsic tag reliability assessment in comparison with other frequently used tag tracking methods.
  • I. Smal, N. Carranza-Herrezuelo, S. Klein, W. J. Niessen, E. Meijering. Quantitative Comparison of Tracking Methods for Motion Analysis in Tagged MRI, IEEE International Symposium on Biomedical Imaging: From Nano to Macro - ISBI 2011 (Chicago, IL, USA, March 30 - April 2, 2011), IEEE, Piscataway, NJ, 2011 (Abstract, pdf)
    • Copyright (c) 2011 by the authors. Published version (c) 2010 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint [xxxkB]
    Myocardial tagging in magnetic resonance imaging (MRI) has shown great potential for noninvasive measurement of the motion of a beating heart. A critical issue in exploiting this technology in practice is the availability of robust and accurate methods for tag tracking. In this paper we quantitatively evaluate and compare four motion analysis methods that are frequently used in practice, based on optical flow, harmonic phase MRI, B-snake grids, and non-rigid registration techniques. Experiments on realistic synthetic images and data from three different (pre)clinical experiments show that non-rigid registration methods yield the highest accuracy and robustness among the considered methods.
  • N. Carranza Herrezuelo, I. Smal, O. Dzyubachyk, W. J. Niessen, E. Meijering. Automated Linneage Tree Reconstruction from Caenorhabditis Elegans Image Data using Particle Filtering Based Cell Tracking, IEEE International Symposium on Biomedical Imaging: From Nano to Macro - ISBI 2011 (Chicago, IL, USA, March 30 - April 2, 2011), IEEE, Piscataway, NJ, 2011 (Abstract, pdf)
    • Copyright (c) 2011 by the authors. Published version (c) 2010 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint [xxxkB]
    Caenorhabditis elegans is an important model organism for the study of molecular mechanisms of development and disease processes, due to its well-known genome and invariant cell lineage tree. Such studies generally produce vast amounts of image data, and require very robust and efficient algorithms to extract and characterize lineage phenotypes and to determine gene expression patterns. Previously published methods for this purpose show only mediocre performance and often require extensive manual post-processing. The challenge remains to develop more powerful and fully automated methods. In this paper we propose a new algorithm for C. elegans cell tracking and lineage reconstruction, based on a Bayesian estimation framework, implemented by means of particle filtering. The tracking is enhanced with a detection stage, based on the h-dome transform. Preliminary experiments on several image sequences demonstrate that the new tracking algorithm is able to reconstruct the lineage tree, at least until the 350-cell stage, without manual intervention, at low computational cost and with low error rates.
  • I. Smal, W. J. Niessen, E. Meijering. Particle Filtering Methods for Motion Analysis in Tagged MRI, IEEE International Symposium on Biomedical Imaging: From Nano to Macro - ISBI 2010 (Rotterdam, NL, April 14-17, 2010), W. Niessen and E. Meijering (eds.), IEEE, Piscataway, NJ, 2010 (Abstract, pdf)
    • Copyright (c) 2010 by the authors. Published version (c) 2010 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint [510kB]
    Myocardial tagging using magnetic resonance imaging (MRI) is a well-known noninvasive method for studying regional heart dynamics. While it offers great potential for quantitative analysis of a variety of kinematic and kinetic parameters, its clinical use has so far been limited, mainly due to mediocre performance of existing tag tracking algorithms under poor imaging conditions. In this paper we propose a new approach to tracking of MRI tag intersections. It is based on a Bayesian estimation framework, implemented by means of particle filtering, and combines information about heart dynamics, the imaging process, and tag appearance. Since at any time point it optimally incorporates all available information, it can be expected to be more robust and accurate. This is demonstrated by results of preliminary experiments on image sequences from (small) animal imaging studies.
  • I. Smal, I. Grigoriev, A. Akhmanova, W. J. Niessen, E. Meijering. Accurate Estimation of Microtubule Dynamics using Kymographs and Variable-Rate Particle Filters, Annual International Conference of the IEEE Engineering in Medicine and Biology Society - EMBC 2009 (Minneapolis, MN, USA, September 2-6, 2009), B. He and Y. Kim (eds.), IEEE, Piscataway, NJ, 2009 (Abstract, pdf)
    • Copyright (c) 2009 by the authors. Published version (c) 2009 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint [510kB]
    Studying intracellular dynamics is of major importance for understanding healthy life at the molecular level and for developing drugs to target disease processes. One of the key technologies to enable this research is the automated tracking and motion analysis of subcellular objects in microscopy image sequences. Contrary to common frame-by-frame tracking methods, two alternative approaches have been proposed recently, based on either Bayesian estimation or space-time segmentation, which better exploit the available spatiotemporal information. In this paper, we propose to combine the power of both approaches, and develop a new probabilistic method to segment the traces of the moving objects in kymograph representations of the image data. It is based on variable-rate particle filtering and uses multiscale trend analysis for estimation of the relevant kinematic parameters using the extracted traces. Experiments on realistic synthetically generated images as well as on real biological image data demonstrate the improved potential of the new method for the analysis of microtubule dynamics in vitro.
  • I. Smal, M. Loog, W. Niessen, E. Meijering. Quantitative Comparison of Spot Detection Methods in Live-Cell Fluorescence Microscopy Imaging, IEEE International Symposium on Biomedical Imaging: From Nano to Macro - ISBI 2009 (Boston, MA, USA, June 28 - July 1, 2009), W. C. Karl, B. Rosen, D. Brooks (eds.), IEEE, Piscataway, NJ, 2009 (Abstract, pdf)
    • Copyright (c) 2009 by the authors. Published version (c) 2009 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint [917kB].
    In live-cell fluorescence microscopy imaging, quantitative analysis of biological image data generally involves the detection of many subresolution objects, appearing as diffraction-limited spots. Due to acquisition limitations, the signal-to-noise ratio (SNR) can be extremely low, making automated spot detection a very challenging task. In this paper, we quantitatively evaluate the performance of the most frequently used supervised and unsupervised detection methods for this purpose. Experiments on synthetic images of three different types, for which ground truth was available, as well as on real image data sets acquired for two different biological studies, for which we obtained expert manual annotations for comparison, revealed that for very low SNRs (≈ 2), the supervised (machine learning) methods perform best overall, closely followed by the detectors based on the so-called h-dome transform from mathematical morphology and the multiscale variance-stabilizing transform, which do not require a learning stage. At high SNRs (> 5), the difference in performance of all considered detectors becomes negligible.
  • I. Smal, W. Niessen, E. Meijering. A New Detection Scheme for Multiple Object Tracking in Fluorescence Microscopy by Joint Probabilistic Data Association Filtering. IEEE International Symposium on Biomedical Imaging: From Nano to Macro - ISBI 2008 (Paris, France, May 14-17, 2008), J.-C. Olivo-Marin, I. Bloch, A. Laine (eds.), IEEE, Piscataway, NJ, 2008, pp. 264-267 (Abstract, pdf)
    • Copyright (c) 2008 by the authors. Published version (c) 2008 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint [642kB].
    Tracking of multiple objects in biological image data is a challenging problem due largely to poor imaging conditions and complicated motion scenarios. Existing tracking algorithms for this purpose often do not provide sufficient robustness and/or are computationally expensive. In this paper we propose a new object detection scheme, based on importance sampling from image intensity distributions, and show how it can be easily incorporated into a probabilistic tracking framework based on Kalman or particle filtering. Experiments on synthetic as well as real fluorescence microscopy image data from different biological studies show that the resulting tracking algorithm yields smaller localization errors at much lower execution times compared to other available methods.
  • M. Schaap, R. Manniesing, I. Smal, T. van Walsum, A. van der Lugt and W.J. Niessen, Bayesian Tracking of Tubular Structures and Its Application to Carotid Arteries in CTA, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2007 (Brisbane, Australia, October 29-November 2, 2007), Lecture Notes in Computer Science, Springer-Verlag, Berlin, vol. 4791, 2007, pp. 562-570 (Abstract, pdf)
    • This paper presents a Bayesian framework for tracking of tubular structures such as vessels. Compared to conventional tracking schemes, its main advantage is its non-deterministic character, which strongly increases the robustness of the method. A key element of our approach is a dedicated observation model for tubular structures in regions with varying intensities. Furthermore, we show how the tracking method can be used to obtain a probabilistic segmentation of the tracked tubular structure. The method has been applied to track the internal carotid artery from CT angiography data of 14 patients (28 carotids) through the skull base. This is a challenging problem, owing to the close proximity of bone, overlap in intensity values of lumen voxels and (partial volume) bone voxels, and the tortuous path of the vessels. The tracking was successful in 25 cases, and the extracted path were found to be close (< 1.0mm) to manually traced paths by two observers.
  • I. Smal, K. Draegestein, N. Galjart, W. Niessen, E. Meijering, Rao-Blackwellized Marginal Particle Filtering for Multiple Object Tracking in Molecular Bioimaging, Information Processing in Medical Imaging - IPMI 2007 (Kerkrade, Limburg, The Netherlands, July 2-6, 2007), N. Karssemeijer and B. Lelieveldt (eds.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, 2007, pp. 110-121 (Abstract, pdf)
    • Copyright (c) 2007 by the authors. Published version (c) 2007 by Springer-Verlag. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint.
    Modern live cell fluorescence microscopy imaging systems, used abundantly for studying intra-cellular processes in vivo, generate vast amounts of noisy image data that cannot be processed efficiently and accurately by means of manual or current computerized techniques. We propose an improved tracking method, built within a Bayesian probabilistic framework, which better exploits temporal information and prior knowledge. Experiments on simulated and real fluorescence microscopy image data acquired for microtubule dynamics studies show that the technique is more robust to noise, photobleaching, and object interaction than common tracking methods and yields results that are in good agreement with expert cell biologists.
  • M. Schaap, I. Smal, C. Metz, T. van Walsum and W.J. Niessen, Bayesian Tracking of Elongated Structures in 3D Images, Information Processing in Medical Imaging - IPMI 2007 (Kerkrade, Limburg, The Netherlands, July 2-6, 2007), N. Karssemeijer and B. Lelieveldt (eds.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, 2007, pp. 74-85 (Abstract, pdf)
    • Copyright (c) 2007 by the authors. Published version (c) 2007 by Springer-Verlag. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint.
    Tracking of tubular elongated structures is an important goal in a wide range of biomedical imaging applications. A Bayesian tube tracking algorithm is presented that allows to easily incorporate a priori knowledge. Because probabilistic tube tracking algorithms are computa- tionally complex, steps towards a computational efficient implementation are suggested in this paper. The algorithm is evaluated on 2D and 3D synthetic data with different noise levels and clinical CTA data. The approach shows good perfor- mance on data with high levels of Gaussian noise.
  • I. Smal, W. Niessen, E. Meijering, Advanced Particle Filtering for Multiple Object Tracking in Dynamic Fluorescence Microscopy Images, Proceedings of the 2007 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (Arlington, VA, USA, April 12-15, 2007), IEEE, Piscataway, NJ, 2007, pp. 1048-1051 (Abstract, pdf)
    • Copyright (c) 2007 by the authors. Published version (c) 2007 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint.
    Quantitative analysis of dynamical processes in living cells by means of fluorescence microscopy imaging requires tracking of hundreds of bright spots in noisy image sequences. Deterministic approaches that perform object detection prior to tracking usually produce many incorrect tracks. We propose an improved, completely automatic tracker, built in a Bayesian probabilistic framework. It fully exploits spatiotemporal information and prior knowledge, yielding more robust tracking also in case of photobleaching and object interaction. Results from a preliminary quantitative evaluation based on highly realistic synthetic image sequences as well as real fluorescence microscopy image data in comparison with manual tracking indicate superior performance.
  • I. Smal, W. Niessen, E. Meijering, Particle Filtering for Multiple Object Tracking in Molecular Cell Biology, Proceedings of the 2006 Nonlinear Statistical Signal Processing Workshop (Cambridge, UK, September 13-15, 2006), IEEE, Piscataway, NJ, 2006 (Abstract, pdf)
    • Copyright 2006 by the authors. Published version 2006 by IEEE. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.

    Download preprint.
    Motion analysis of subcellular structures in living cells is currently a major topic in molecular cell biology, for which computerized methods are desperately needed. In this paper we adopt and tailor particle filtering techniques for this purpose and present the results of robust and accurate tracking of multiple objects in real fluorescence microscopy image data acquired for specific biological studies.
  • I. Smal, W. Niessen, E. Meijering, Bayesian Tracking for Fluorescence Microscopic Imaging, Proceedings of the 2006 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (Arlington, VA, USA, April 6-9, 2006), IEEE, Piscataway, NJ, 2006, pp. 550-553 (Abstract, pdf)
    • Copyright 2006 IEEE. Published in the 2006 International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2006), scheduled for April 6-9, 2006 in Arlington, Virginia, U.S.A. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager, Copyrights and Permissions / IEEE Service Center / 445 Hoes Lane / P.O. Box 1331 / Piscataway, NJ 08855-1331, USA. Telephone: + Intl. 908-562-3966.

    Download preprint.
    Fluorescence microscopy is a powerful imaging tool for studying molecular dynamics in living cells. For quantitative motion analysis of subcellular structures robust and accurate detection and tracking techniques are necessary. Sequential Monte Carlo methods, also known as Particle Filters (PF), have become a tremendously popular tool to perform tracking in many fields. We propose a PF-based approach for quantitative analysis of subcellular dynamics. This approach utilizes all spatiotemporal information, which is an important advantage over existing methods that separate the object detection and object linking stage. The tracking technique has been evaluated using simulated but highly realistic image sequences, for which ground truth was available, showing that the method is more robust to noise than existing tracking techniques. In addition, evaluation experiments were conducted with real fluorescence microscopy image data acquired for specific biological studies.
  • L. A. Sinitsky, I. Smal, "Synthesis of Oscillators with One Degree of Freedom which Reproduce Oscillations with the Prescribed Waveform", Proceeding of Third International Scientific Technical Conference "Mathematical Modeling in Electrical Engineering", Lviv, Ukraine, Oct. 25-30, 1999. pp.248-250.
  • I. Smal, "Synthesis of Relaxation Oscillators with the Prescribed Impulse Form", Proceeding of Third International Scientific Technical Conference "Mathematical Modeling in Electrical Engineering", Lviv, Ukraine, Oct. 25-30, 1999, pp. 255-257.