Dr. Tatyana Ivanovska

Group(s): Computer Vision
Email:
tatyana.ivanovska@phys.uni-goettingen.de
Phone: +49 551/ 39 10764
Room: E.01.103

Global QuickSearch:   Matches: 0

Search Settings

    Author / Editor / Organization
    Year
    Title
    Journal / Proceedings / Book
    Ivanovska, T. and Herzog, S. and Flores, J. M. and Ciet, P. and Linsen, L. and Duijts, L. and Tiddens, H. and Völzke, H. and Annette Peters, F. W. (2017).
    Potential of Epidemiological Imaging for Image Analysis and Visualization Applications: A Brief Review. In Proceedings of 4th Int.Conf. on Mathematics and Computers in Sciences and Industry (MCSI 2017).
    BibTeX:
    @conference{ivanovskaherzogflores2017,
      author = {Ivanovska, T. and Herzog, S. and Flores, J. M. and Ciet, P. and Linsen, L. and Duijts, L. and Tiddens, H. and Völzke, H. and Annette Peters, F. W.},
      title = {Potential of Epidemiological Imaging for Image Analysis and Visualization Applications: A Brief Review},
      booktitle = {In Proceedings of 4th Int.Conf. on Mathematics and Computers in Sciences and Industry (MCSI 2017)},
      year = {2017},
      abstract = {Recently, large population-based studies gain increasing focus in the research community. Epidemiological studies acquire numerous data by means of questionnaires and examinations. Many of these studies also collect imaging data, for instance, magnetic resonance imaging or ultrasonography from hundreds or even thousands of participants. Here, we consider several on-going epidemiological studies conducted in Europe as well as challenges of subsequent image analysis and visualization of heterogeneous data, which were obtained within these studies. In particular, the main focus is on airway extraction tasks and the visual analytics problems. Available solutions and future directions for computer science specialists are presented and analyzed in terms of user-friendliness, speed, and efficiency.}}
    Abstract: Recently, large population-based studies gain increasing focus in the research community. Epidemiological studies acquire numerous data by means of questionnaires and examinations. Many of these studies also collect imaging data, for instance, magnetic resonance imaging or ultrasonography from hundreds or even thousands of participants. Here, we consider several on-going epidemiological studies conducted in Europe as well as challenges of subsequent image analysis and visualization of heterogeneous data, which were obtained within these studies. In particular, the main focus is on airway extraction tasks and the visual analytics problems. Available solutions and future directions for computer science specialists are presented and analyzed in terms of user-friendliness, speed, and efficiency.
    Review:
    Ivanovska, T. and Ciet, P. and Perez-Rovira, A. and Nguyen, A. and Tiddens, H. and Duijts, L. and Bruijne, M. and Wörgötter, F. (2017).
    Fully Automated Lung Volume Assessment from MRI in a Population-based Child Cohort Study. Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), 53-58. DOI: 10.5220/0006075300530058.
    BibTeX:
    @conference{ivanovskacietperezrovira2017,
      author = {Ivanovska, T. and Ciet, P. and Perez-Rovira, A. and Nguyen, A. and Tiddens, H. and Duijts, L. and Bruijne, M. and Wörgötter, F.},
      title = {Fully Automated Lung Volume Assessment from MRI in a Population-based Child Cohort Study},
      pages = {53-58},
      booktitle = {Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP)},
      year = {2017},
      organization = {INSTICC},
      publisher = {ScitePress},
      doi = {10.5220/0006075300530058},
      abstract = {In this work, a framework for fully automated lung extraction from magnetic resonance imaging (MRI) inspiratory data that have been acquired within a on-going epidemiological child cohort study is presented. The methods main steps are intensity inhomogeneity correction, denoising, clustering, airway extraction and lung region refinement. The presented approach produces highly accurate results (Dice coefficients 95%), when compared to semi-automatically obtained masks, and has potential to be applied to the whole study data.}}
    Abstract: In this work, a framework for fully automated lung extraction from magnetic resonance imaging (MRI) inspiratory data that have been acquired within a on-going epidemiological child cohort study is presented. The methods main steps are intensity inhomogeneity correction, denoising, clustering, airway extraction and lung region refinement. The presented approach produces highly accurate results (Dice coefficients 95%), when compared to semi-automatically obtained masks, and has potential to be applied to the whole study data.
    Review:
    Gressmann, F. and Lüddecke, T. and Ivanovska, T. and Schoeler, M. and Wörgötter, F. (2017).
    Part-driven Visual Perception of 3D Objects. Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017), 370-377. DOI: 10.5220/0006211203700377.
    BibTeX:
    @conference{gressmannlueddeckeivanovska2017,
      author = {Gressmann, F. and Lüddecke, T. and Ivanovska, T. and Schoeler, M. and Wörgötter, F.},
      title = {Part-driven Visual Perception of 3D Objects},
      pages = {370-377},
      booktitle = {Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
      year = {2017},
      organization = {INSTICC},
      publisher = {ScitePress},
      doi = {10.5220/0006211203700377},
      abstract = {During the last years, approaches based on convolutional neural networks (CNN) had substantial success in visual object perception. CNNs turned out to be capable of extracting high-level features of objects, which allow for fine-grained classification. However, some object classes exhibit tremendous variance with respect to their instances appearance. We believe that considering object parts as an intermediate representation could be helpful in these cases. In this work, a part-driven perception of everyday objects with a rotation estimation is implemented using deep convolution neural networks. The used network is trained and tested on artificially generated RGB-D data. The approach has a potential to be used for part recognition of realistic sensor recordings in present robot systems.}}
    Abstract: During the last years, approaches based on convolutional neural networks (CNN) had substantial success in visual object perception. CNNs turned out to be capable of extracting high-level features of objects, which allow for fine-grained classification. However, some object classes exhibit tremendous variance with respect to their instances appearance. We believe that considering object parts as an intermediate representation could be helpful in these cases. In this work, a part-driven perception of everyday objects with a rotation estimation is implemented using deep convolution neural networks. The used network is trained and tested on artificially generated RGB-D data. The approach has a potential to be used for part recognition of realistic sensor recordings in present robot systems.
    Review:
    Shahid, M. L. U. R. and Chitiboi, T. and Ivanovska, T. and Molchanov, V. and Völzke, H. and Linsen, L. (2017).
    Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification. BMC Medical Imaging, 15, 17, 1. DOI: 10.1186/s12880-017-0179-7.
    BibTeX:
    @article{shahidchitiboiivanovska2017,
      author = {Shahid, M. L. U. R. and Chitiboi, T. and Ivanovska, T. and Molchanov, V. and Völzke, H. and Linsen, L.},
      title = {Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification},
      pages = {15},
      journal = {BMC Medical Imaging},
      year = {2017},
      volume= {17},
      number = {1},
      url = {http://dx.doi.org/10.1186/s12880-017-0179-7},
      doi = {10.1186/s12880-017-0179-7},
      abstract = {Obstructive sleep apnea (OSA) is a public health problem. Detailed analysis of the para-pharyngeal fat pads can help us to understand the pathogenesis of OSA and may mediate the intervention of this sleeping disorder. A reliable and automatic para-pharyngeal fat pads segmentation technique plays a vital role in investigating larger data bases to identify the anatomic risk factors for the OSA.}}
    Abstract: Obstructive sleep apnea (OSA) is a public health problem. Detailed analysis of the para-pharyngeal fat pads can help us to understand the pathogenesis of OSA and may mediate the intervention of this sleeping disorder. A reliable and automatic para-pharyngeal fat pads segmentation technique plays a vital role in investigating larger data bases to identify the anatomic risk factors for the OSA.
    Review:
    Ivanovska, T. and Hegenscheid, K. and Laqua, R. and Gläser, S. and Ewert, R. and Völzke, H. (2016).
    Lung Segmentation of MR Images: A Review. Visualization in Medicine and Life Sciences III: Towards Making an Impact, 3-24. DOI: 10.1007/978-3-319-24523-2_1.
    BibTeX:
    @inbook{ivanovskahegenscheidlaqua2016,
      author = {Ivanovska, T. and Hegenscheid, K. and Laqua, R. and Gläser, S. and Ewert, R. and Völzke, H.},
      title = {Lung Segmentation of MR Images: A Review},
      pages = {3-24},
      booktitle = {Visualization in Medicine and Life Sciences III: Towards Making an Impact},
      year = {2016},
      editor = {Linsen, Lars and Hamann, Bernd and Hege, Hans-Christian},
      publisher = {Springer International Publishing},
      url = {https://link.springer.com/chapter/10.1007%2F978-3-319-24523-2_1},
      doi = {10.1007/978-3-319-24523-2_1},
      abstract = {Magnetic resonance imaging (MRI) is a non-radiation based examination method, which gains an increasing popularity in research and clinical settings. Manual analysis of large data volumes is a very time-consuming and tedious process. Therefore, automatic analysis methods are required. This paper reviews different methods that have been recently proposed for automatic and semi-automatic lung segmentation from magnetic resonance imaging data. These techniques include thresholding, region growing, morphological operations, active contours, level sets, and neural networks. We also discuss the methodologies that have been utilized for performance and accuracy evaluation of each method.}}
    Abstract: Magnetic resonance imaging (MRI) is a non-radiation based examination method, which gains an increasing popularity in research and clinical settings. Manual analysis of large data volumes is a very time-consuming and tedious process. Therefore, automatic analysis methods are required. This paper reviews different methods that have been recently proposed for automatic and semi-automatic lung segmentation from magnetic resonance imaging data. These techniques include thresholding, region growing, morphological operations, active contours, level sets, and neural networks. We also discuss the methodologies that have been utilized for performance and accuracy evaluation of each method.
    Review:
    Ivanovska, T. and Pomschar, A. and Lorbeer, R. and Kunz, W. and Schulz, H. and Hetterich, H. and Völzke, H. and Bamber, F. and Peters, A. and Wörgötter, F. (2016).
    Efficient population-based big MR data analysis: a lung segmentation and volumetry example. In Proceedings of Sixth International Workshop on Pulmonary Image Analysis (PIA) at MICCAI 2016.
    BibTeX:
    @conference{ivanovskapomscharlorbeer2016,
      author = {Ivanovska, T. and Pomschar, A. and Lorbeer, R. and Kunz, W. and Schulz, H. and Hetterich, H. and Völzke, H. and Bamber, F. and Peters, A. and Wörgötter, F.},
      title = {Efficient population-based big MR data analysis: a lung segmentation and volumetry example},
      booktitle = {In Proceedings of Sixth International Workshop on Pulmonary Image Analysis (PIA) at MICCAI 2016},
      year = {2016},
      location = {Athens, Greece},
      abstract = {In this paper, we discuss magnetic resonance (MR) lung imaging and the related image processing tasks from two on-going epidemiological studies conducted in Germany. A modularized system for efficient lung segmentation is proposed and applied for test lung datasets from both studies. The efficiency of the framework is demonstrated by comparison of automatically computed results to the manually created ground truth masks. The presented pipeline allows one to obtain highly accurate segmentation results even for MR data with lower quality.}}
    Abstract: In this paper, we discuss magnetic resonance (MR) lung imaging and the related image processing tasks from two on-going epidemiological studies conducted in Germany. A modularized system for efficient lung segmentation is proposed and applied for test lung datasets from both studies. The efficiency of the framework is demonstrated by comparison of automatically computed results to the manually created ground truth masks. The presented pipeline allows one to obtain highly accurate segmentation results even for MR data with lower quality.
    Review:
    Ivanovska, T. and Reich, S. and Bevec, R. and Gosar, Z. and Tamosiunaite, M. and Ude, A. and Wörgötter, F. (2018).
    Visual Inspection And Error Detection In a Reconfigurable Robot Workcell: An Automotive Light Assembly Example. Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP): Visapp (VCEA), 607-615, 5. DOI: 10.5220/0006666506070615.
    BibTeX:
    @inproceedings{ivanovskareichbevec2018,
      author = {Ivanovska, T. and Reich, S. and Bevec, R. and Gosar, Z. and Tamosiunaite, M. and Ude, A. and Wörgötter, F.},
      title = {Visual Inspection And Error Detection In a Reconfigurable Robot Workcell: An Automotive Light Assembly Example},
      pages = {607-615},
      booktitle = {Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP): Visapp (VCEA)},
      year = {2018},
      volume= {5},
      location = {Funchal, Madeira (Portugal)},
      month = {January 27-29},
      organization = {INSTICC},
      publisher = {SciTePress},
      doi = {10.5220/0006666506070615},
      abstract = {Small and medium size enterprises (SMEs) often have small batch production. It leads to decreasing product lifetimes and also to more frequent product launches. In order to assist such production, a highly reconfigurable robot workcell is being developed. In this work, a visual inspection system designed for the robot workcell is presented and discussed in the context of the automotive light assembly example. The proposed framework is implemented using ROS and OpenCV libraries. We describe the hardware and software components of the framework and explain the systems benefits when compared to other commercial packages.}}
    Abstract: Small and medium size enterprises (SMEs) often have small batch production. It leads to decreasing product lifetimes and also to more frequent product launches. In order to assist such production, a highly reconfigurable robot workcell is being developed. In this work, a visual inspection system designed for the robot workcell is presented and discussed in the context of the automotive light assembly example. The proposed framework is implemented using ROS and OpenCV libraries. We describe the hardware and software components of the framework and explain the systems benefits when compared to other commercial packages.
    Review:
    Dietrich, P. and Schmidt, C. and Völzke, H. and Beule, A. and Wörgötter, F. and Ivanovska, T. (2018).
    Effiziente Segmentierung trachealer Strukturenin MRI-Aufnahmen. Bildverarbeitung für die Medizin 2018 (In press).
    BibTeX:
    @incollection{dietrichschmidtvoelzke2018,
      author = {Dietrich, P. and Schmidt, C. and Völzke, H. and Beule, A. and Wörgötter, F. and Ivanovska, T.},
      title = {Effiziente Segmentierung trachealer Strukturenin MRI-Aufnahmen},
      booktitle = {Bildverarbeitung für die Medizin 2018},
      year = {2018},
      note = {In press},
      abstract = {Die Segmentierung verschiedener Strukturen im Korper ist eine der grundlegenden Operationen in der medizinischen Bildverarbeitung. In dieser Arbeit werden auf Machine Learning basierende Methoden zur Segmentierung medizinischer Bilder untersucht. Das Ziel ist es, in MRI-Scans die Trachea zu segmentieren. Jedoch soll in dieser Arbeit speziell die Effizienz der Algorithmen im Vordergrund stehen. Die verwendeten Ansatze basierten auf einer Deep Learning Architektur, welche zunachst individuell optimiert wird. Es konnte ein maximaler DICE-Koeffizient von (94.4 2.1)% erzielt werden. Zusatzlich kann festgestellt werden, dass die Segmentierung sehr effizient geschieht. Die Segmentierung von einmen Datensatz aus 40 Schichten dauert dabei weniger als eine Sekunde, wobei bei bisherigen Methoden es uber eine Minute benotigte.}}
    Abstract: Die Segmentierung verschiedener Strukturen im Korper ist eine der grundlegenden Operationen in der medizinischen Bildverarbeitung. In dieser Arbeit werden auf Machine Learning basierende Methoden zur Segmentierung medizinischer Bilder untersucht. Das Ziel ist es, in MRI-Scans die Trachea zu segmentieren. Jedoch soll in dieser Arbeit speziell die Effizienz der Algorithmen im Vordergrund stehen. Die verwendeten Ansatze basierten auf einer Deep Learning Architektur, welche zunachst individuell optimiert wird. Es konnte ein maximaler DICE-Koeffizient von (94.4 2.1)% erzielt werden. Zusatzlich kann festgestellt werden, dass die Segmentierung sehr effizient geschieht. Die Segmentierung von einmen Datensatz aus 40 Schichten dauert dabei weniger als eine Sekunde, wobei bei bisherigen Methoden es uber eine Minute benotigte.
    Review:
    Jentschke, T. G. and Hegenscheid, K. and Völzke, H. and Wörgötter Florentin Ivanovska, T. (2018).
    Segmentierung von Brustvolumina in Magnetresonanztomographiedaten unter derVerwendung von Deep Learning. Bildverarbeitung für die Medizin 2018 (In press).
    BibTeX:
    @incollection{jentschkehegenscheidvoelzke2018,
      author = {Jentschke, T. G. and Hegenscheid, K. and Völzke, H. and Wörgötter Florentin Ivanovska, T.},
      title = {Segmentierung von Brustvolumina in Magnetresonanztomographiedaten unter derVerwendung von Deep Learning},
      booktitle = {Bildverarbeitung für die Medizin 2018},
      year = {2018},
      note = {In press},
      abstract = {Kurzfassung. Die Segmentierung von Hintergrund und Brustgewebe ist ein wichtiger Teil der Auswertung von Magnetresonanztomographie-Daten der Brust. Normalerweise wird diese von Arzten manuell durchgefuhrt. In dieser Arbeit wurde die Segmentierung hingegen mit einer U-net Architektur realisiert. Dabei wurden zwei Netzwerke trainiert und anschließend auf ein unbekanntes Testset, bestehend aus 8 Probandinnen, angewendet. Die so berechneten Segmentierungen wurden dann mit von Arzten manuell vorgenommenen verglichen. Das erste U-net nutzt keine weitere Vorverarbeitungsmethode und erreicht einen DSC von 0.91 0.09 (Mittelwert Standardabweichung). Beim zweiten Netzwerk wurde der N4ITK Bias Correction Algorithmus als Vorverarbeitungsmethode verwendet. Die Masken fur N4ITK konnen sehr grob sein und daher in einer spateren Anwendung von einem Arzt schnell erstellt werden. In dieser Konstellation wurde bei der Segmentierung des Testsets ein DSC von 0.98 0.05 erreicht. Die Segmentierungen benotigen daruber hinaus nach Anfertigung der Masken fur den Vorverarbeitungsalgorithmus 14s. Die Methode hat somit das Potential, Anwendung in der medizinischen Diagnostik zu finden.}}
    Abstract: Kurzfassung. Die Segmentierung von Hintergrund und Brustgewebe ist ein wichtiger Teil der Auswertung von Magnetresonanztomographie-Daten der Brust. Normalerweise wird diese von Arzten manuell durchgefuhrt. In dieser Arbeit wurde die Segmentierung hingegen mit einer U-net Architektur realisiert. Dabei wurden zwei Netzwerke trainiert und anschließend auf ein unbekanntes Testset, bestehend aus 8 Probandinnen, angewendet. Die so berechneten Segmentierungen wurden dann mit von Arzten manuell vorgenommenen verglichen. Das erste U-net nutzt keine weitere Vorverarbeitungsmethode und erreicht einen DSC von 0.91 0.09 (Mittelwert Standardabweichung). Beim zweiten Netzwerk wurde der N4ITK Bias Correction Algorithmus als Vorverarbeitungsmethode verwendet. Die Masken fur N4ITK konnen sehr grob sein und daher in einer spateren Anwendung von einem Arzt schnell erstellt werden. In dieser Konstellation wurde bei der Segmentierung des Testsets ein DSC von 0.98 0.05 erreicht. Die Segmentierungen benotigen daruber hinaus nach Anfertigung der Masken fur den Vorverarbeitungsalgorithmus 14s. Die Methode hat somit das Potential, Anwendung in der medizinischen Diagnostik zu finden.
    Review:

    © 2011 - 2017 Dept. of Computational Neuroscience • comments to: sreich _at_ gwdg.de • Impressum / Site Info