Search

Your search keyword '"Kellner, Elias"' showing total 294 results
Start Over Author "Kellner, Elias"
294 results on '"Kellner, Elias"'

8. Deep Neural Patchworks: Coping with Large Segmentation Tasks

Author

Reisert, Marco, Russe, Maximilian, Elsheikh, Samer, Kellner, Elias, and Skibbe, Henrik

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Convolutional neural networks are the way to solve arbitrary image segmentation tasks. However, when images are large, memory demands often exceed the available resources, in particular on a common GPU. Especially in biomedical imaging, where 3D images are common, the problems are apparent. A typical approach to solve this limitation is to break the task into smaller subtasks by dividing images into smaller image patches. Another approach, if applicable, is to look at the 2D image sections separately, and to solve the problem in 2D. Often, the loss of global context makes such approaches less effective; important global information might not be present in the current image patch, or the selected 2D image section. Here, we propose Deep Neural Patchworks (DNP), a segmentation framework that is based on hierarchical and nested stacking of patch-based networks that solves the dilemma between global context and memory limitations.

Published
2022

14. Predictors of Early Neurological Improvement in Patients with Anterior Large Vessel Occlusion and Successful Reperfusion Following Endovascular Thrombectomy—Does CT Perfusion Imaging Matter?

Author

Li, Yan, van Landeghem, Natalie, Demircioglu, Aydin, Köhrmann, Martin, Kellner, Elias, Milles, Lennart, Stolte, Benjamin, Totzeck, Andreas, Dammann, Philipp, Wrede, Karsten, Theysohn, Jens Matthias, Styczen, Hanna, Forsting, Michael, Wanke, Isabel, Frank, Benedikt, and Deuschl, Cornelius

Published
2022
Full Text
View/download PDF

15. Intra-axonal Diffusivity in Brain White Matter

Author

Dhital, Bibek, Reisert, Marco, Kellner, Elias, and Kiselev, Valerij G.

Subjects
Physics - Biological Physics, Physics - Medical Physics
Abstract

Biophysical modeling is the mediator of evaluating the cellular structure of biological tissues using diffusion-weighted MRI. It is however the bottleneck of microstructural MRI. Beyond the complexity of diffusion, the current development is hindered by the fact that biophysical models heavily rely on diffusion-specific properties of diverse cellular compartments that are still unknown and must be measured in vivo. Obtaining such parameters by straightforward fitting is hindered by the degenerated landscape of the likelihood functions, in particular, the signal obtained for multiple diffusion directions and moderate diffusion weighting strength is not enough to estimate these parameters: different parameter constellations explain the signal equally well. The aim of this study is to measure the central parameter of white matter models, namely the intra-axonal water diffusivity in the normal human brain. Proper estimation of this parameter is complicated due to (i) the presence of both intra- and extra-axonal water compartments and (ii) the orientation dispersion of axons. Our measurement involves an efficient suppression of extra-axonal space and all cellular processes oriented outside a narrow cone around the principal fiber direction. This is achieved using a planar water mobility filter -- a strong diffusion weighting that suppresses signal from all molecules that are mobile in the plane transverse to the fiber bundle. Following the planar filter, the diffusivity in the remaining compartment is measured using linear and isotropic weighting. We find the specifically averaged intra-axonal diffusivity $D_0 = 2.25\pm 0.03{\,\rm \mu m^2/ms}$ for the timing of the applied gradients. Extrapolation to the infinite diffusion time gives $D_\infty \approx 2.0{\,\rm \mu m^2/ms}$. This result imposes a strong limitation on the parameter selection for biophysical modeling of diffusion-weighted MRI.

Published
2017

23. Gibbs-Ringing Artifact Removal Based on Local Subvoxel-shifts

Author

Kellner, Elias, Dhital, Bibek, and Reisert, Marco

Subjects
Physics - Medical Physics, Computer Science - Computer Vision and Pattern Recognition
Abstract

Gibbs-ringing is a well known artifact which manifests itself as spurious oscillations in the vicinity of sharp image transients, e.g. at tissue boundaries. The origin can be seen in the truncation of k-space during MRI data-acquisition. Consequently, correction techniques like Gegenbauer reconstruction or extrapolation methods aim at recovering these missing data. Here, we present a simple and robust method which exploits a different view on the Gibbs-phenomena. The truncation in k-space can be interpreted as a convolution with a sinc-function in image space. Hence, the severity of the artifacts depends on how the sinc-function is sampled. We propose to re-interpolate the image based on local, subvoxel shifts to sample the ringing pattern at the zero-crossings of the oscillating sinc-function. With this, the artifact can effectively and robustly be removed with a minimal amount of smoothing., Comment: 8 pages, 7 figures

Published
2015

24. Imaging Markers Derived From MRI-Based Automated Kidney Segmentation: An Analysis of Data From the German National Cohort (NAKO Gesundheitsstudie).

Author

Kellner, Elias, Sekula, Peggy, Reisert, Marco, and Köttgen, Anna

Abstract

Background: Population-wide research on potential new imaging biomarkers of the kidney depends on accurate automated segmentation of the kidney and its compartments (cortex, medulla, and sinus). Methods: We developed a robust deep-learning framework for kidney (sub-)segmentation based on a hierarchical, three-dimensional convolutional neural network (CNN) that was optimized for multiscale problems of combined localization and segmentation. We applied the CNN to abdominal magnetic resonance images from the population-based German National Cohort (NAKO) study. Results: There was good to excellent agreement between the model predictions and manual segmentations. The median values for the body-surface normalized total kidney, cortex, medulla, and sinus volumes of 9934 persons were 158, 115, 43, and 24 mL/m2. Distributions of these markers are provided both for the overall study population and for a subgroup of persons without kidney disease or any associated conditions. Multivariable adjusted regression analyses revealed that diabetes, male sex, and a higher estimated glomerular filtration rate (eGFR) are important predictors of higher total and cortical volumes. Each increase of eGFR by one unit (i.e., 1 mL/min per 1.73 m2 body surface area) was associated with a 0.98 mL/m2 increase in total kidney volume, and this association was significant. Volumes were lower in persons with eGFR-defined chronic kidney disease. Conclusion: The extraction of image-based biomarkers through CNN-based renal sub-segmentation using data from a population-based study yields reliable results, forming a solid foundation for future investigations. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

33. Cerebellar, Not Nigrostriatal Degeneration Impairs Dexterity in Multiple System Atrophy.

Author

Rau, Alexander, Hosp, Jonas A., Rijntjes, Michel, Weiller, Cornelius, Kellner, Elias, Berberovic, Emir, Oikonomou, Panteleimon, Jost, Wolfgang H., Reisert, Marco, Urbach, Horst, and Schröter, Nils

Abstract

Background: Multiple system atrophy (MSA) clinically manifests with either predominant nigrostriatal or cerebellopontine degeneration. This corresponds to two different phenotypes, one with predominant Parkinson's symptoms (MSA‐P [multiple system atrophy‐parkinsonian subtype]) and one with predominant cerebellar deficits (MSA‐C [multiple system atrophy‐cerebellar subtype]). Both nigrostriatal and cerebellar degeneration can lead to impaired dexterity, which is a frequent cause of disability in MSA. Objective: The aim was to disentangle the contribution of nigrostriatal and cerebellar degeneration to impaired dexterity in both subtypes of MSA. Methods: We thus investigated nigrostriatal and cerebellopontine integrity using diffusion microstructure imaging in 47 patients with MSA‐P and 17 patients with MSA‐C compared to 31 healthy controls (HC). Dexterity was assessed using the 9‐Hole Peg Board (9HPB) performance. Results: Nigrostriatal degeneration, represented by the loss of cells and neurites, leading to a larger free‐fluid compartment, was present in MSA‐P and MSA‐C when compared to HCs. Whereas no intergroup differences were observed between the MSAs in the substantia nigra, MSA‐P showed more pronounced putaminal degeneration than MSA‐C. In contrast, a cerebellopontine axonal degeneration was observed in MSA‐P and MSA‐C, with stronger effects in MSA‐C. Interestingly, the degeneration of cerebellopontine fibers is associated with impaired dexterity in both subtypes, whereas no association was observed with nigrostriatal degeneration. Conclusion: Cerebellar dysfunction contributes to impaired dexterity not only in MSA‐C but also in MSA‐P and may be a promising biomarker for disease staging. In contrast, no significant association was observed with nigrostriatal dysfunction. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

35. ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI

Author

Maier, Oskar, Menze, Bjoern H., von der Gablentz, Janina, Häni, Levin, Heinrich, Mattias P., Liebrand, Matthias, Winzeck, Stefan, Basit, Abdul, Bentley, Paul, Chen, Liang, Christiaens, Daan, Dutil, Francis, Egger, Karl, Feng, Chaolu, Glocker, Ben, Götz, Michael, Haeck, Tom, Halme, Hanna-Leena, Havaei, Mohammad, Iftekharuddin, Khan M., Jodoin, Pierre-Marc, Kamnitsas, Konstantinos, Kellner, Elias, Korvenoja, Antti, Larochelle, Hugo, Ledig, Christian, Lee, Jia-Hong, Maes, Frederik, Mahmood, Qaiser, Maier-Hein, Klaus H., McKinley, Richard, Muschelli, John, Pal, Chris, Pei, Linmin, Rangarajan, Janaki Raman, Reza, Syed M.S., Robben, David, Rueckert, Daniel, Salli, Eero, Suetens, Paul, Wang, Ching-Wei, Wilms, Matthias, Kirschke, Jan S., Krämer, Ulrike M., Münte, Thomas F., Schramm, Peter, Wiest, Roland, Handels, Heinz, and Reyes, Mauricio

Published
2017
Full Text
View/download PDF

39. Where Position Matters - Deep-Learning-Driven Normalization and Coregistration of Computed Tomography in the Postoperative Analysis of Deep Brain Stimulation

Author

Reisert, Marco, Sajonz, Bastian E.A., Brugger, Timo S., Reinacher, Peter Christoph, Russe, Maximilian F., Kellner, Elias, Skibbe, Henrik, Coenen, Volker A., and Publica

Subjects
lead localization, image data aggregation, deep learning, magnetic resonance imaging, Computed tomography, deep brain stimulation
Abstract

Introduction: Recent developments in the postoperative evaluation of deep brain stimulation surgery on the group level warrant the detection of achieved electrode positions based on postoperative imaging. Computed tomography (CT) is a frequently used imaging modality, but because of its idiosyncrasies (high spatial accuracy at low soft tissue resolution), it has not been sufficient for the parallel determination of electrode position and details of the surrounding brain anatomy (nuclei). The common solution is rigid fusion of CT images and magnetic resonance (MR) images, which have much better soft tissue contrast and allow accurate normalization into template spaces. Here, we explored a deep-learning approach to directly relate positions (usually the lead position) in postoperative CT images to the native anatomy of the midbrain and group space. Materials and Methods: Deep learning is used to create derived tissue contrasts (white matter, gray matter, cerebrospinal fluid, brainstem nuclei) based on the CT image; that is, a convolution neural network (CNN) takes solely the raw CT image as input and outputs several tissue probability maps. The ground truth is based on coregistrations with MR contrasts. The tissue probability maps are then used to either rigidly coregister or normalize the CT image in a deformable way to group space. The CNN was trained in 220 patients and tested in a set of 80 patients. Results: Rigorous validation of such an approach is difficult because of the lack of ground truth. We examined the agreements between the classical and proposed approaches and considered the spread of implantation locations across a group of identically implanted subjects, which serves as an indicator of the accuracy of the lead localization procedure. The proposed procedure agrees well with current magnetic resonance imaging–based techniques, and the spread is comparable or even lower. Conclusions: Postoperative CT imaging alone is sufficient for accurate localization of the midbrain nuclei and normalization to the group space. In the context of group analysis, it seems sufficient to have a single postoperative CT image of good quality for inclusion. The proposed approach will allow researchers and clinicians to include cases that were not previously suitable for analysis.

Published
2023

40. MesoFT: Unifying Diffusion Modelling and Fiber Tracking

Author

Reisert, Marco, Kiselev, V. G., Dihtal, Bibek, Kellner, Elias, Novikov, D. S., Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Kobsa, Alfred, Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Golland, Polina, editor, Hata, Nobuhiko, editor, Barillot, Christian, editor, Hornegger, Joachim, editor, and Howe, Robert, editor

Published
2014
Full Text
View/download PDF

41. Differentiation of Perilesional Edema in Glioblastomas and Brain Metastases: Comparison of Diffusion Tensor Imaging, Neurite Orientation Dispersion and Density Imaging and Diffusion Microstructure Imaging

Author

Würtemberger, Urs, primary, Rau, Alexander, additional, Reisert, Marco, additional, Kellner, Elias, additional, Diebold, Martin, additional, Erny, Daniel, additional, Reinacher, Peter C., additional, Hosp, Jonas A., additional, Hohenhaus, Marc, additional, Urbach, Horst, additional, and Demerath, Theo, additional

Published
2022
Full Text
View/download PDF

46. Quantification of Left Atrial Size and Function in Cardiac MR in Correlation to Non-Gated MR and Cardiovascular Risk Factors in Subjects without Cardiovascular Disease: A Population-Based Cohort Study

Author

Kulka, Charlotte, primary, Lorbeer, Roberto, additional, Askani, Esther, additional, Kellner, Elias, additional, Reisert, Marco, additional, von Krüchten, Ricarda, additional, Rospleszcz, Susanne, additional, Hasic, Dunja, additional, Peters, Annette, additional, Bamberg, Fabian, additional, and Schlett, Christopher L., additional

Published
2022
Full Text
View/download PDF

47. Effect of surface-partial-volume correction and adaptive threshold on segmentation of uroliths in computed tomography.

Author

Neubauer, Jakob, Wilhelm, Konrad, Gratzke, Christian, Bamberg, Fabian, Reisert, Marco, and Kellner, Elias

Subjects
COMPUTED tomography, ABSOLUTE value, URINARY calculi, STATISTICS, UROLOGISTS, ADAPTIVE optics
Abstract

Computed tomography (CT) is used to diagnose urolithiasis, a prevalent condition. In order to establish the strongest foundation for the quantifiability of urolithiasis, this study aims to develop semi-automated urolithiasis segmentation methods for CT images that differ in terms of surface-partial-volume correction and adaptive thresholding. It also examines the diagnostic accuracy of these methods in terms of volume and maximum stone diameter. One hundred and one uroliths were positioned in an anthropomorphic phantom and prospectively examined in CT. Four different segmentation methods were developed and used to segment the uroliths semi-automatically based on CT images. Volume and maximum diameter were calculated from the segmentations. Volume and maximum diameter of the uroliths were measured independently by three urologists by means of electronic calipers. The average value of the urologists´ measurements was used as a reference standard. Statistical analysis was performed with multivariate Bartlett's test. Volume and maximum diameter were in very good agreement with the reference measurements (r>0.99) and the diagnostic accuracy of all segmentation methods used was very high. Regarding the diagnostic accuracy no difference could be detected between the different segmentation methods tested (p>0.55). All four segmentation methods allow for accurate characterization of urolithiasis in CT with respect to volume and maximum diameter of uroliths. Thus, a simple thresholding approach with an absolute value may suffice for robust determination of volume and maximum diameter in urolithiasis. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

48. Widespread white matter oedema in subacute COVID-19 patients with neurological symptoms

Author

Rau, Alexander, primary, Schroeter, Nils, additional, Blazhenets, Ganna, additional, Dressing, Andrea, additional, Walter, Lea I, additional, Kellner, Elias, additional, Bormann, Tobias, additional, Mast, Hansjörg, additional, Wagner, Dirk, additional, Urbach, Horst, additional, Weiller, Cornelius, additional, Meyer, Philipp T, additional, Reisert, Marco, additional, and Hosp, Jonas A, additional

Published
2022
Full Text
View/download PDF

50. Association of MRI‐based adrenal gland volume and impaired glucose metabolism in a population‐based cohort study

Author

Askani, Esther, primary, Rospleszcz, Susanne, additional, Lorbeer, Roberto, additional, Kulka, Charlotte, additional, von Krüchten, Ricarda, additional, Müller‐Peltzer, Katharina, additional, Hasic, Dunja, additional, Kellner, Elias, additional, Reisert, Marco, additional, Rathmann, Wolfgang, additional, Peters, Annette, additional, Schlett, Christopher L., additional, Bamberg, Fabian, additional, and Storz, Corinna, additional

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results