Search

Your search keyword '"Schock, Justus"' showing total 48 results
Start Over Author "Schock, Justus"
48 results on '"Schock, Justus"'

1. A self-supervised, physics-aware, Bayesian neural network architecture for modelling galaxy emission-line kinematics

Author

Dawson, James M., Davis, Timothy A., Gomez, Edward L., and Schock, Justus

Subjects
Astrophysics - Astrophysics of Galaxies
Abstract

In the upcoming decades large facilities, such as the SKA, will provide resolved observations of the kinematics of millions of galaxies. In order to assist in the timely exploitation of these vast datasets we explore the use of a self-supervised, physics aware neural network capable of Bayesian kinematic modelling of galaxies. We demonstrate the network's ability to model the kinematics of cold gas in galaxies with an emphasis on recovering physical parameters and accompanying modelling errors. The model is able to recover rotation curves, inclinations and disc scale lengths for both CO and HI data which match well with those found in the literature. The model is also able to provide modelling errors over learned parameters thanks to the application of quasi-Bayesian Monte-Carlo dropout. This work shows the promising use of machine learning, and in particular self-supervised neural networks, in the context of kinematically modelling galaxies. This work represents the first steps in applying such models for kinematic fitting and we propose that variants of our model would seem especially suitable for enabling emission-line science from upcoming surveys with e.g. the SKA, allowing fast exploitation of these large datasets.

Published
2021
Full Text
View/download PDF

2. Using machine learning to study the kinematics of cold gas in galaxies

Author

Dawson, James M., Davis, Timothy A., Gomez, Edward L., Schock, Justus, Zabel, Nikki, and Williams, Thomas G.

Subjects
Astrophysics - Astrophysics of Galaxies
Abstract

Next generation interferometers, such as the Square Kilometre Array, are set to obtain vast quantities of information about the kinematics of cold gas in galaxies. Given the volume of data produced by such facilities astronomers will need fast, reliable, tools to informatively filter and classify incoming data in real time. In this paper, we use machine learning techniques with a hydrodynamical simulation training set to predict the kinematic behaviour of cold gas in galaxies and test these models on both simulated and real interferometric data. Using the power of a convolutional autoencoder we embed kinematic features, unattainable by the human eye or standard tools, into a three-dimensional space and discriminate between disturbed and regularly rotating cold gas structures. Our simple binary classifier predicts the circularity of noiseless, simulated, galaxies with a recall of $85\%$ and performs as expected on observational CO and HI velocity maps, with a heuristic accuracy of $95\%$. The model output exhibits predictable behaviour when varying the level of noise added to the input data and we are able to explain the roles of all dimensions of our mapped space. Our models also allow fast predictions of input galaxies' position angles with a $1\sigma$ uncertainty range of $\pm17^{\circ}$ to $\pm23^{\circ}$ (for galaxies with inclinations of $82.5^{\circ}$ to $32.5^{\circ}$, respectively), which may be useful for initial parameterisation in kinematic modelling samplers. Machine learning models, such as the one outlined in this paper, may be adapted for SKA science usage in the near future., Comment: 15 pages, 11 figures

Published
2019
Full Text
View/download PDF

3. Radiomic Feature Stability Analysis based on Probabilistic Segmentations

Author

Haarburger, Christoph, Schock, Justus, Truhn, Daniel, Weitz, Philippe, Mueller-Franzes, Gustav, Weninger, Leon, and Merhof, Dorit

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Identifying image features that are robust with respect to segmentation variability and domain shift is a tough challenge in radiomics. So far, this problem has mainly been tackled in test-retest analyses. In this work we analyze radiomics feature stability based on probabilistic segmentations. Based on a public lung cancer dataset, we generate an arbitrary number of plausible segmentations using a Probabilistic U-Net. From these segmentations, we extract a high number of plausible feature vectors for each lung tumor and analyze feature variance with respect to the segmentations. Our results suggest that there are groups of radiomic features that are more (e.g. statistics features) and less (e.g. gray-level size zone matrix features) robust against segmentation variability. Finally, we demonstrate that segmentation variance impacts the performance of a prognostic lung cancer survival model and propose a new and potentially more robust radiomics feature selection workflow., Comment: accepted at ISBI 2020

Published
2019

4. Super-realtime facial landmark detection and shape fitting by deep regression of shape model parameters

Author

Kopaczka, Marcin, Schock, Justus, and Merhof, Dorit

Subjects
Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

We present a method for highly efficient landmark detection that combines deep convolutional neural networks with well established model-based fitting algorithms. Motivated by established model-based fitting methods such as active shapes, we use a PCA of the landmark positions to allow generative modeling of facial landmarks. Instead of computing the model parameters using iterative optimization, the PCA is included in a deep neural network using a novel layer type. The network predicts model parameters in a single forward pass, thereby allowing facial landmark detection at several hundreds of frames per second. Our architecture allows direct end-to-end training of a model-based landmark detection method and shows that deep neural networks can be used to reliably predict model parameters directly without the need for an iterative optimization. The method is evaluated on different datasets for facial landmark detection and medical image segmentation. PyTorch code is freely available at https://github.com/justusschock/shapenet, Comment: https://github.com/justusschock/shapenet

Published
2019

5. Probabilistic Image Diversification to Improve Segmentation in 3D Microscopy Image Data

Author

Eschweiler, Dennis, Schock, Justus, Stegmaier, Johannes, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Zhao, Can, editor, Svoboda, David, editor, Wolterink, Jelmer M., editor, and Escobar, Maria, editor

Published
2022
Full Text
View/download PDF

7. Adaptive Preprocessing for Generalization in Cardiac MR Image Segmentation

Author

Khader, Firas, Schock, Justus, Truhn, Daniel, Morsbach, Fabian, Haarburger, Christoph, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Puyol Anton, Esther, editor, Pop, Mihaela, editor, Sermesant, Maxime, editor, Campello, Victor, editor, Lalande, Alain, editor, Lekadir, Karim, editor, Suinesiaputra, Avan, editor, Camara, Oscar, editor, and Young, Alistair, editor

Published
2021
Full Text
View/download PDF

11. A Method for Semantic Knee Bone and Cartilage Segmentation with Deep 3D Shape Fitting Using Data from the Osteoarthritis Initiative

Author

Schock, Justus, Kopaczka, Marcin, Agthe, Benjamin, Huang, Jie, Kruse, Paul, Truhn, Daniel, Conrad, Stefan, Antoch, Gerald, Kuhl, Christiane, Nebelung, Sven, Merhof, Dorit, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Reuter, Martin, editor, Wachinger, Christian, editor, Lombaert, Hervé, editor, Paniagua, Beatriz, editor, Goksel, Orcun, editor, and Rekik, Islem, editor

Published
2020
Full Text
View/download PDF

15. Combined Learning for Similar Tasks with Domain-Switching Networks

Author

Bug, Daniel, Eschweiler, Dennis, Liu, Qianyu, Schock, Justus, Weninger, Leon, Feuerhake, Friedrich, Schüler, Julia, Stegmaier, Johannes, Merhof, Dorit, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Shen, Dinggang, editor, Liu, Tianming, editor, Peters, Terry M., editor, Staib, Lawrence H., editor, Essert, Caroline, editor, Zhou, Sean, editor, Yap, Pew-Thian, editor, and Khan, Ali, editor

Published
2019
Full Text
View/download PDF

23. Monoplanar CT Reconstruction with GANs

Author

Schock, Justus, primary, Lan, Yu-Chia, additional, Truhn, Daniel, additional, Kopaczka, Marcin, additional, Conrad, Stefan, additional, Nebelung, Sven, additional, and Merhof, Dorit, additional

Published
2022
Full Text
View/download PDF

25. TorchMetrics - Measuring Reproducibility in PyTorch

Author

Detlefsen, Nicki, primary, Borovec, Jiri, additional, Schock, Justus, additional, Jha, Ananya, additional, Koker, Teddy, additional, Di Liello, Luca, additional, Stancl, Daniel, additional, Quan, Changsheng, additional, Grechkin, Maxim, additional, and Falcon, William, additional

Published
2022
Full Text
View/download PDF

27. Micro- and Macroscale Assessment of Posterior Cruciate Ligament Functionality Based on Advanced MRI Techniques

Author

Wilms, Lena Marie, Radke, Karl Ludger, Abrar, Daniel Benjamin, Latz, David, Schock, Justus, Frenken, Miriam, Windolf, Joachim, Antoch, Gerald, Filler, Timm Joachim, and Nebelung, Sven

Subjects
loading, Medicine (General), R5-920, quantitative imaging, magnetic resonance imaging, posterior cruciate ligament, posterior drawer test, musculoskeletal system, knee joint stability, Article
Abstract

T2 mapping assesses tissue ultrastructure and composition, yet the association of imaging features and tissue functionality is oftentimes unclear. This study aimed to elucidate this association for the posterior cruciate ligament (PCL) across the micro- and macroscale and as a function of loading. Ten human cadaveric knee joints were imaged using a clinical 3.0T scanner and high-resolution morphologic and T2 mapping sequences. Emulating the posterior drawer test, the joints were imaged in the unloaded (δ0) and loaded (δ1) configurations. For the entire PCL, its subregions, and its osseous insertion sites, loading-induced changes were parameterized as summary statistics and texture variables, i.e., entropy, homogeneity, contrast, and variance. Histology confirmed structural integrity. Statistical analysis was based on parametric and non-parametric tests. Mean PCL length (37.8 ± 1.8 mm [δ0]; 44.0 ± 1.6 mm [δ1] [p < 0.01]), mean T2 (35.5 ± 2.0 ms [δ0]; 37.9 ± 1.3 ms [δ1] [p = 0.01]), and mean contrast values (4.0 ± 0.6 [δ0]; 4.9 ± 0.9 [δ1] [p = 0.01]) increased significantly under loading. Other texture features or ligamentous, osseous, and meniscal structures remained unaltered. Beyond providing normative T2 values across various scales and configurations, this study suggests that ligaments can be imaged morphologically and functionally based on joint loading and advanced MRI acquisition and post-processing techniques to assess ligament integrity and functionality in variable diagnostic contexts.

Published
2021

28. In-Situ Cartilage Functionality Assessment Based on Advanced MRI Techniques and Precise Compartmental Knee Joint Loading through Varus and Valgus Stress

Author

Said, Oliver, Schock, Justus, Abrar, Daniel Benjamin, Schad, Philipp, Kuhl, Christiane, Nolte, Teresa, Knobe, Matthias, Prescher, Andreas, Truhn, Daniel, and Nebelung, Sven

Subjects
body regions, musculoskeletal diseases, knee joint, Medicine (General), loading, valgus, R5-920, varus, stress MRI, musculoskeletal system, cartilage, Article
Abstract

Stress MRI brings together mechanical loading and MRI in the functional assessment of cartilage and meniscus, yet lacks basic scientific validation. This study assessed the response-to-loading patterns of cartilage and meniscus incurred by standardized compartmental varus and valgus loading of the human knee joint. Eight human cadaveric knee joints underwent imaging by morphologic (i.e., proton density-weighted fat-saturated and 3D water-selective) and quantitative (i.e., T1ρ and T2 mapping) sequences, both unloaded and loaded to 73.5 N, 147.1 N, and 220.6 N of compartmental pressurization. After manual segmentation of cartilage and meniscus, morphometric measures and T2 and T1ρ relaxation times were quantified. CT-based analysis of joint alignment and histologic and biomechanical tissue measures served as references. Under loading, we observed significant decreases in cartilage thickness (p &lt, 0.001 (repeated measures ANOVA)) and T1ρ relaxation times (p = 0.001, medial meniscus, lateral tibia, (Friedman test)), significant increases in T2 relaxation times (p ≤ 0.004, medial femur, lateral tibia, (Friedman test)), and adaptive joint motion. In conclusion, varus and valgus stress MRI induces meaningful changes in cartilage and meniscus secondary to compartmental loading that may be assessed by cartilage morphometric measures as well as T2 and T1ρ mapping as imaging surrogates of tissue functionality.

Published
2021
Full Text
View/download PDF

29. Comprehensive Assessment of Medial Knee Joint Instability by Valgus Stress MRI

Author

Ciba, Malin, Winkelmeyer, Eva-Maria, Schock, Justus, Schad, Philipp, Kotowski, Niklas, Nolte, Teresa, Wollschläger, Lena Marie, Knobe, Matthias, Prescher, Andreas, Kuhl, Christiane, Truhn, Daniel, and Nebelung, Sven

Subjects
musculoskeletal diseases, knee joint, medial collateral ligament, Medicine (General), R5-920, valgus stress, anterior cruciate ligament, magnetic resonance imaging, musculoskeletal system, human activities, functionality, Article, biomechanics
Abstract

Diagnostics : open access journal 11(8), 1433 (2021). doi:10.3390/diagnostics11081433 special issue: "Special issue "Advanced MRI techniques for musculoskeletal imaging" / special issue editor: Sven Nebelung, guest editor", Published by MDPI, Basel

Published
2021
Full Text
View/download PDF

30. Longitudinal T2 Mapping and Texture Feature Analysis in the Detection and Monitoring of Experimental Post-Traumatic Cartilage Degeneration

Author

Huppertz, Marc Sebastian, Schock, Justus, Radke, Karl Ludger, Abrar, Daniel Benjamin, Post, Manuel, Kuhl, Christiane, Truhn, Daniel, and Nebelung, Sven

Subjects
T2 mapping, ddc:570, posttraumatic osteoarthritis, lcsh:Q, focal cartilage defect, cartilage, lcsh:Science, Article, texture analysis
Abstract

Life : open access journal 11(3), 201 (2021). doi:10.3390/life11030201 special issue: "Special Issue "Focal Chondral Defects" / Special Issue Editors: Dr. Filippo Migliorini, Guest Editor; Prof. Dr. Nicola Maffulli, Guest Editor", Published by MDPI, Basel

Published
2021
Full Text
View/download PDF

31. Seeing Beyond Morphology-Standardized Stress MRI to Assess Human Knee Joint Instability

Author

Winkelmeyer, Eva-Maria, Schock, Justus, Wollschläger, Lena Marie, Schad, Philipp, Huppertz, Marc Sebastian, Kotowski, Niklas, Prescher, Andreas, Kuhl, Christiane, Truhn, Daniel, and Nebelung, Sven

Subjects
knee joint, Medicine (General), R5-920, anterior cruciate ligament, physiology, magnetic resonance imaging, musculoskeletal system, Article, biomechanical phenomena
Abstract

Diagnostics : open access journal 11(6), 1035 (2021). doi:10.3390/diagnostics11061035 special issue: "Special issue "Advanced MRI techniques for musculoskeletal imaging" / special issue editor: Sven Nebelung, guest editor", Published by MDPI, Basel

Published
2021
Full Text
View/download PDF

32. Deep Learning-Based Post-Processing of Real-Time MRI to Assess and Quantify Dynamic Wrist Movement in Health and Disease

Author

Radke, Karl Ludger, primary, Wollschläger, Lena Marie, additional, Nebelung, Sven, additional, Abrar, Daniel Benjamin, additional, Schleich, Christoph, additional, Boschheidgen, Matthias, additional, Frenken, Miriam, additional, Schock, Justus, additional, Klee, Dirk, additional, Frahm, Jens, additional, Antoch, Gerald, additional, Thelen, Simon, additional, Wittsack, Hans-Jörg, additional, and Müller-Lutz, Anja, additional

Published
2021
Full Text
View/download PDF

44. Introducing CNN-Based Mouse Grim Scale Analysis for Fully Automated Image-Based Assessment of Distress in Laboratory Mice

Author

Kopaczka, Marcin, Ernst, Lisa, Schock, Justus, Schneuing, Arne, Guth, Alexander, Tolba, Rene, and Merhof, Dorit

Abstract

International standards require close monitoring of distress of animals undergoing laboratory experiments in order to minimize the stress level and allow choosing minimally stressful procedures for the experiments. Currently, one of the the best established severity assessment procedures is the mouse grimace scale (MGS), a protocol in which images of the animals are taken and scored by assessing five key visual features that have been shown to be highly correlated with distress and pain. While proven to be highly reliable, MGS assessment is currently a time-consuming task requiring manual video processing for key frame extraction and subsequent expert grading. Additionally, due to the the high per-picture expert time required, MGS scoring is performed on a small number of selected frames from a video. To address these shortcomings, we introduce a method for fully automated real-time MGS scoring of orbital eye tightening, one of the five sub-scores. We define and evaluate the method which is centered around a set of convolutional neural networks (CNNs) and allows live continuous MGS assessment of a mouse in real time. We additionally describe a multithreaded client-server architecture with a graphical user interface that allows convenient use of the developed method for simultaneous real-time MGS scoring of several animals., Eurographics Workshop on Visual Computing for Biology and Medicine, Head and Brain, 101, 106, Marcin Kopaczka, Lisa Ernst, Justus Schock, Arne Schneuing, Alexander Guth, Rene Tolba, and Dorit Merhof

Published
2018
Full Text
View/download PDF

46. Using machine learning to study the kinematics of cold gas in galaxies.

Author

Dawson, James M, Davis, Timothy A, Gomez, Edward L, Schock, Justus, Zabel, Nikki, and Williams, Thomas G

Subjects
COLD gases, MACHINE learning, KINEMATICS, GALAXIES, GALACTIC evolution
Abstract

Next generation interferometers, such as the Square Kilometre Array, are set to obtain vast quantities of information about the kinematics of cold gas in galaxies. Given the volume of data produced by such facilities astronomers will need fast, reliable, tools to informatively filter and classify incoming data in real time. In this paper, we use machine learning techniques with a hydrodynamical simulation training set to predict the kinematic behaviour of cold gas in galaxies and test these models on both simulated and real interferometric data. Using the power of a convolutional autoencoder we embed kinematic features, unattainable by the human eye or standard tools, into a 3D space and discriminate between disturbed and regularly rotating cold gas structures. Our simple binary classifier predicts the circularity of noiseless, simulated, galaxies with a recall of 85% and performs as expected on observational CO and H  i velocity maps, with a heuristic accuracy of 95%. The model output exhibits predictable behaviour when varying the level of noise added to the input data and we are able to explain the roles of all dimensions of our mapped space. Our models also allow fast predictions of input galaxies' position angles with a 1σ uncertainty range of ±17° to ±23° (for galaxies with inclinations of 82.5° to 32.5°, respectively), which may be useful for initial parametrization in kinematic modelling samplers. Machine learning models, such as the one outlined in this paper, may be adapted for SKA science usage in the near future. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

47. Automated Analysis of Alignment in Long-Leg Radiographs by Using a Fully Automated Support System Based on Artificial Intelligence.

Author

Schock J, Truhn D, Abrar DB, Merhof D, Conrad S, Post M, Mittelstrass F, Kuhl C, and Nebelung S

Abstract

Purpose: To develop and validate a deep learning-based method for automatic quantitative analysis of lower-extremity alignment., Materials and Methods: In this retrospective study, bilateral long-leg radiographs (LLRs) from 255 patients that were obtained between January and September of 2018 were included. For training data ( n = 109), a U-Net convolutional neural network was trained to segment the femur and tibia versus manual segmentation. For validation data ( n = 40), model parameters were optimized. Following identification of anatomic landmarks, anatomic and mechanical axes were identified and used to quantify alignment through the hip-knee-ankle angle (HKAA) and femoral anatomic-mechanical angle (AMA). For testing data ( n = 106), algorithm-based angle measurements were compared with reference measurements by two radiologists. Angles and time for 30 random radiographs were compared by using repeated-measures analysis of variance and one-way analysis of variance, whereas correlations were quantified by using Pearson r and intraclass correlation coefficients., Results: Bilateral LLRs of 255 patients (mean age, 26 years ± 23 [standard deviation]; range, 0-88 years; 157 male patients) were included. Mean Sørensen-Dice coefficients for segmentation were 0.97 ± 0.09 for the femur and 0.96 ± 0.11 for the tibia. Mean HKAAs and AMAs as measured by the readers and the algorithm ranged from 0.05° to 0.11° ( P = .5) and from 4.82° to 5.43° ( P < .001). Interreader correlation coefficients ranged from 0.918 to 0.995 ( r range, P < .001), and agreement was almost perfect (intraclass correlation coefficient range, 0.87-0.99). Automatic analysis was faster than the two radiologists' manual measurements (3 vs 36 vs 35 seconds, P < .001)., Conclusion: Fully automated analysis of LLRs yielded accurate results across a wide range of clinical and pathologic indications and is fast enough to enhance and accelerate clinical workflows. Supplemental material is available for this article. © RSNA, 2020See also commentary by Andreisek in this issue., Competing Interests: Disclosures of Conflicts of Interest: J.S. disclosed no relevant relationships. D.T. disclosed no relevant relationships. D.B.A. disclosed no relevant relationships. D.M. disclosed no relevant relationships. S.C. disclosed no relevant relationships. M.P. disclosed no relevant relationships. F.M. disclosed no relevant relationships. C.K. disclosed no relevant relationships. S.N. disclosed no relevant relationships., (2021 by the Radiological Society of North America, Inc.)

Published
2020
Full Text
View/download PDF

48. Assessment of Laboratory Mouse Activity in Video Recordings Using Deep Learning Methods.

Author

Kopaczka M, Tillmann D, Ernst L, Schock J, Tolba R, and Merhof D

Subjects
Algorithms, Animals, Mice, Behavior, Animal, Deep Learning, Neural Networks, Computer, Video Recording
Abstract

Analysis of laboratory animal behavior allows assessment of animal wellbeing. We present a method for the classification of different activities of laboratory mice by analyzing video clips using three deep learning methods. Animals placed in observation cages are filmed and short video clips are labelled as belonging to one of five defined behaviors. Subsequently, three different methods based on convolutional neural networks (CNNS) are applied to classify the clips. The best performing method - a two-stream network that analyzes individual frames as well as the video's optical flow - achieves an accuracy of 86.4%, including detection of important behavioral patterns such as self-grooming. These results show that the presented analysis protocol allows automated assessment of animal behavior by algorithmic analysis of videos of mice on observation boxes.

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results