@inproceedings{OksuzMukhopadhyayBevilacquaetal.2015, author = {Oksuz, Ilkay and Mukhopadhyay, Anirban and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Dictionary Learning Based Image Descriptor for Myocardial Registration of CP-BOLD MR}, volume = {9350}, booktitle = {Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015}, publisher = {Springer}, doi = {10.1007/978-3-319-24571-3_25}, pages = {205 -- 213}, year = {2015}, abstract = {Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP- BOLD) MRI is a new contrast agent- and stress-free imaging technique for the assessment of myocardial ischemia at rest. The precise registration among the cardiac phases in this cine type acquisition is essential for automating the analysis of images of this technique, since it can potentially lead to better specificity of ischemia detection. However, inconsistency in myocardial intensity patterns and the changes in myocardial shape due to the heart's motion lead to low registration performance for state- of-the-art methods. This low accuracy can be explained by the lack of distinguishable features in CP-BOLD and inappropriate metric defini- tions in current intensity-based registration frameworks. In this paper, the sparse representations, which are defined by a discriminative dictionary learning approach for source and target images, are used to improve myocardial registration. This method combines appearance with Gabor and HOG features in a dictionary learning framework to sparsely represent features in a low dimensional space. The sum of squared differences of these distinctive sparse representations are used to define a similarity term in the registration framework. The proposed descriptor is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canines.}, language = {en} } @inproceedings{SalehSahuZafaretal.2015, author = {Saleh, Salah and Sahu, Manish and Zafar, Zuhair and Berns, Karsten}, title = {A Multimodal Nonverbal Human-robot Communication System}, booktitle = {VI International Conference on Computational Bioengineering}, year = {2015}, abstract = {Socially interactive robot needs the same behaviors and capabilities of human to be accepted as a member in human society. The environment, in which this robot should operate, is the human daily life. The interaction capabilities of current robots are still limited due to complex inter-human interaction system. Humans usually use different types of verbal and nonverbal cues in their communication. Facial expression and head movement are good examples of nonverbal cues used in feedback. This paper presents a biological inspired system for Human-Robot Interaction (HRI). This system is based on the interactive model of inter-human communication proposed by Schramm. In this model, the robot and its interaction partner can be send and receive information at the same time. For example, if the robot is talking, it also perceive the feedback of the human via his/her nonverbal cues. In this work, we are focusing on recognizing the facial expression of human. The proposed facial expression recognition technique is based on machine learning. Multi SVMs have been used to recognize the six basic emotions in addition to the neutral expression. This technique uses only the depth information, acquired by Kinect, of human face.}, language = {en} } @inproceedings{JacomeEggelerPoethkowetal.2015, author = {J{\´a}come, Leonardo Agudo and Eggeler, Gunter and P{\"o}thkow, Kai and Paetsch, Olaf and Hege, Hans-Christian}, title = {Three-Dimensional Characterization of Superdislocation Interactions in the High Temperature and Low Stress Creep Regime of Ni-Base Superalloy Single Crystals}, booktitle = {Proceedings of CREEP 2015 - 13th International Conference on Creep and Fracture of Engineering Materials and Structures, May 31 - June 4, 2015, Toulouse, France}, pages = {16 -- 17}, year = {2015}, abstract = {Monocrystaline Ni-base superalloys are the material of choice for first row blades in jet engine gas turbines. Using a novel visualization tool for 3D reconstruction and visualization of dislocation line segments from stereo-pairs of scanning transmission electron microscopies, the superdislocation substructures in Ni-base superalloy LEK 94 (crept to ε = 26\%) are characterized. Probable scenarios are discussed, how these dislocation substructures form.}, language = {en} } @inproceedings{TackKobayashiGaueretal.2015, author = {Tack, Alexander and Kobayashi, Yuske and Gauer, Tobias and Schlaefer, Alexander and Werner, Ren{\´e}}, title = {Groupwise Registration for Robust Motion Field Estimation in Artifact-Affected 4D CT Images}, booktitle = {ICART: Imaging and Computer Assistance in Radiation Therapy: A workshop held on Friday 9th October as part of MICCAI 2015 in Munich, Germany. MICCAI workshop. 2015.}, pages = {18 -- 25}, year = {2015}, abstract = {Precise voxel trajectory estimation in 4D CT images is a prerequisite for reliable dose accumulation during 4D treatment planning. 4D CT image data is, however, often affected by motion artifacts and applying standard pairwise registration to such data sets bears the risk of aligning anatomical structures to artifacts - with physiologically unrealistic trajectories being the consequence. In this work, the potential of a novel non-linear hybrid intensity- and feature-based groupwise registration method for robust motion field estimation in artifact-affected 4D CT image data is investigated. The overall registration performance is evaluated on the DIR-lab datasets; Its robustness if applied to artifact-affected data sets is analyzed using clinically acquired data sets with and without artifacts. The proposed registration approach achieves an accuracy comparable to the state-of-the-art (subvoxel accuracy), but smoother voxel trajectories compared to pairwise registration. Even more important: it maintained accuracy and trajectory smoothness in the presence of image artifacts - in contrast to standard pairwise registration, which yields higher landmark-based registration errors and a loss of trajectory smoothness when applied to artifact-affected data sets.}, language = {en} } @inproceedings{PaetschBaumProhaskaetal.2015, author = {Paetsch, Olaf and Baum, Daniel and Prohaska, Steffen and Ehrig, Karsten and Meinel, Dietmar and Ebell, Gino}, title = {3D Corrosion Detection in Time-dependent CT Images of Concrete}, booktitle = {DIR-2015 Proceedings}, year = {2015}, abstract = {In civil engineering, the corrosion of steel reinforcements in structural elements of concrete bares a risk of stability-reduction, mainly caused by the exposure to chlorides. 3D computed tomography (CT) reveals the inner structure of concrete and allows one to investigate the corrosion with non-destructive testing methods. To carry out such investigations, specimens with a large artificial crack and an embedded steel rebar have been manufactured. 3D CT images of those specimens were acquired in the original state. Subsequently three cycles of electrochemical pre-damaging together with CT imaging were applied. These time series have been evaluated by means of image processing algorithms to segment and quantify the corrosion products. Visualization of the results supports the understanding of how corrosion propagates into cracks and pores. Furthermore, pitting of structural elements can be seen without dismantling. In this work, several image processing and visualization techniques are presented that have turned out to be particularly effective for the visualization and segmentation of corrosion products. Their combination to a workflow for corrosion analysis is the main contribution of this work.}, language = {en} } @inproceedings{HanikHegevonTycowicz2022, author = {Hanik, Martin and Hege, Hans-Christian and von Tycowicz, Christoph}, title = {A Nonlinear Hierarchical Model for Longitudinal Data on Manifolds}, booktitle = {2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)}, arxiv = {http://arxiv.org/abs/2202.01180}, doi = {10.1109/ISBI52829.2022.9761465}, pages = {1 -- 5}, year = {2022}, abstract = {Large longitudinal studies provide lots of valuable information, especially in medical applications. A problem which must be taken care of in order to utilize their full potential is that of correlation between intra-subject measurements taken at different times. For data in Euclidean space this can be done with hierarchical models, that is, models that consider intra-subject and between-subject variability in two different stages. Nevertheless, data from medical studies often takes values in nonlinear manifolds. Here, as a first step, geodesic hierarchical models have been developed that generalize the linear ansatz by assuming that time-induced intra-subject variations occur along a generalized straight line in the manifold. However, this is often not the case (e.g., periodic motion or processes with saturation). We propose a hierarchical model for manifold-valued data that extends this to include trends along higher-order curves, namely B{\´e}zier splines in the manifold. To this end, we present a principled way of comparing shape trends in terms of a functional-based Riemannian metric. Remarkably, this metric allows efficient, yet simple computations by virtue of a variational time discretization requiring only the solution of regression problems. We validate our model on longitudinal data from the osteoarthritis initiative, including classification of disease progression.}, language = {en} } @inproceedings{AmbellanZachowvonTycowicz2021, author = {Ambellan, Felix and Zachow, Stefan and von Tycowicz, Christoph}, title = {Geodesic B-Score for Improved Assessment of Knee Osteoarthritis}, booktitle = {Proc. Information Processing in Medical Imaging (IPMI)}, arxiv = {http://arxiv.org/abs/2104.01107}, doi = {10.1007/978-3-030-78191-0_14}, pages = {177 -- 188}, year = {2021}, abstract = {Three-dimensional medical imaging enables detailed understanding of osteoarthritis structural status. However, there remains a vast need for automatic, thus, reader-independent measures that provide reliable assessment of subject-specific clinical outcomes. To this end, we derive a consistent generalization of the recently proposed B-score to Riemannian shape spaces. We further present an algorithmic treatment yielding simple, yet efficient computations allowing for analysis of large shape populations with several thousand samples. Our intrinsic formulation exhibits improved discrimination ability over its Euclidean counterpart, which we demonstrate for predictive validity on assessing risks of total knee replacement. This result highlights the potential of the geodesic B-score to enable improved personalized assessment and stratification for interventions.}, language = {en} } @inproceedings{AmiranashviliLuedkeLietal.2022, author = {Amiranashvili, Tamaz and L{\"u}dke, David and Li, Hongwei and Menze, Bjoern and Zachow, Stefan}, title = {Learning Shape Reconstruction from Sparse Measurements with Neural Implicit Functions}, booktitle = {Medical Imaging with Deep Learning}, year = {2022}, abstract = {Reconstructing anatomical shapes from sparse or partial measurements relies on prior knowledge of shape variations that occur within a given population. Such shape priors are learned from example shapes, obtained by segmenting volumetric medical images. For existing models, the resolution of a learned shape prior is limited to the resolution of the training data. However, in clinical practice, volumetric images are often acquired with highly anisotropic voxel sizes, e.g. to reduce image acquisition time in MRI or radiation exposure in CT imaging. The missing shape information between the slices prohibits existing methods to learn a high-resolution shape prior. We introduce a method for high-resolution shape reconstruction from sparse measurements without relying on high-resolution ground truth for training. Our method is based on neural implicit shape representations and learns a continuous shape prior only from highly anisotropic segmentations. Furthermore, it is able to learn from shapes with a varying field of view and can reconstruct from various sparse input configurations. We demonstrate its effectiveness on two anatomical structures: vertebra and femur, and successfully reconstruct high-resolution shapes from sparse segmentations, using as few as three orthogonal slices.}, language = {en} } @inproceedings{PaskinDeanBaumetal.2022, author = {Paskin, Martha and Dean, Mason and Baum, Daniel and von Tycowicz, Christoph}, title = {A Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks}, booktitle = {Computer Vision -- ECCV 2022}, publisher = {Springer Nature Switzerland}, arxiv = {http://arxiv.org/abs/2207.12687}, doi = {10.1007/978-3-031-20086-1_21}, pages = {363 -- 379}, year = {2022}, abstract = {3D shapes provide substantially more information than 2D images. However, the acquisition of 3D shapes is sometimes very difficult or even impossible in comparison with acquiring 2D images, making it necessary to derive the 3D shape from 2D images. Although this is, in general, a mathematically ill-posed problem, it might be solved by constraining the problem formulation using prior information. Here, we present a new approach based on Kendall's shape space to reconstruct 3D shapes from single monocular 2D images. The work is motivated by an application to study the feeding behavior of the basking shark, an endangered species whose massive size and mobility render 3D shape data nearly impossible to obtain, hampering understanding of their feeding behaviors and ecology. 2D images of these animals in feeding position, however, are readily available. We compare our approach with state-of-the-art shape-based approaches both on human stick models and on shark head skeletons. Using a small set of training shapes, we show that the Kendall shape space approach is substantially more robust than previous methods and always results in plausible shapes. This is essential for the motivating application in which specimens are rare and therefore only few training shapes are available.}, language = {en} } @inproceedings{HarthVohraUdvaryetal.2022, author = {Harth, Philipp and Vohra, Sumit and Udvary, Daniel and Oberlaender, Marcel and Hege, Hans-Christian and Baum, Daniel}, title = {A Stratification Matrix Viewer for Analysis of Neural Network Data}, booktitle = {Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM)}, address = {Vienna, Austria}, doi = {10.2312/vcbm.20221194}, year = {2022}, abstract = {The analysis of brain networks is central to neurobiological research. In this context the following tasks often arise: (1) understand the cellular composition of a reconstructed neural tissue volume to determine the nodes of the brain network; (2) quantify connectivity features statistically; and (3) compare these to predictions of mathematical models. We present a framework for interactive, visually supported accomplishment of these tasks. Its central component, the stratification matrix viewer, allows users to visualize the distribution of cellular and/or connectional properties of neurons at different levels of aggregation. We demonstrate its use in four case studies analyzing neural network data from the rat barrel cortex and human temporal cortex.}, language = {en} } @inproceedings{LuedkeAmiranashviliAmbellanetal.2022, author = {L{\"u}dke, David and Amiranashvili, Tamaz and Ambellan, Felix and Ezhov, Ivan and Menze, Bjoern and Zachow, Stefan}, title = {Landmark-free Statistical Shape Modeling via Neural Flow Deformations}, volume = {13432}, booktitle = {Medical Image Computing and Computer Assisted Intervention - MICCAI 2022}, publisher = {Springer, Cham}, arxiv = {http://arxiv.org/abs/2209.06861}, doi = {10.1007/978-3-031-16434-7_44}, year = {2022}, abstract = {Statistical shape modeling aims at capturing shape variations of an anatomical structure that occur within a given population. Shape models are employed in many tasks, such as shape reconstruction and image segmentation, but also shape generation and classification. Existing shape priors either require dense correspondence between training examples or lack robustness and topological guarantees. We present FlowSSM, a novel shape modeling approach that learns shape variability without requiring dense correspondence between training instances. It relies on a hierarchy of continuous deformation flows, which are parametrized by a neural network. Our model outperforms state-of-the-art methods in providing an expressive and robust shape prior for distal femur and liver. We show that the emerging latent representation is discriminative by separating healthy from pathological shapes. Ultimately, we demonstrate its effectiveness on two shape reconstruction tasks from partial data. Our source code is publicly available (https://github.com/davecasp/flowssm).}, language = {en} } @inproceedings{IravaniConrad2019, author = {Iravani, Sahar and Conrad, Tim}, title = {Deep Learning for Proteomics Data for Feature Selection and Classification}, volume = {11713}, booktitle = {Machine Learning and Knowledge Extraction. CD-MAKE 2019}, editor = {Holzinger, A. and Kieseberg, P. and Tjoa, A. and Weippl, E.}, publisher = {Springer, Cham}, doi = {10.1007/978-3-030-29726-8_19}, year = {2019}, language = {en} }