Joachim Hornegger
University of Erlangen-Nuremberg
Imaging phantomAlgorithmOpticsPhysicsRadiologyIterative reconstructionArtificial intelligenceImage registrationPattern recognitionProjection (set theory)Materials scienceOptical coherence tomographyNuclear medicineComputer visionMathematicsComputer scienceImage qualityMedicineSegmentation
609Publications
65H-index
12.4kCitations
Publications 598
Newest
#1Andreas MaierH-Index: 36
#2Stefan SteidlH-Index: 36
Last. Joachim HorneggerH-Index: 65
view all 4 authors...
This open access book gives a complete and comprehensive introduction to the fields of medical imaging systems, as designed for a broad range of applications. The authors of the book first explain the foundations of system theory and image processing, before highlighting several modalities in a dedicated chapter. The initial focus is on modalities that are closely related to traditional camera systems such as endoscopy and microscopy. This is followed by more complex image formation processes: m...
20 Citations
#1Yanye Lu (Siemens)H-Index: 9
#2Markus Kowarschik (Siemens)H-Index: 21
Last. Andreas MaierH-Index: 36
view all 11 authors...
PURPOSE: Benefiting from multi-energy x-ray imaging technology, material decomposition facilitates the characterization of different materials in x-ray imaging. However, the performance of material decomposition is limited by the accuracy of the decomposition model. Due to the presence of nonideal effects in x-ray imaging systems, it is difficult to explicitly build the imaging system models for material decomposition. As an alternative, this paper explores the feasibility of using machine learn...
16 CitationsSource
#1Florin-Cristian Ghesu (Princeton University)H-Index: 1
#2Bogdan Georgescu (Princeton University)H-Index: 35
Last. Dorin Comaniciu (Princeton University)H-Index: 67
view all 7 authors...
Robust and fast detection of anatomical structures is a prerequisite for both diagnostic and interventional medical image analysis. Current solutions for anatomy detection are typically based on machine learning techniques that exploit large annotated image databases in order to learn the appearance of the captured anatomy. These solutions are subject to several limitations, including the use of suboptimal feature engineering techniques and most importantly the use of computationally suboptimal ...
129 CitationsSource
#1Florin C. Ghesu (Princeton University)H-Index: 9
#2Bogdan Georgescu (Princeton University)H-Index: 35
Last. Dorin Comaniciu (Princeton University)H-Index: 67
view all 6 authors...
Abstract Robust and fast detection of anatomical structures represents an important component of medical image analysis technologies. Current solutions for anatomy detection are based on machine learning, and are generally driven by suboptimal and exhaustive search strategies. In particular, these techniques do not effectively address cases of incomplete data, i.e., scans acquired with a partial field-of-view. We address these challenges by following a new paradigm, which reformulates the detect...
17 CitationsSource
#1Franziska Schirrmacher (FAU: University of Erlangen-Nuremberg)H-Index: 3
#2Thomas Köhler (FAU: University of Erlangen-Nuremberg)H-Index: 8
Last. Andreas Maier (FAU: University of Erlangen-Nuremberg)H-Index: 36
view all 10 authors...
Abstract This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical imaging modalities. We demonstrate its effectiveness on volumetric optical coherence tomography (OCT) and computed tomography (CT) data, which show different noise and image characteristics. OCT offers high-resolution scans of the human retina but is inherently impaired by speckle noise. CT on the oth...
10 CitationsSource
#1Xiaolin HuangH-Index: 19
#2Johan A. K. Suykens (Katholieke Universiteit Leuven)H-Index: 89
Last. Andreas Maier (FAU: University of Erlangen-Nuremberg)H-Index: 36
view all 5 authors...
This brief proposes a truncated \ell _{1}distance (TL1) kernel, which results in a classifier that is nonlinear in the global region but is linear in each subregion. With this kernel, the subregion structure can be trained using all the training data and local linear classifiers can be established simultaneously. The TL1 kernel has good adaptiveness to nonlinearity and is suitable for problems which require different nonlinearities in different areas. Though the TL1 kernel is not positive sem...
13 CitationsSource
This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical imaging modalities. We demonstrate its effectiveness on volumetric optical coherence tomography (OCT) and computed tomography (CT) data, which show different noise and image characteristics. OCT offers high-resolution scans of the human retina but is inherently impaired by speckle noise. CT on the other hand h...
This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical image modalities. We demonstrate its effectivness on volumetric optical coherence tomography (OCT) and computed tomography (CT) data, which show differnt noise and image characteristics. OCT offers high-resolution scans of the human retina but is inherently impaired by speckle noise. CT on the other hand has a...
#1Yanye Lu (FAU: University of Erlangen-Nuremberg)H-Index: 9
#2Markus Kowarschik (Siemens)H-Index: 21
Last. Andreas Maier (FAU: University of Erlangen-Nuremberg)H-Index: 36
view all 8 authors...
Material decomposition allows the reconstruction of material-specific images in spectral X-ray imaging, which requires efficient decomposition models. Due to the presence of nonideal effects in X-ray imaging systems, it is difficult to explicitly estimate the imaging systems for material decomposition tasks. As an alternative to previous empirical material decomposition methods, we investigated material decomposition using ensemble learning methods in this paper. Three ensemble methods with two ...
10 CitationsSource
#1Jens Wetzl (FAU: University of Erlangen-Nuremberg)H-Index: 8
#2Michaela Schmidt (Siemens)H-Index: 21
Last. Christoph Forman (Siemens)H-Index: 15
view all 8 authors...
Objectives Our objectives were to evaluate a single-breath-hold approach for Cartesian 3-D CINE imaging of the left ventricle with a nearly isotropic resolution of \(1.9 \times 1.9 \times 2.5\,{\text {mm}^3}\) and a breath-hold duration of \(\sim \)19 s against a standard stack of 2-D CINE slices acquired in multiple breath-holds. Validation is performed with data sets from ten healthy volunteers.
24 CitationsSource