Gábor Székely

Gábor Székely
ETH Zurich | ETH Zürich · Computer Vision Laboratory

About

331
Publications
40,683
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
12,841
Citations

Publications

Publications (331)
Article
Full-text available
Background: The accurate restoration of premorbid anatomy is key for the success of reconstructive surgeries of the proximal part of the humerus. The bicipital groove has been proposed as a landmark for the prediction of humeral head retrotorsion. We hypothesized that a novel method based on bilateral registration of the bicipital groove yields an...
Article
Background: In computer-assisted reconstructive surgeries, the contralateral anatomy is established as the best available reconstruction template. However, existing intra-individual bilateral differences or a pathological, contralateral humerus may limit the applicability of the method. The aim of the study was to evaluate whether a statistical sh...
Article
Background: With current 3-dimensional (3D) computer-based methods for the assessment of deformities, a surface registration method is applied to superimpose a computer model of the pathological bone onto a mirrored computer model of the contralateral side. However, because of bilateral differences, especially in humeral torsion, such template-bas...
Article
The optimal surgical treatment of complex fractures of the proximal humerus is controversial. It is proven that best results are obtained if an anatomical reduction of the fragments is achieved and, therefore, computer-assisted methods have been proposed for the reconstruction of the fractures. However, complex fractures of the proximal humerus are...
Article
Spatial regularization is essential in image registration, which is an ill-posed problem. Regularization can help to avoid both physically implausible displacement fields and local minima during optimization. Tikhonov regularization (squared ? 2 -norm) is unable to correctly represent non-smooth displacement fields, that can, for example, occur at...
Article
Congenital or posttraumatic bone deformity may lead to reduced range of motion, joint instability, pain, and osteoarthritis. The conventional joint-preserving therapy for such deformities is corrective osteotomy-the anatomical reduction or realignment of bones with fixation. In this procedure, the bone is cut and its fragments are correctly realign...
Conference Paper
Respiratory motion is a limiting factor during cancer therapy. Although image tracking can facilitate compensation for this motion, system latencies will still reduce the accuracy of tracking-based treatments. We propose a novel approach for temporal prediction of the motion of anatomical targets in the liver, observed from ultrasound sequences. Th...
Conference Paper
Respiratory motion limits the use of focused ultrasound surgery and conformal radiation therapies for livers. Population motion models have shown their ability to predict unobservable motion from tracking results. These models require establishment of inter-subject correspondences, which is non-trivial. In this study we compare the use of a landmar...
Conference Paper
Magnetic resonance guided high intensity focused ultrasound (MRgHIFU) is a new therapy for treating malignant liver tissues. However, the motion of the ribs in the beam path may compromise an effective and safe treatment. Due to poor visibility of bones in MR and US liver images, tracking them in real time is currently not feasible. We propose a me...
Article
In shoulder arthroplasty, the proximal humeral head is resected by sawing along the cartilage-bone transition and replaced by a prosthetic implant. The resection plane, called articular margin plane (AMP), defines the orientation, position and size of the prosthetic humeral head in relation to the humeral shaft. Therefore, the correct definition of...
Article
Full-text available
Transcranial focused ultrasound (tcFUS) is an attractive noninvasive modality for neurosurgical interventions. The presence of the skull, however, compromises the efficiency of tcFUS therapy, as its heterogeneous nature and acoustic characteristics induce significant distortion of the acoustic energy deposition, focal shifts, and thermal gain decre...
Article
Background: In the presence of severe osteoarthritis, osteonecrosis, or proximal humeral fracture, the contralateral humerus may serve as a template for the 3-dimensional (3D) preoperative planning of reconstructive surgery. The purpose of this study was to develop algorithms for performing 3D measurements of the humeral anatomy and further to ass...
Conference Paper
Image-guided radiation therapy during free-breathing requires estimation of the target position and compensation for its motion. Estimation of the observed motion during therapy needs to be reliable and accurate. In this paper we propose a novel, image sequence-specific confidence measure to predict the reliability of the tracking results. The sequ...
Article
Reviewed here are methods developed for following (i.e., tracking) structures in medical B-mode ultrasound time sequences during large-scale motion. The resulting motion estimation problem and its key components are defined. The main tracking approaches are described, and their strengths and weaknesses are discussed. Existing motion estimation meth...
Article
Image registration is used extensively in medical imaging. Visual assessment of its quality is time consuming and not necessarily accurate. Automatic estimation of registration accuracy is desired for many clinical applications. Current methods rely on learning a relationship between image features and registration error. In this paper we propose a...
Article
This study investigates the benefits of observing an example of the subject-specific 3D liver motion for individualizing a statistical population model and the influence of tracking errors on the model predictions based on 4D-MRI data from 16 subjects, simulated erroneous 2D tracking surrogates and leave-one-subject-out tests. A robust formulation...
Article
Full-text available
Central venous pressure (CVP) information is crucial in clinical situations such as cardiac failure, intravascular volume overload, and sepsis. The measurement of CVP, however, requires catheterization of vena cava through the subclavian or internal jugular veins, which is an impractical and costly procedure with related risk of complications. Peri...
Article
Full-text available
We demonstrate a novel method for automatic direct lesion depth (LD) tracking during coagulation from time series of a single A-mode ultrasound (US) transducer custom fit at the tip of a RFA catheter. This method is named thermal expansion imaging (TEI). A total of 35 porcine myocardium samples were ablated (LD 0.5-5 mm) while acquiring US, electri...
Article
We introduce a probabilistic approach to vessel network extraction that enforces physiological constraints on the vessel structure. The method accounts for both image evidence and geometric relationships between vessels by solving an integer program, which is shown to yield the maximum a posteriori (MAP) estimate to a probabilistic model. Starting...
Article
We present a technique to rectify nonrigid registrations by improving their group-wise consistency, which is a widely used unsupervised measure to assess pair-wise registration quality. While pair-wise registration methods cannot guarantee any group-wise consistency, group-wise approaches typically enforce perfect consistency by registering all ima...
Chapter
In diesem Beitrag adressieren wir die Rekonstruktion zerebrovaskul ärer Netzwerke mit einem Ansatz, der es erlaubt, Vorwissen über physiologisch plausible Strukturen zu berücksichtigen und gegen- über Bildinformation abzuwägen. Ausgehend von einem überkonnektierten Netzwerk wird in einer globalen Optimierung – unter Berücksichtigung von geometrisch...
Article
Full-text available
In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients – manually annotated by...
Patent
Full-text available
A method, system and device are described for generating high-resolution flow-field data from sparse measurement data by interpolating from a reference database of pre-computed, highly-resolved fluid dynamic simulation results, to generate a highly-resolved set of flow field data which correspond to the sparse measurements. In one embodiment, the m...
Chapter
Thus far, endoscopes are still mainly used as a keyhole to look inside the human body. Of course, endoscopes can be integrated into standard navigation systems, allowing to fuse the acquired images with other imaging modalities or 3-dimensional models derived from them. Such approaches usually rely on tracking external markers, allowing the visuali...
Conference Paper
Transcatheter aortic valve implantation (TAVI) is a minimally invasive procedure to treat severe aortic stenosis in patients with a high risk for conventional surgery. In-silico experiments of stent deployment within patient-specific models of the aortic root have created an opportunity to predict stent behavior during the intervention. Current lim...
Article
We propose a novel framework for joint 3-D vessel segmentation and centerline extraction. The approach is based on multivariate Hough voting and oblique random forests (RFs) that we learn from noisy annotations. It relies on steerable filters for the efficient computation of local image features at different scales and orientations. We validate bot...
Conference Paper
In this work, we present multi-atlas based techniques for both segmentation and landmark detection in images with large field-of-view (FOV). Such images can provide important insight in the anatomical structure of the human body, but are challenging to deal with since the localization search space for landmarks and organs, in addition to the raw am...
Conference Paper
Magnetic resonance guided high intensity focused ultrasound (MRgHIFU) is a new type of minimally invasive therapy for treating malignant liver tissues. Since the ribs on the beam path can compromise an effective therapy, detecting them and tracking their motion on MR images is of great importance. However, due to poor magnetic signal emission of bo...
Conference Paper
The reconstruction of 4D images from 2D navigator and data slices requires sufficient observations per motion state to avoid blurred images and motion artifacts between slices. Especially images from rare motion states, like deep inhalations during free-breathing, suffer from too few observations. To address this problem, we propose to actively gen...
Conference Paper
We introduce an integer programming-based approach to vessel network extraction that enforces global physiological constraints on the vessel structure and learn this prior from a high-resolution reference network. The method accounts for both image evidence and geometric relationships between vessels by formulating and solving an integer programmin...
Conference Paper
This paper describes a new approach for the reconstruction of complete 3-D arterial trees from partially incomplete image data. We utilize a physiologically motivated simulation framework to iteratively generate artificial, yet physiologically meaningful, vasculatures for the correction of vascular connectivity. The generative approach is guided by...
Conference Paper
Spatial regularization is indispensable in image registration to avoid both physically implausible displacement fields and potential local minima in optimization methods. Typical \(\ell _2\)-regularization is incapable of correctly recovering non-smooth displacement fields, such as at sliding organ boundaries during time-series of breathing motion....
Conference Paper
Transcatheter aortic valve implantation (TAVI) is a minimally invasive procedure to replace aortic leaflets in cases of severe aortic stenosis and regurgitation, which can be the result of valve calcification. Patient-specific procedure planning currently involves acquisition of CT scan data to determine anatomic measurements within the area of int...
Conference Paper
Image registration is a ubiquitous technique in medical imaging. However, finding correspondences reliably between images is a difficult task since the registration problem is ill-posed and registration algorithms are only capable of finding local optima. This makes it challenging to find a suitable registration method and parametrization for a spe...
Article
Full-text available
In this paper, a novel Markov random field (MRF)-based approach is presented for segmenting medical images while simultaneously registering an atlas nonrigidly. In the literature, both segmentation and registration have been studied extensively. For applications that involve both, such as segmentation via atlas-based registration, earlier studies p...
Conference Paper
Automatic detection of ribs in magnetic resonance images (MRIs) is extremely challenging due to their poor image appearance. Yet localization of ribs is highly important for effective and safe focused ultrasound therapy. We propose a semi-automatic rib centerline detection method based on combining a rib cage shape model generated from computed tom...
Conference Paper
Information concerning central venous pressure (CVP) is crucial in clinical situations, such as cardiac failure, volume overload, and sepsis. The measurement of CVP, however, requires insertion of a catheter through a vein up a vena cava — close to the heart — with related cost and risk of complications. Peripheral venous pressure (PVP) measurement...
Conference Paper
In this study we propose to combine the outcome of four temporal prediction methods, which have different strength and weaknesses, by taking their median. Based on 25 motion traces from ultrasound liver tracking, this decision fusion provided statistically significantly better results than the individual outcomes for latencies from 150 to 1000ms. O...
Conference Paper
In this paper we present a novel post-processing technique to detect and correct inconsistency-based errors in non-rigid registration. While deformable registration is ubiquitous in medical image computing, assessing its quality has yet been an open problem. We propose a method that predicts local registration errors of existing pairwise registrati...
Conference Paper
This paper studies improving joint segmentation and registration by introducing auxiliary labels for anatomy that has similar appearance to the target anatomy while not being part of that target. Such auxiliary labels help avoid false positive labelling of non-target anatomy by resolving ambiguity. A known registration of a segmented atlas can help...
Article
Full-text available
An approach for extracting the radial force load on an implanted stent from medical images is proposed. To exemplify the approach, a system is presented which computes a radial force estimation from computer tomography images acquired from patients who underwent transcatheter aortic valve implantation (TAVI). The deformed shape of the implanted val...
Article
This paper describes a new approach for the reconstruction of complete 3-D arterial trees from partially incomplete image data. We utilize a physiologically motivated simulation framework to iteratively generate artificial, yet physiologically meaningful, vasculatures for the correction of vascular connectivity. The generative approach is guided by...
Article
In this work, we present multi-atlas based techniques for both segmentation and landmark detection. We focus on modality and anatomy independent techniques to be applied to a wide range of input images, in contrast to methods customized to a specific anatomy or image modality. For segmentation, we use label propagation from several atlases to a tar...
Article
Full-text available
In the past years multiphysics computational models aiming at describing clot formation and growth have been developed using different constitutive equations. Most models were designed to investigate the interactions between many agents of the so-called coagulation cascade but were based on simple assumptions to describe the complex interaction bet...
Article
Full-text available
Abstract The development of phased array transducers and their integration with magnetic resonance (MR) guidance and thermal monitoring has established transcranial MR-guided focused ultrasound (tcMRgFUS) as an attractive non-invasive modality for neurosurgical interventions. The presence of the skull, however, compromises the efficiency of transcr...
Conference Paper
We propose a learning-based method for robust tracking in long ultrasound sequences for image guidance applications. The framework is based on a scale-adaptive block-matching and temporal realignment driven by the image appearance learned from an initial training phase. The latter is introduced to avoid error accumulation over long sequences. The v...
Conference Paper
Precise radiation therapies require not only accurate prediction of the motion of the structures in the treatment region, but also confidence values of these predictions to enable planning of residual motion and detection of failure predictions. While various motion models have been proposed for the prediction of motion in the abdomen due to free-b...
Article
Full-text available
Volumes change during fractionated radiotherapy (RT). We investigate a tool based on the Hierarchical Enhanced Registration Algorithm (HERA) to project a 3D segmentation set of the prostate into the subsequent imaging sets at any time point during RT by using intensity-based image registration techniques. Sequential CT sets during RT at 15, 30, 45,...
Article
Full-text available
Volumes change during fractionated radiotherapy (RT). We investigate a tool based on the Hierarchical Enhanced Registration Algorithm (HERA) to project a 3D segmentation set of the prostate into the subsequent imaging sets at any time point during RT by using intensity‐based image registration techniques. Sequential CT sets during RT at 15, 30, 45,...
Article
Full-text available
Transcatheter aortic valve implantation (TAVI) is a minimally invasive off-pump procedure to replace diseased aortic heart valves. Known complications include paravalvular leaks, atrioventricular blocks, coronary obstruction and annular rupture. Careful procedure planning including appropriate stent selection and sizing are crucial. Few patient-spe...
Poster
Full-text available
Atlas-based segmentation is an essential component of computer aided planning for radiotherapy. Commercial products often have access to a large number of candidate images to be used as atlases and thus efficient mechanisms are necessitated to automatically retrieve suitable atlas images. In this study, we have first developed methods to extract gl...
Conference Paper
Full-text available
Anatomy related heterogeneous discontinuities in material properties strongly influence human soft tissue behavior under mechanical load. We present a parametric model of the aortic root, which defines multi-material surface regions for advanced tissue property control and supports patient-specific model refinement. Our results strongly indicate improv...
Article
Improved performance has been reported for computer aided detection (CADe) methods using information from multiple mammographic views over single-view CADe approaches. Linkage across the views is based on assuming that location and image features from the same lesion depicted in both views will be similar. In this study we investigate if the locati...
Patent
Full-text available
A force sensor device has at least three arcs distributed around " a central axis. The arcs have integrated sensing elements that measure strain applied on the arc resulting from a force applied on the central axis.
Article
A novel, robust, tri-axial force sensor has been developed that can be integrated into biomedical and robotic devices thanks to its size and accuracy. It features a titanium alloy body, the components of the force are separated by four basic strain sensing elements. The sensor was modeled by finite element method and the results were validated by e...
Conference Paper
Segmentation via atlas registration is a common technique in medical image analysis. Devising estimates of such segmentation outcome has been of interest in cases with multiple atlases, both for single-atlas selection and for multi-atlas fusion. This paper studies the estimation of expected Dice's similarity metric for registering atlas-target pair...
Conference Paper
Interaction with virtual deformable models is common in several haptic contexts, such as in medical training simulators. This paper presents a methodological procedure for the creation of such virtual models from their real-life counterparts. Both the surface geometry and the elastic parametrization of an object are reconstructed from position/forc...
Conference Paper
Sliding boundaries are a challenge when registering abdominal images, especially for MRI where the boundaries are not clearly visible. Various automatic methods have been proposed, but evaluation has been insufficient. In this study we assess the performance of several anisotropic diffusion based methods for registering abdominal MR images undergoi...
Conference Paper
Treatment of tumor sites affected by respiratory motion requires knowledge of the position and the shape of the tumor and the surrounding organs during breathing. As not all structures of interest can be observed in real-time, their position needs to be predicted from partial information (so-called surrogates) like motion of diaphragm, internal mar...
Conference Paper
A semi-supervised segmentation method using a single atlas is presented in this paper. Traditional atlas-based segmentation suffers from either a strong bias towards the selected atlas or the need for manual effort to create multiple atlas images. Similar to semi-supervised learning in computer vision, we study a method which exploits information c...
Article
Full-text available
Background and purpose: Neurosurgical interventions of the thalamus rely on transferring stereotactic coordinates from an atlas onto the patient's MR brain images. We propose a prototype application for performing thalamus target map individualization by fusing patient-specific thalamus geometric information and diffusion tensor tractography. Mat...
Conference Paper
We propose a machine learning-based framework using oblique random forests for 3-D vessel segmentation. Two different kinds of features are compared. One is based on orthogonal subspace filtering where we learn 3-D eigenspace filters from local image patches that return task optimal feature responses. The other uses a specific set of steerable filt...
Conference Paper
The effective modeling and predicting of respiratory motion in abdominal organs is crucial to the task of tumor treatments. Current approaches in statistical respiration modeling either build a subject-specific model which is only suitable for that single subject or create a population model by assuming a coherent population with a relatively simpl...
Conference Paper
Full-text available
Robust and reliable validation of stent designs and materials is an essential aspect in the development and improvement of these medical devices. It is essential to perform a variety of experiments at an early stage of this process to define suitable material requirements and stent geometry. We present a rapid prototyping framework for silicone-base...
Article
Full-text available
False positive (FP) marks represent an obstacle for effective use of computer-aided detection (CADe) of breast masses in mammography. Typically, the problem can be approached either by developing more discriminative features or by employing different classifier designs. In this paper, the usage of support vector machine (SVM) classification for FP...
Conference Paper
In this work, a classifier combination approach for computer aided diagnosis (CADx) of breast mass lesions in mammography (MG) and magnetic resonance imaging (MRI) is investigated, using a database with 278 and 243 findings in MG resp. MRI including 98 multimodal (MM) lesion annotations. For each modality, feature selection was performed separately...
Article
Minimal invasive tumor therapies are getting ever more sophisticated with novel treatment approaches and new devices allowing for improved targeting precision. Applying these effectively requires precise localization of the structures of interest. Vital processes, such as respiration and heartbeat, induce organ motion, which cannot be neglected dur...
Conference Paper
A miniature tri-axial force sensor has been developed that complies with the requirements of integration into biomedical and robotic devices due to its size and accuracy. The sensor is a machined Titanium alloy body of the overall dimensions 8.6 × Ø3.4 mm with semi-conductor strain gauges embedded on it. The sensing beam's size is 1 × 1 × 4.4 mm. W...
Article
We present an approach to generate 3-D arterial tree models based on physiological principles while at the same time certain morphological properties are enforced at construction time. The driving force of the construction is a simplified angiogenesis model incorporating case-specific information about the metabolic demand within the considered dom...
Article
In computer-assisted orthopaedic surgery, recovering three-dimensional patient-specific anatomy from incomplete information has been focus of interest due to several factors such as less invasive surgical procedures, reduced radiation doses, and rapid intra-operative updates of the anatomy. The aim of this paper is to report results obtained combin...
Article
We propose a novel approach for real-time image registration for image sequences of organs subject to repetitive movement, such as breathing. The method exploits the redundancy within the images and consists of a training and an application phase. During training, the images are registered and then the relationship between the image appearance and...
Article
Full-text available
The cerebrovascular system continuously delivers oxygen and energy substrates to the brain, which is one of the organs with the highest basal energy requirement in mammals. Discontinuities in the delivery lead to fatal consequences for the brain tissue. A detailed understanding of the structure of the cerebrovascular system is important for a multi...
Article
Shape prediction from sparse observation is of increasing interest in minimally invasive surgery, in particular when the target is not directly visible on images. This can be caused by a limited field-of-view of the imaging device, missing contrast or an insufficient signal-to-noise ratio. In such situations, a statistical shape model can be employ...