Orcun Goksel

ETH Zurich, Zürich, Zurich, Switzerland

Are you Orcun Goksel?

Claim your profile

Publications (48)32.25 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: 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 realigned and stabilized with an implant to secure their position during bone healing. Corrective osteotomy is an elective procedure scheduled in advance, providing sufficient time for careful diagnosis and operation planning. Accordingly, computer-based methods have become very popular for its preoperative planning. These methods can improve precision not only by enabling the surgeon to quantify deformities and to simulate the intervention preoperatively in three dimensions, but also by generating a surgical plan of the required correction. However, generation of complex surgical plans is still a major challenge, requiring sophisticated techniques and profound clinical expertise. In addition to preoperative planning, computer-based approaches can also be used to support surgeons during the course of interventions. In particular, since recent advances in additive manufacturing technology have enabled cost-effective production of patient-and intervention-specific osteotomy instruments, customized interventions can thus be planned for and performed using such instruments. In this chapter, state of the art and future perspectives of computer-assisted deformity-correction surgery of the upper and lower extremities are presented. We elaborate on the benefits and pitfalls of different approaches based on our own experience in treating over 150 patients with three-dimensional preoperative planning and patient-specific instrumentation.
    No preview · Article · Jan 2016

  • No preview · Article · Nov 2015 · IEEE Transactions on Medical Imaging
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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 assess side-to-side (bilateral) differences in humeral head retrotorsion, humeral head inclination, humeral length, and humeral head radius and height. Methods: The 3D models of 140 paired humeri (70 cadavers) were extracted from computed tomographic data. Geometric characteristics quantifying the humeral anatomy in 3D were determined in a semiautomatic fashion using the developed computer algorithms. The results between the sides were compared for evaluating bilateral differences. Results: The mean bilateral difference of the humeral retrotorsion angle was 6.7° (standard deviation [SD], 5.7°; range, -15.1° to 24.0°; P = .063); the mean side difference of the humeral head inclination angle was 2.3° (SD, 1.8°; range, -5.1° to 8.4°; P = .12). The side difference in humeral length (mean, 2.9 mm; SD, 2.5 mm; range, -8.7 mm to 10.1 mm; P = .04) was significant. The mean side difference in the head sphere radius was 0.5 mm (SD, 0.6 mm; range, -3.2 mm to 2.2 mm; P = .76), and the mean side difference in humeral head height was 0.8 mm (SD, 0.6 mm; range, -2.4 mm to 2.4 mm; P = .44). Conclusions: The contralateral anatomy may serve as a reliable reconstruction template for humeral length, humeral head radius, and humeral head height if it is analyzed with 3D algorithms. In contrast, determining humeral head retrotorsion and humeral head inclination from the contralateral anatomy may be more prone to error.
    No preview · Article · Oct 2015 · Journal of shoulder and elbow surgery / American Shoulder and Elbow Surgeons ... [et al.]
  • V. Vishnevskiy · T. Gass · G. Szekely · C. Tanner · O. Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 an unsupervised method for the detection of local registration errors of a user-specified magnitude. Our method analyses the consistency error of registration circuits, does not require image intensity information, and achieves an error detection accuracy of 82% for 3D liver MRI registration of breathing phases.
    No preview · Article · Jul 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: 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. Peripheral venous pressure (PVP), which correlates with CVP under certain patient positioning, can be measured noninvasively using ultrasound via controlled compressions of a superficial vein. This paper presents an automatic system for acquiring such noninvasive measurements. Robust signal and image processing techniques developed for this purpose are introduced in this work. The proposed stand-alone, mobile platform collects images in real-time from the display output of any ultrasound machine, meanwhile measuring the pressure on the skin underneath the ultrasound transducer via a liquid-filled pouch. The image and pressure data are synchronized through an automated temporal calibration procedure. During forearm compressions, blood vessels are detected and tracked in the images using robust geometric (ellipse) models, the parameters of which are used further in model-based estimation of PVP. The proposed system was tested in 56 image sequences on 14 healthy volunteers, and was shown to achieve measurements with errors comparable to or lower than the interoperator variability between expert manual assessments.
    Full-text · Article · Jul 2015 · IEEE transactions on bio-medical engineering
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In surface-based registration for image-guided interventions, the presence of missing data can be a significant issue. This often arises with real-time imaging modalities such as ultrasound, where poor contrast can make tissue boundaries difficult to distinguish from surrounding tissue. Missing data poses two challenges: ambiguity in establishing correspondences; and extrapolation of the deformation field to those missing regions. To address these, we present a novel non-rigid registration method. For establishing correspondences, we use a probabilistic framework based on a Gaussian mixture model (GMM) that treats one surface as a potentially partial observation. To extrapolate and constrain the deformation field, we incorporate biomechanical prior knowledge in the form of a finite element model (FEM). We validate the algorithm, referred to as GMM-FEM, in the context of prostate interventions. Our method leads to a significant reduction in target registration error (TRE) compared to similar state-of-the-art registration algorithms in the case of missing data up to 30%, with a mean TRE of 2:6 mm. The method also performs well when full segmentations are available, leading to TREs that are comparable to or better than other surface-based techniques. We also analyze robustness of our approach, showing that GMM-FEM is a practical and reliable solution for surfacebased registration.
    Full-text · Article · Jun 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: 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, electrical impedance (EI) and contact force (CF) data. US images are generated in real time in terms of echo intensity (M-mode) and phase (TEI). For TEI, displacements between US time series are estimated with time-domain cross-correlation. A modified least squares strain estimation with temporal and depth smoothing reveals a thermal expansion boundary (TEB)-negative zero-crossing of temporal strain-which is associated to the coagulated tissue front. M-mode does not reliably delineate RFA lesions. TEI images reveal a traceable TEB with RMSE [Formula: see text] 0.50 mm and [Formula: see text] with respect to visual observations. The conventional technique, EI, shows lower [Formula: see text] and [Formula: see text]200 % variations with CF. The discontinuous time progression of the TEB is qualitatively associated to tissue heterogeneity and CF variations, which are directly traceable with TEI. The speed of sound, measured in function of tissue temperature, increases up to a plateau at 55 [Formula: see text], which does not explain the observed strain bands in the TEB. TEI successfully tracks LD in in vitro experiments based on a single US transducer and is robust to catheter/tissue contact, ablation time and even tissue heterogeneity. The presence of a TEB suggests thermal expansion as the main strain mechanism during coagulation, accompanied by compression of the adjacent non-ablated tissue. The isolation of thermally induced displacements from in vivo motion is a matter of future research. TEI is potentially applicable to other treatments such as percutaneous RFA of liver and high-intensity focused ultrasound.
    Full-text · Article · Apr 2015 · International Journal of Computer Assisted Radiology and Surgery
  • Tobias Gass · Gábor Székely · Orcun Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 images to a common reference. However, errors in individual registrations to the reference then propagate, distorting the mean and accumulating in the pair-wise registrations inferred via the reference. Furthermore, the assumption that perfect correspondences exist is not always true, e.g., for interpatient registration. The proposed consistency-based registration rectification (CBRR) method addresses these issues by minimizing the group-wise inconsistency of all pair-wise registrations using a regularized least-squares algorithm. The regularization controls the adherence to the original registration, which is additionally weighted by the local postregistration similarity. This allows CBRR to adaptively improve consistency while locally preserving accurate pair-wise registrations. We show that the resulting registrations are not only more consistent, but also have lower average transformation error when compared to known transformations in simulated data. On clinical data, we show improvements of up to 50% target registration error in breathing motion estimation from four-dimensional MRI and improvements in atlas-based segmentation quality of up to 65% in terms of mean surface distance in three-dimensional (3-D) CT. Such improvement was observed consistently using different registration algorithms, dimensionality (two-dimensional/3-D), and modalities (MRI/CT).
    No preview · Article · Mar 2015
  • Tobias Gass · Gabor Szekely · Orcun Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 amount of data, is large. In many studies, segmentation and localization techniques are developed specifically for an individual target anatomy or image modality. This can leave a substantial amount of the potential of large FOV images untapped, as the co-localization and shape variability of organs are neglected. We thus focus on modality and anatomy independent techniques to be applied to a wide range of input images. For segmentation, we propagate the multi-organ label maps from several atlases to a target image via a large FOV Markov random field (MRF) based non-rigid registration method. The propagated labels are then fused in the target domain using similarity-weighted majority voting. For landmark localization, we use a consensus based fusion of location estimates from several atlases identified by a template-matching approach. We present our results in the IEEE ISBI 2014 VISCERAL challenge as well as VISCERAL Anatomy1 and Anatomy2 benchmarks.
    No preview · Chapter · Sep 2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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. In this paper, Total Variation (TV) regularization is used to allow for accurate registration near such boundaries. We propose a novel formulation of TV-regularization for parametric displacement fields and introduce an efficient and general numerical solution scheme using the Alternating Directions Method of Multipliers (ADMM). Our method has been evaluated on two public datasets of 4D CT lung images as well as a dataset of 4D MR liver images, demonstrating accurate registrations both inside and outside moving organs. The target registration error of our method is 2.56 mm on average in the liver dataset, which indicates an improvement of over 24 % in comparison to other published methods.
    No preview · Chapter · Sep 2014
  • Source
    Tobias Gass · Gabor Szekely · Orcun Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 proposed addressing these problems iteratively by feeding the output of each to initialize the other. This scheme, however, cannot guarantee an optimal solution for the combined task at hand, since these two individual problems are then treated separately. In this paper, we formulate simultaneous registration and segmentation (SRS) as a maximum a-posteriori (MAP) problem. We decompose the resulting probabilities such that the MAP inference can be done using MRFs. An efficient hierarchical implementation is employed, allowing coarse-to-fine registration while estimating segmentation at pixel level. The method is evaluated on two clinical data sets: 1) mandibular bone segmentation in 3D CT and 2) corpus callosum segmentation in 2D midsaggital slices of brain MRI. A video tracking example is also given. Our implementation allows us to directly compare the proposed method with the individual segmentation/registration and the iterative approach using the exact same potential functions. In a leave-one-out evaluation, SRS demonstrated more accurate results in terms of dice overlap and surface distance metrics for both data sets. We also show quantitatively that the SRS method is less sensitive to the errors in the registration as opposed to the iterative approach.
    Full-text · Article · Jul 2014 · IEEE Transactions on Image Processing
  • A. Crimi · M. Makhinya · U. Baumann · G. Szekely · O. Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 is a technique which allows indirect assessment of CVP without catheterization. However, PVP measurement is cumbersome since it requires several devices, trained medical personnel, and is difficult to perform repeatably. Aiming at an automatic venous pressure measurement system via image-processing, we introduce in this paper a robust vessel tracking algorithm fit for this purpose. The proposed algorithm addresses the challenge of tracking compressed vessels, which is essential for this venous pressure measurement technique. Given this tracking algorithm, initial PVP measurements on healthy volunteers are reported.
    No preview · Conference Paper · Apr 2014
  • Tobias Gass · Gabor Szekely · Orcun Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 registrations between a set of images, while simultaneously estimating corrected registrations. In the solution the error is constrained to be small in areas of high post-registration image similarity, while local registrations are constrained to be consistent between direct and indirect registration paths. The latter is a critical property of an ideal registration process, and has been frequently used to asses the performance of registration algorithms. In our work, the consistency is used as a target criterion, for which we efficiently find a solution using a linear least-squares model on a coarse grid of registration control points. We show experimentally that the local errors estimated by our algorithm correlate strongly with true registration errors in experiments with known, dense ground-truth deformations. Additionally, the estimated corrected registrations consistently improve over the initial registrations in terms of average deformation error or TRE for different registration algorithms on both simulated and clinical data, independent of modality (MRI/CT), dimensionality (2D/3D) and employed primary registration method (demons/Markov-randomfield).
    No preview · Conference Paper · Mar 2014
  • Tobias Gass · Gabor Szekely · Orcun Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 identify where a target segmentation should lie. Conversely, segmentations of anatomy in two images can help them be better registered. Joint segmentation and registration is then a method that can leverage information from both registration and segmentation to help one another. It has received increasing attention recently in the literature. Often, merely a single organ of interest is labelled in the atlas. In the presense of other anatomical structures with similar appearance, this leads to ambiguity in intensity based segmentation; for example, when segmenting individual bones in CT images where other bones share the same intensity profile. To alleviate this problem, we introduce automatic generation of additional labels in atlas segmentations, by marking similar-appearance non-target anatomy with an auxiliary label. Information from the auxiliary-labeled atlas segmentation is then incorporated by using a novel coherence potential, which penalizes differences between the deformed atlas segmentation and the target segmentation estimate. We validated this on a joint segmentation-registration approach that iteratively alternates between registering an atlas and segmenting the target image to find a final anatomical segmentation. The results show that automatic auxiliary labelling outperforms the same approach using a single label atlasses, for both mandibular bone segmentation in 3D-CT and corpus callosum segmentation in 2D-MRI.
    No preview · Conference Paper · Mar 2014
  • O. Goksel · T. Gass · G. Szekely
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 target image via a Markov random field (MRF) based registration method, followed by label fusion by majority voting weighted by local cross-correlations. For landmark localization, we use a consensus based fusion of location estimates from several atlases identified by a template-matching approach. Results in IEEE ISBI 2014 VISCERAL challenge as well as VISCERAL Anatomy1 challenge are presented herein.
    No preview · Article · Jan 2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 global features from thoracic CT images. These include geometrical features based on both voxel intensities and the outlines of automatic approximate bone, lung, and whole-body segmentations that can be calculated in seconds. Our goal is to study image retrieval techniques using these global image features, in particular investigating the feasibility of various supervised learning algorithms. Such retrieved images are then to be used as atlasses for the atlas-based segmentation of anatomy that cannot be segmented automatically such as lymph nodes.
    Full-text · Conference Paper · Jun 2013
  • O. Goksel · T. Gass · V. Vishnevsky · G. Szekely
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 pairs, by employing registration loops with models of such metric (error) accumulation over these loops. In this framework, the use of registration information also from unsegmented images is proposed and is shown to outperform using segmented atlas images alone. We demonstrate a fast, memory-efficient implementation and single-atlas selection results using a CT and an MR dataset.
    No preview · Conference Paper · Jan 2013
  • Tobias Gass · Gábor Székely · Orcun Goksel
    [Show abstract] [Hide abstract]
    ABSTRACT: 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 contained in a set of unlabelled images by mutually registering them nonrigidly and propagating the single atlas segmentation over multiple such registration paths to each target. These multiple segmentation hypotheses are then fused by local weighting based on registration similarity. Our results on two datasets of different anatomies and image modalities, corpus callosum MR and mandible CT images, show a significant improvement in segmentation accuracy compared to traditional single atlas based segmentation. We also show that the bias towards the selected atlas is minimized using our method. Additionally, we devise a method for the selection of intermediate targets used for propagation, in order to reduce the number of necessary inter-target registrations without loss of final segmentation accuracy.
    No preview · Chapter · Jan 2013
  • O. Goksel · Seokhee Jeon · M. Harders · G. Szekely
    [Show abstract] [Hide abstract]
    ABSTRACT: 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/force readings during an operator-assisted exploration of the object. A 3D mesh model is then generated from the surface contact points. The internal elastic modulus is found using the 3D finite element method. This modeling method is compared with two common 1D elastic models, namely Kelvin-Voigt and Hunt-Crossley. Results using three deformable homogeneous silicone samples show successful geometry reconstruction. 1D model parameterizations exhibit high variation dependent on geometry and contact location. In contrast, elastic modulus reconstruction yields a global model parameterization independent of geometry. Elastic moduli estimated in experiments correlated with their known values, and were shown to be reproducible among samples with different geometries.
    No preview · Conference Paper · Jan 2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: The finite element method is commonly used to model tissue deformation in order to solve for unknown parameters in the inverse problem of viscoelasticity. Typically, a (regular-grid) structured mesh is used since the internal geometry of the domain to be identified is not known a priori. In this work, the generation of problem-specific meshes is studied and such meshes are shown to significantly improve inverse-problem elastic parameter reconstruction. Improved meshes are generated from axial strain images, which provide an approximation to the underlying structure, using an optimization-based mesh adaptation approach. Such strain-based adapted meshes fit the underlying geometry even at coarse mesh resolutions, therefore improving the effective resolution of the reconstruction at a given mesh size/complexity. Elasticity reconstructions are then performed iteratively using the reflective trust-region method for optimizing the fit between estimated and observed displacements. This approach is studied for Youngs modulus reconstruction at various mesh resolutions through simulations, yielding 40% to 72% decrease in root-mean-square reconstruction error and 4 to 52 times improvement in contrast-to-noise ratio in simulations of a numerical phantom with a circular inclusion. A noise study indicates that conventional structured meshes with no noise perform considerably worse than the proposed adapted meshes with noise levels up to 20% of the compression amplitude. A phantom study and preliminary in-vivo results from a breast tumor case confirm the benefit of the proposed technique. Not only conventional axial strain images but also other elasticity approximations can be used to adapt meshes. This is demonstrated on images generated by combining axial strain and axial-shear strain, which enhances lateral image contrast in particular settings, consequently further improving meshadapted reconstructions.
    No preview · Article · Nov 2012