Stefan Klein

Universita' degli Studi "Magna Græcia" di Catanzaro, Catanzaro, Calabria, Italy

Are you Stefan Klein?

Claim your profile

Publications (103)167.95 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Purpose To determine if T1ρ mapping can be used as an alternative to delayed gadolinium-enhanced magnetic resonance imaging of cartilage (dGEMRIC) in the quantification of cartilage biochemical composition in vivo in human knees with osteoarthritis. Materials and Methods This study was approved by the institutional review board. Written informed consent was obtained from all participants. Twelve patients with knee osteoarthritis underwent dGEMRIC and T1ρ mapping at 3.0 T before undergoing total knee replacement. Outcomes of dGEMRIC and T1ρ mapping were calculated in six cartilage regions of interest. Femoral and tibial cartilages were harvested during total knee replacement. Cartilage sulphated glycosaminoglycan (sGAG) and collagen content were assessed with dimethylmethylene blue and hydroxyproline assays, respectively. A four-dimensional multivariate mixed-effects model was used to simultaneously assess the correlation between outcomes of dGEMRIC and T1ρ mapping and the sGAG and collagen content of the articular cartilage. Results T1 relaxation times at dGEMRIC showed strong correlation with cartilage sGAG content (r = 0.73; 95% credibility interval [CI] = 0.60, 0.83) and weak correlation with cartilage collagen content (r = 0.40; 95% CI: 0.18, 0.58). T1ρ relaxation times did not correlate with cartilage sGAG content (r = 0.04; 95% CI: -0.21, 0.28) or collagen content (r = -0.05; 95% CI = -0.31, 0.20). Conclusion dGEMRIC can help accurately measure cartilage sGAG content in vivo in patients with knee osteoarthritis, whereas T1ρ mapping does not appear suitable for this purpose. Although the technique is not completely sGAG specific and requires a contrast agent, dGEMRIC is a validated and robust method for quantifying cartilage sGAG content in human osteoarthritis subjects in clinical research. (©) RSNA, 2015.
    Full-text · Article · Nov 2015 · Radiology
  • Source
    Dataset: AkkusZ 2015

    Full-text · Dataset · Nov 2015
  • Source
    Dataset: AkkusZ 2015

    Full-text · Dataset · Nov 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In a continuous setting, diffeomorphisms generated by stationary velocity fields (SVF) are invertible transformations with differen-tiable inverses. However, due to the numerical integration of the velocity field, inverse consistency is not achieved in practice. In SVF based image registration, inverse consistency is therefore often enforced through a penalty term. Existing penalty terms penalize the inverse consistency error generated by the composition of the forward and backward transformations. However, in such terms, a higher consistency requirement pushes the transformation towards linearity due to the discretization involved and fixed number of integration time-steps. In this paper, we propose a method to both penalize inverse consistency error and to adaptively set the number of integration time-steps required, so that the predicted maximum inverse consistency error is bounded, taking into account discretization errors. This formulation allows more flexibility in the transformation model to realize complex deformations while still achieving the desired level of inverse consistency. Using synthetic examples, we show that the measured inverse consistency and the predicted inverse consistency match. Also, the proposed method is able to achieve more accurate image registration. On the MGH10 dataset, the Jaccard index of the proposed method on inter-subject registration reaches the same level as the registration scheme using a fixed-time step and the conventional penalty term while using a lower number of integration time-steps, thus saving on the computational time.
    Full-text · Conference Paper · Oct 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose an automated Euler's time-step adjustment scheme for diffeomorphic image registration using stationary velocity fields (SVFs). The proposed variational problem aims at bounding the inverse consistency error by adaptively adjusting the number of Euler's step required to realize the time integration. This particular formulation allows us to gain computationally since only relevant number of time steps are taken. We parameterize the SVFs using multi-scale Wendland kernels through the kernel bundle framework. In terms of performance, the proposed scheme reaches the same accuracy as a fixed time-step scheme however at a much less computational cost.
    Full-text · Conference Paper · Jul 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We evaluate the integration of 3D preoperative computed tomography angiography of the coronary arteries with intraoperative 2D X-ray angiographies by a recently proposed novel registration-by-regression method. The method relates image features of 2D projection images to the transformation parameters of the 3D image. We compared different sets of features and studied the influence of preprocessing the training set. For the registration evaluation, a gold standard was developed from eight X-ray angiography sequences from six different patients. The alignment quality was measured using the 3D mean target registration error (mTRE). The registration-by-regression method achieved moderate accuracy (median mTRE of 15 mm) on real images. It does therefore not provide yet a complete solution to the 3D–2D registration problem but it could be used as an initialisation method to eliminate the need for manual initialisation.
    Full-text · Article · Jun 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: To investigate arterial spin labeling (ASL)-MRI for the early diagnosis of and differentiation between the two most common types of presenile dementia: Alzheimer's disease (AD) and frontotemporal dementia (FTD), and for distinguishing age-related from pathological perfusion changes. Thirteen AD and 19 FTD patients, and 25 age-matched older and 22 younger controls underwent 3D pseudo-continuous ASL-MRI at 3 T. Gray matter (GM) volume and cerebral blood flow (CBF), corrected for partial volume effects, were quantified in the entire supratentorial cortex and in 10 GM regions. Sensitivity, specificity and diagnostic performance were evaluated in regions showing significant CBF differences between patient groups or between patients and older controls. AD compared with FTD patients had hypoperfusion in the posterior cingulate cortex, differentiating these with a diagnostic performance of 74 %. Compared to older controls, FTD patients showed hypoperfusion in the anterior cingulate cortex, whereas AD patients showed a more widespread regional hypoperfusion as well as atrophy. Regional atrophy was not different between AD and FTD. Diagnostic performance of ASL to differentiate AD or FTD from controls was good (78-85 %). Older controls showed global hypoperfusion compared to young controls. ASL-MRI contributes to early diagnosis of and differentiation between presenile AD and FTD. • ASL-MRI facilitates differentiation of early Alzheimer's disease and frontotemporal dementia. • Posterior cingulate perfusion is lower in Alzheimer's disease than frontotemporal dementia. • Compared to controls, Alzheimer's disease patients show hypoperfusion in multiple regions. • Compared to controls, frontotemporal dementia patients show focal anterior cingulate hypoperfusion. • Global decreased perfusion in older adults differs from hypoperfusion in dementia.
    Full-text · Article · May 2015 · European Radiology
  • Source
    Esther E Bron · Marion Smits · Wiro J Niessen · Stefan Klein
    [Show abstract] [Hide abstract]
    ABSTRACT: Computer-aided diagnosis of dementia using a support vector machine (SVM) can be improved with feature selection. The relevance of individual features can be quantified from the SVM weights as a significance map (p-map). Although these p-maps previously showed clusters of relevant voxels in dementia-related brain regions, they have not yet been used for feature selection. Therefore, we introduce two novel feature selection methods based on p-maps using a direct approach (filter) and an iterative approach (wrapper). To evaluate these p-map feature selection methods, we compared them with methods based on the SVM weight vector directly, t-statistics and expert knowledge. We used MRI data from the Alzheimer’s Disease Neuroimaging Initiative classifying Alzheimer’s disease (AD) patients, mild cognitive impairment (MCI) patients who converted to AD (MCIc), MCI patients who did not convert to AD (MCInc), and cognitively normal controls (CN). Features for each voxel were derived from gray matter morphometry. Feature selection based on the SVM weights gave better results than t-statistics and expert knowledge. The p-map methods performed slightly better than those using the weight vector. The wrapper method scored better than the filter method. Recursive feature elimination based on the p-map improved most for AD-CN: the area under the receiver-operating-characteristic curve (AUC) significantly increased from 90.3% without feature selection to 92.0% when selecting 1.5%-3% of the features. This feature selection method also improved the other classifications: AD-MCI 0.1% improvement in AUC (not significant), MCI-CN 0.7%, and MCIc-MCInc 0.1% (not significant). Although the performance improvement due to feature selection was limited, the methods based on the p-map generally had the best performance and were therefore better in estimating the relevance of individual features.
    Full-text · Article · May 2015 · IEEE Journal of Biomedical and Health Informatics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi- center data set. Using clinical practice as starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer’s disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with in total 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimer’s Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.
    Full-text · Article · May 2015 · NeuroImage
  • Source

    Preview · Article · May 2015 · Journal of Clinical Bioinformatics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel three-dimensional (3D) T1 and T2 mapping protocol for the carotid artery is presented. A 3D black-blood imaging sequence was adapted allowing carotid T1 and T2 mapping using multiple flip angles and echo time (TE) preparation times. B1 mapping was performed to correct for spatially varying deviations from the nominal flip angle. The protocol was optimized using simulations and phantom experiments. In vivo scans were performed on six healthy volunteers in two sessions, and in a patient with advanced atherosclerosis. Compensation for patient motion was achieved by 3D registration of the inter/intrasession scans. Subsequently, T1 and T2 maps were obtained by maximum likelihood estimation. Simulations and phantom experiments showed that the bias in T1 and T2 estimation was < 10% within the range of physiological values. In vivo T1 and T2 values for carotid vessel wall were 844 ± 96 and 39 ± 5 ms, with good repeatability across scans. Patient data revealed altered T1 and T2 values in regions of atherosclerotic plaque. The 3D T1 and T2 mapping of the carotid artery is feasible using variable flip angle and variable TE preparation acquisitions. We foresee application of this technique for plaque characterization and monitoring plaque progression in atherosclerotic patients. Magn Reson Med, 2015. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.
    Full-text · Article · Apr 2015 · Magnetic Resonance in Medicine
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Carotid plaque segmentation in B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) is crucial to the assessment of plaque morphology and composition, which are linked to plaque vulnerability. Segmentation in BMUS is challenging because of noise, artifacts and echo-lucent plaques. CEUS allows better delineation of the lumen but contains artifacts and lacks tissue information. We describe a method that exploits the combined information from simultaneously acquired BMUS and CEUS images. Our method consists of non-rigid motion estimation, vessel detection, lumen-intima segmentation and media-adventitia segmentation. The evaluation was performed in training (n = 20 carotids) and test (n = 28) data sets by comparison with manually obtained ground truth. The average root-mean-square errors in the training and test data sets were comparable for media-adventitia (411 ± 224 and 393 ± 239 μm) and for lumen-intima (362 ± 192 and 388 ± 200 μm), and were comparable to inter-observer variability. To the best of our knowledge, this is the first method to perform fully automatic carotid plaque segmentation using combined BMUS and CEUS. Copyright © 2014 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.
    Full-text · Article · Feb 2015 · Ultrasound in Medicine & Biology
  • Dirk H J Poot · Stefan Klein
    [Show abstract] [Hide abstract]
    ABSTRACT: In this work we present a framework for reliably detecting significant differences in quantitative magnetic resonance imaging (MRI) and evaluate it with diffusion tensor imaging (DTI) experiments. As part of this framework we propose a new spatially regularized maximum likelihood estimator that simultaneously estimates the quantitative parameters and the spatially -smoothly- varying noise level from the acquisitions. The noise level estimation method does not require repeated acquisitions. We show that the amount of regularization in this method can be set a-priori to achieve a desired coefficient of variation of the estimated noise level. The noise level estimate allows the construction of a Cram´er-Rao-lower-bound based test statistic that reliably assesses the significance of differences between voxels within a scan or across different scans. We show that the regularized noise level estimate improves upon existing methods and results in a substantially increased precision of the uncertainty estimates of the DTI parameters. It enables correct specification of the null distribution of the test statistic and with it the test statistic obtains the highest sensitivity and specificity. The source code of the estimation framework, test statistic and experiment scripts are made available to the community.
    No preview · Article · Dec 2014 · IEEE Transactions on Medical Imaging
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In standard B-mode ultrasound (BMUS), segmentation of the lumen of atherosclerotic carotid arteries and studying the lumen geometry over time are difficult owing to irregular lumen shapes, noise, artifacts, and echolucent plaques. Contrast enhanced ultrasound (CEUS) improves lumen visualization, but lumen segmentation remains challenging owing to varying intensities, CEUS-specific artifacts and lack of tissue visualization. To overcome these challenges, we propose a novel method using simultaneously acquired BMUS&CEUS image sequences. Initially, the method estimates nonrigid motion (NME) from the image sequences, using intensity-based image registration. The motion-compensated image sequence is then averaged to obtain a single 'epitome' image with improved signal-to-noise ratio. The lumen is segmented from the epitome image through an intensity joint-histogram classification and a graph-based segmentation. NME was validated by comparing displacements with manual annotations in eleven carotids. The average root-mean-squareerror (RMSE) was 112 73 μm. Segmentation results were validated against manual delineations in the epitome images of two different datasets, respectively containing eleven (RMSE 191 43 μm) and ten (RMSE 351 176 μm) carotids. From the deformation fields, we derived arterial distensibility with values comparable to the literature. The average errors in all experiments were in the inter-observer variability range. To the best of our knowledge, this is the first study exploiting combined BMUS&CEUS images for atherosclerotic carotid lumen segmentation.
    Full-text · Article · Nov 2014 · IEEE Transactions on Medical Imaging
  • [Show abstract] [Hide abstract]
    ABSTRACT: Background To evaluate the influence of image registration on apparent diffusion coefficient (ADC) images obtained from abdominal free-breathing diffusion-weighted MR images (DW-MRIs).MethodsA comprehensive pipeline based on automatic three-dimensional nonrigid image registrations is developed to compensate for misalignments in DW-MRI datasets obtained from five healthy subjects scanned twice. Motion is corrected both within each image and between images in a time series. ADC distributions are compared with and without registration in two abdominal volumes of interest (VOIs). The effects of interpolations and Gaussian blurring as alternative strategies to reduce motion artifacts are also investigated.ResultsAmong the four considered scenarios (no processing, interpolation, blurring and registration), registration yields the best alignment scores. Median ADCs vary according to the chosen scenario: for the considered datasets, ADCs obtained without processing are 30% higher than with registration. Registration improves voxelwise reproducibility at least by a factor of 2 and decreases uncertainty (Fréchet-Cramér-Rao lower bound). Registration provides similar improvements in reproducibility and uncertainty as acquiring four times more data.Conclusion Patient motion during image acquisition leads to misaligned DW-MRIs and inaccurate ADCs, which can be addressed using automatic registration. J. Magn. Reson. Imaging 2014.
    No preview · Article · Nov 2014 · Journal of Magnetic Resonance Imaging
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Support vector machine significance maps (SVM p-maps) previously showed clusters of significantly different voxels in dementia-related brain regions. We propose a novel feature selection method for classification of dementia based on these p-maps. In our approach, the SVM p-maps are calculated on the training set with a time-efficient analytic approximation. The features that are most significant on the p-map are selected for classification with an SVM classifier. We validated our method using MRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), classifying Alzheimer’s disease (AD) patients, mild cognitive impairment (MCI) patients who converted to AD within 18 months, MCI patients who did not convert to AD, and cognitively normal controls (CN). The voxel-wise features were based on gray matter morphometry. We compared p-map feature selection to classification without feature selection and feature selection based on t-tests and expert knowledge. Our method obtained in all experiments similar or better performance and robustness than classification without feature selection with a substantially reduced number of features. In conclusion, we proposed a novel and efficient feature selection method with promising results.
    Full-text · Conference Paper · Sep 2014
  • Wei Sun · Wiro J Niessen · Stefan Klein
    [Show abstract] [Hide abstract]
    ABSTRACT: In traditional free-form deformation (FFD) based registration, a B-spline basis function is commonly utilized to build the transformation model. As the B-spline order increases, the corresponding B-spline function becomes smoother. However, the higher-order B-spline has a larger support region, which means higher computational cost. For a given D-dimensional nth-order B-spline, an mth-order B-spline where (m < or = n) has (m +1/n + 1)D times lower computational complexity. Generally, the third-order B-spline is regarded as keeping a good balance between smoothness and computation time. A lower-order function is seldom used to construct the deformation field for registration since it is less smooth. In this research, we investigated whether lower-order B-spline functions can be utilized for efficient registration, by using a novel stochastic perturbation technique in combination with a postponed smoothing technique to higher B-spline order. Experiments were performed with 3D lung and brain scans, demonstrating that the lower-order B-spline FFD in combination with the proposed perturbation and postponed smoothing techniques even results in better accuracy and smoothness than the traditional third-order B-spline registration, while substantially reducing computational costs.
    No preview · Article · Sep 2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Because hypoperfusion of brain tissue precedes atrophy in dementia, the detection of dementia may be advanced by the use of perfusion information. Such information can be obtained noninvasively with arterial spin labeling (ASL), a relatively new MR technique quantifying cerebral blood flow (CBF). Using ASL and structural MRI, we evaluated diagnostic classification in 32 prospectively included presenile early stage dementia patients and 32 healthy controls. Patients were suspected of Alzheimer's disease (AD) or frontotemporal dementia. Classification was based on CBF as perfusion marker, gray matter (GM) volume as atrophy marker, and their combination. These markers were each examined using six feature extraction methods: a voxel-wise method and a region of interest (ROI)-wise approach using five ROI-sets in the GM. These ROI-sets ranged in number from 72 brain regions to a single ROI for the entire supratentorial brain. Classification was performed with a linear support vector machine classifier. For validation of the classification method on the basis of GM features, a reference dataset from the AD Neuroimaging Initiative database was used consisting of AD patients and healthy controls. In our early stage dementia population, the voxelwise feature-extraction approach achieved more accurate results (area under the curve (AUC) range = 86 − 91%) than all other approaches (AUC = 57 − 84%). Used in isolation, CBF quantified with ASL was a good diagnostic marker for dementia. However, our findings indicated only little added diagnostic value when combining ASL with the structural MRI data (AUC = 91%), which did not significantly improve over accuracy of structural MRI atrophy marker by itself. Hum Brain Mapp, 2014. © 2014 Wiley Periodicals, Inc.
    Full-text · Article · Sep 2014 · Human Brain Mapping
  • Source
    Wei Sun · Wiro J. Niessen · Stefan Klein
    [Show abstract] [Hide abstract]
    ABSTRACT: B-spline based free-form deformation (FFD) is a widely used technique in nonrigid image registration. In general, a third-order B-spline function is used, because of its favorable trade-off between smoothness and computational cost. Compared with the third-order B-splines, a B-spline function with a lower order has shorter support length, which means it is computationally more attractive. However, a lower-order function is seldom used to construct the deformation field for registration since it is less smooth. In this work, we propose a randomly perturbed FFD strategy (RPFFD) which uses a lower-order B-spline FFD with a random perturbation around the original position to approximate a higher-order B-spline FFD in a stochastic fashion. For a given D-dimensional nth-order FFD, its corresponding (n − 1)th-order RPFFD has \((\frac{n}{n+1})^{D}\) times lower computational complexity. Experiments on 3D lung and brain data show that, with this lower computational complexity, the proposed RPFFD registration results in even slightly better accuracy and smoothness than the traditional higher-order FFD.
    Full-text · Chapter · Jul 2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Quantitative magnetic resonance imaging (qMRI) aims to extract quantitative parameters representing tissue properties from a series of images by modeling the image acquisition process. This requires the images to be spatially aligned but, due to patient motion, anatomical structures in the consecutive images may be misaligned. In this work, we propose a groupwise non-rigid image registration method for motion compensation in qMRI. The method minimizes a dissimilarity measure based on principal component analysis (PCA), exploiting the fact that intensity changes can be described by a low-dimensional acquisition model. Using an unbiased groupwise formulation of the registration problem, there is no need to choose a reference image as in conventional pairwise approaches. The method was evaluated on three applications: modified Look-Locker inversion recovery T 1 mapping in a porcine myocardium, black-blood variable flip-angle T 1 mapping in the carotid artery region, and apparent diffusion coefficient (ADC) mapping in the abdomen. The method was compared to a conventional pairwise alignment that uses a mutual information similarity measure. Registration accuracy was evaluated by computing precision of the estimated parameters of the qMRI model. The results show that the proposed method performs equally well or better than an optimized pairwise approach and is therefore a suitable motion compensation method for a wide variety of qMRI applications.
    Full-text · Conference Paper · Jul 2014

Publication Stats

2k Citations
167.95 Total Impact Points

Institutions

  • 2015
    • Universita' degli Studi "Magna Græcia" di Catanzaro
      • Department of Medical and Surgical Sciences
      Catanzaro, Calabria, Italy
  • 2009-2015
    • Erasmus MC
      • • Department of Radiology
      • • Department of Cardiology
      Rotterdam, South Holland, Netherlands
    • Universiteit Utrecht
      • Image Sciences Institute
      Utrecht, Utrecht, Netherlands
  • 2011-2014
    • Erasmus Universiteit Rotterdam
      • • Department of Radiology
      • • Department of Medical Informatics
      Rotterdam, South Holland, Netherlands
    • Delft University Of Technology
      • Department of Imaging Science and Technology
      Delft, South Holland, Netherlands
  • 2005-2010
    • University Medical Center Utrecht
      • Image Sciences Institute
      Utrecht, Provincie Utrecht, Netherlands