http://ieeexplore.ieee.org TOC Alert for Publication# 42 2010 February 09 29 2 C1 C4 116 29 2 C2 C2 43 For imaging problems in which numerical solutions need to be computed for both the inverse and the underlying forward problems, discretization can be a major factor that determines the accuracy of imaging. In this work, we analyze the effect of discretization on the accuracy of fluorescence diffuse optical tomography. We model the forward problem by a pair of diffusion equations at the excitation and emission wavelengths and consider a finite element discretization method for the numerical solution of the forward problem. For the inverse problem, we use an optimization framework which allows incorporation of a priori information in the form of zeroth- and first-order Tikhonov regularization terms. Next, we convert the inverse problem into a variational problem and use Galerkin projection to discretize the inverse problem. Following the discretization, we analyze the error in reconstructed images due to the discretization of the forward and inverse problems and present two theorems which point out the factors that may lead to high error such as the mutual dependence of the forward and inverse problems, the number of sources and detectors, their configuration and their positions with respect to fluorophore concentration, and the formulation of the inverse problem. Finally, we demonstrate the results and implications of our error analysis by numerical experiments. In the second part of the paper, we apply our results to design novel adaptive discretization algorithms. ]]> 29 2 217 229 487 In the first part of this work, we analyze the effect of discretization on the accuracy of fluorescence diffuse optical tomography (FDOT). Our error analysis provides two new error estimates which present a direct relationship between the error in the reconstructed fluorophore concentration and the discretization of the forward and inverse problems. In this paper, based on these error estimates, we develop two new adaptive mesh generation algorithms for the numerical solutions of the forward and inverse problems in FDOT, with the objective of error reduction in the reconstructed optical images due to discretization while keeping the size of the discretized forward and inverse problems within the allowable limits. We present three-dimensional numerical simulations to demonstrate the improvements in accuracy, resolution and detectability of small heterogeneities in reconstructed images provided by the use of the new adaptive mesh generation algorithms. Finally, we compare our algorithms both analytically and numerically with the existing conventional adaptive mesh generation algorithms. ]]> 29 2 230 245 1643 Intestinal motility assessment with video capsule endoscopy arises as a novel and challenging clinical fieldwork. This technique is based on the analysis of the patterns of intestinal contractions shown in a video provided by an ingestible capsule with a wireless micro-camera. The manual labeling of all the motility events requires large amount of time for offline screening in search of findings with low prevalence, which turns this procedure currently unpractical. In this paper, we propose a machine learning system to automatically detect the phasic intestinal contractions in video capsule endoscopy, driving a useful but not feasible clinical routine into a feasible clinical procedure. Our proposal is based on a sequential design which involves the analysis of textural, color, and blob features together with SVM classifiers. Our approach tackles the reduction of the imbalance rate of data and allows the inclusion of domain knowledge as new stages in the cascade. We present a detailed analysis, both in a quantitative and a qualitative way, by providing several measures of performance and the assessment study of interobserver variability. Our system performs at 70% of sensitivity for individual detection, whilst obtaining equivalent patterns to those of the experts for density of contractions. ]]> 29 2 246 259 1322 Since the introduction of 3-D rotational X-ray imaging, protocols for 3-D rotational coronary artery imaging have become widely available in routine clinical practice. Intra-procedural cardiac imaging in a computed tomography (CT)-like fashion has been particularly compelling due to the reduction of clinical overhead and ability to characterize anatomy at the time of intervention. We previously introduced a clinically feasible approach for imaging the left atrium and pulmonary veins (LAPVs) with short contrast bolus injections and scan times of ${sim 4}$ –10 s. The resulting data have sufficient image quality for intra-procedural use during electro-anatomic mapping (EAM) and interventional guidance in atrial fibrillation (AF) ablation procedures. In this paper, we present a novel technique to intra-procedural surface generation which integrates fully-automated segmentation of the LAPVs for guidance in AF ablation interventions. Contrast-enhanced rotational X-ray angiography (3-D RA) acquisitions in combination with filtered-back-projection-based reconstruction allows for volumetric interrogation of LAPV anatomy in near-real-time. An automatic model-based segmentation algorithm allows for fast and accurate LAPV mesh generation despite the challenges posed by image quality; relative to pre-procedural cardiac CT/MR, 3-D RA images suffer from more artifacts and reduced signal-to-noise. We validate our integrated method by comparing 1) automatic and manual segmentations of intra-procedural 3-D RA data, 2) automatic segmentations of intra-procedural 3-D RA and pre-procedural CT/MR data, and 3) intra-procedural EAM point cloud data with automatic segmentations of 3-D RA and CT/MR data. Our validation results for automatically segmented intra-procedural 3-D RA data show average segmentation errors of 1) ${sim 1.3}~{rm mm}$ com- pared with manual 3-D RA segmentations 2) ${sim 2.3}~{rm mm}$ compared with automatic segmentation of pre-procedural CT/MR data and 3) ${sim 2.1}~{rm mm}$ compared with registered intra-procedural EAM point clouds. The overall experiments indicate that LAPV surfaces can be automatically segmented intra-procedurally from 3-D RA data with comparable quality relative to meshes derived from pre-procedural CT/MR. ]]> 29 2 260 272 2207 Magnetic susceptibility is an important physical property of tissues, and can be used as a contrast mechanism in magnetic resonance imaging (MRI). Recently, targeting contrast agents by conjugation with signaling molecules and labeling stem cells with contrast agents have become feasible. These contrast agents are strongly paramagnetic, and the ability to quantify magnetic susceptibility could allow accurate measurement of signaling and cell localization. Presented here is a technique to estimate arbitrary magnetic susceptibility distributions by solving an ill-posed inversion problem from field maps obtained in an MRI scanner. Two regularization strategies are considered: conventional Tikhonov regularization and a sparsity promoting nonlinear regularization using the $ell_{1}$ norm. Proof of concept is demonstrated using numerical simulations, phantoms, and in a stroke model in a rat. Initial experience indicates that the nonlinear regularization better suppresses noise and streaking artifacts common in susceptibility estimation. ]]> 29 2 273 281 673 Quantitative analysis of biological image data generally involves the detection of many subresolution spots. Especially in live cell imaging, for which fluorescence microscopy is often used, the signal-to-noise ratio (SNR) can be extremely low, making automated spot detection a very challenging task. In the past, many methods have been proposed to perform this task, but a thorough quantitative evaluation and comparison of these methods is lacking in the literature. In this paper, we evaluate the performance of the most frequently used detection methods for this purpose. These include seven unsupervised and two supervised methods. We perform experiments on synthetic images of three different types, for which the ground truth was available, as well as on real image data sets acquired for two different biological studies, for which we obtained expert manual annotations to compare with. The results from both types of experiments suggest that for very low SNRs $(approx 2)$, the supervised (machine learning) methods perform best overall. Of the unsupervised methods, the detectors based on the so-called $h$ -dome transform from mathematical morphology or the multiscale variance-stabilizing transform perform comparably, and have the advantage that they do not require a cumbersome learning stage. At high SNRs $(> 5)$, the difference in performance of all considered detectors becomes negligible. ]]> 29 2 282 301 5679 This paper presents a new algorithm for denoising dynamic contrast-enhanced (DCE) MR images. It is a novel variation on the nonlocal means (NLM) algorithm. The algorithm, called dynamic nonlocal means (DNLM), exploits the redundancy of information in the temporal sequence of images. Empirical evaluations of the performance of the DNLM algorithm relative to seven other denoising methods—simple Gaussian filtering, the original NLM algorithm, a trivial extension of NLM to include the temporal dimension, bilateral filtering, anisotropic diffusion filtering, wavelet adaptive multiscale products threshold, and traditional wavelet thresholding—are presented. The evaluations include quantitative evaluations using simulated data and real data (20 DCE-MRI data sets from routine clinical breast MRI examinations) as well as qualitative evaluations using the same real data (24 observers: 14 image/signal-processing specialists, 10 clinical breast MRI radiographers). The results of the quantitative evaluation using the simulated data show that the DNLM algorithm consistently yields the smallest MSE between the denoised image and its corresponding original noiseless version. The results of the quantitative evaluation using the real data provide evidence, at the $alpha =0.05$ level of significance, that the DNLM algorithm yields the smallest MSE between the denoised image and its corresponding original noiseless version. The results of the qualitative evaluation provide evidence, at the $alpha=0.05$ level of significance, that the DNLM algorithm performs visually better than all of the other algorithms. Collectively the qualitative and quantitative results suggest that the DNLM algorithm more effectively attenuates noise in DCE MR images than any of the other algorithms. ]]> 29 2 302 310 816 The use of time-of-flight (TOF) information during positron emission tomography (PET) reconstruction has been found to improve the image quality. In this work we quantified this improvement using two existing methods: 1) a very simple analytical expression only valid for a central point in a large uniform disk source and 2) efficient analytical approximations for postfiltered maximum likelihood expectation maximization (MLEM) reconstruction with a fixed target resolution, predicting the image quality in a pixel or in a small region of interest based on the Fisher information matrix. Using this latter method the weighting function for filtered backprojection reconstruction of TOF PET data proposed by C. Watson can be derived. The image quality was investigated at different locations in various software phantoms. Simplified as well as realistic phantoms, measured both with TOF PET systems and with a conventional PET system, were simulated. Since the time resolution of the system is not always accurately known, the effect on the image quality of using an inaccurate kernel during reconstruction was also examined with the Fisher information-based method. First, we confirmed with this method that the variance improvement in the center of a large uniform disk source is proportional to the disk diameter and inversely proportional to the time resolution. Next, image quality improvement was observed in all pixels, but in eccentric and high-count regions the contrast-to-noise ratio (CNR) increased less than in central and low- or medium-count regions. Finally, the CNR was seen to decrease when the time resolution was inaccurately modeled (too narrow or too wide) during reconstruction. Although the maximum CNR is not very sensitive to the time resolution error, using an inaccurate TOF kernel tends to introduce artifacts in the reconstructed image. ]]> 29 2 311 321 1044 During neurosurgery, nonrigid brain deformation prevents preoperatively-acquired images from accurately depicting the intraoperative brain. Stereo vision systems can be used to track intraoperative cortical surface deformation and update preoperative brain images in conjunction with a biomechanical model. However, these stereo systems are often plagued with calibration error, which can corrupt the deformation estimation. In order to decouple the effects of camera calibration from the surface deformation estimation, a framework that can solve for disparate and often competing variables is needed. Game theory, which was developed to handle decision making in this type of competitive environment, has been applied to various fields from economics to biology. In this paper, game theory is applied to cortical surface tracking during neocortical epilepsy surgery and used to infer information about the physical processes of brain surface deformation and image acquisition. The method is successfully applied to eight in vivo cases, resulting in an 81% decrease in mean surface displacement error. This includes a case in which some of the initial camera calibration parameters had errors of 70%. Additionally, the advantages of using a game theoretic approach in neocortical epilepsy surgery are clearly demonstrated in its robustness to initial conditions. ]]> 29 2 322 338 1802 It is a well-known property in Fourier transform magnetic resonance imaging (MRI) that rigid body translational motion in image space results in linear phase accumulation in $k$ -space. This work describes Multiple Overlapping $k$-space Junctions for Investigating Translating Objects (MOJITO), a correction scheme based on phase differences at trajectory intersections caused by 2-D alterations in the position of an object during MR imaging. The algorithm allows both detection and correction of motion artifacts caused by 2-D rigid body translational motion. Although similar in concept to navigator echoes, MOJITO does not require a repeating path through $k$-space, uses $k$-space data from a broader region of $k$ -space, and uses the repeated data in image reconstruction; this provides the potential for a highly efficient self-navigating motion correction method. Here, the concept and theoretical basis of MOJITO is demonstrated using the continuous sampling BOWTIE trajectory in simulation and MR experiments. This particular trajectory is selected since it is well suited for such an algorithm due to numerous trajectory intersections. Specifically, the validity of the technique in the presence of noise and off-resonance effects is demonstrated through simulation. ]]> 29 2 339 349 1143 In this study, a combination of active shape model (ASM) and active appearance model (AAM) was used to segment the left and right ventricles of normal and Tetralogy of Fallot (TOF) hearts on 4-D (3-D+time) MR images. For each ventricle, a 4-D model was first used to achieve robust preliminary segmentation on all cardiac phases simultaneously and a 3-D model was then applied to each phase to improve local accuracy while maintaining the overall robustness of the 4-D segmentation. On 25 normal and 25 TOF hearts, in comparison to the expert traced independent standard, our comprehensive performance assessment showed subvoxel segmentation accuracy, high overlap ratios, good ventricular volume correlations, and small percent volume differences. Following 4-D segmentation, novel quantitative shape and motion features were extracted using shape information, volume-time and dV/dt curves, analyzed and used for disease status classification. Automated discrimination between normal/TOF subjects achieved 90%–100% sensitivity and specificity. The features obtained from TOF hearts show higher variability compared to normal subjects, suggesting their potential use as disease progression indicators. The abnormal shape and motion variations of the TOF hearts were accurately captured by both the segmentation and feature characterization. ]]> 29 2 350 364 1923 Fluorescence molecular tomography (FMT) allows in vivo localization and quantification of fluorescence biodistributions in whole animals. The ill-posed nature of the tomographic reconstruction problem, however, limits the attainable resolution. Improvements in resolution and overall imaging performance can be achieved by forming image priors from geometric information obtained by a secondary anatomical or functional high-resolution imaging modality such as X-ray computed tomography or magnetic resonance imaging. A particular challenge in using image priors is to avoid the use of assumptions that may bias the solution and reduced the accuracy of the inverse problem. This is particularly relevant in FMT inversions where there is not an evident link between secondary geometric information and the underlying fluorescence biodistribution. We present here a new, two step approach to incorporating structural priors into the FMT inverse problem. By using the anatomic information to define a low dimensional inverse problem, we obtain a solution which we then use to determine the parameters defining a spatially varying regularization matrix for the full resolution problem. The regularization term is thus customized for each data set and is guided by the data rather than depending only on user defined a priori assumptions. Results are presented for both simulated and experimental data sets, and show significant improvements in image quality as compared to traditional regularization techniques. ]]> 29 2 365 374 513 Detection of multiple lesions in images is a medically important task and free-response receiver operating characteristic (FROC) analyses and its variants, such as alternative FROC (AFROC) analyses, are commonly used to quantify performance in such tasks. However, ideal observers that optimize FROC or AFROC performance metrics have not yet been formulated in the general case. If available, such ideal observers may turn out to be valuable for imaging system optimization and in the design of computer aided diagnosis techniques for lesion detection in medical images. In this paper, we derive ideal AFROC and FROC observers. They are ideal in that they maximize, amongst all decision strategies, the area, or any partial area, under the associated AFROC or FROC curve. Calculation of observer performance for these ideal observers is computationally quite complex. We can reduce this complexity by considering forms of these observers that use false positive reports derived from signal-absent images only. We also consider a Bayes risk analysis for the multiple-signal detection task with an appropriate definition of costs. A general decision strategy that minimizes Bayes risk is derived. With particular cost constraints, this general decision strategy reduces to the decision strategy associated with the ideal AFROC or FROC observer. ]]> 29 2 375 386 254 Several different reconstruction algorithms have been proposed for photoacoustic tomography, most of which presuppose that the acoustic properties of the medium are constant and homogeneous. In practice, there are often unknown spatial variations in the acoustic properties, and these algorithms give, at best, only approximate estimates of the true image. The question as to which approach is the most robust in these circumstances is therefore one of practical importance. Image reconstruction by “time reversal”—using a numerical propagation model with a time-varying boundary condition corresponding to the measured data in reversed temporal order—has been shown to be less restrictive in its assumptions than most, and therefore a good candidate for a general and practically useful algorithm. Here, it is shown that such reconstruction algorithms can “trap” time reversed scattered waves, leading to artifacts within the image region. Two ways to mitigate this effect are proposed. ]]> 29 2 387 396 1953 Nodule growth as observed in computed tomography (CT) scans acquired at different times is the primary feature to malignancy of indeterminate small lung nodules. In this paper, we propose the estimation of nodule size through a scale–space representation which needs no segmentation and has high intra- and inter-operator reproducibility. Lung nodules usually appear in CT images as blob-like patterns and can be analyzed in the scale–space by Laplacian of Gaussian (${LoG}$ ) kernels. For each nodular pattern the ${LoG}$ scale–space signature was computed and the related characteristic scale adopted as measurement of nodule size. Both in vitro and in vivo validation of ${LoG}$ characteristic scale were carried out. In vitro validation was done by 40 nondeformable phantoms and 10 deformable phantoms. A close relationship between the characteristic scale and the equivalent diameter, i.e., the diameter of the sphere having the same volume of nodules, (Pearson correlation coefficient was 0.99) and, for nodules undergoing little deformations (obtained at constant volume), small variability of the characteristic scale was observed. The in vivo validation was performed on low and standard-dose CT scans collected from the ITALUNG screening trial (86 nodules) and from the LIDC public data set (89 solid nodules and 40 part-solid nodules or ground-glass opacities). The Pearson correlation coefficient between characteristic scale and equivalent diameter was 0.83–0.93 for ITALUNG and 0.68–0.83 for LIDC data set. Intra- and inter-operator reproducibility of charact- eristic scale was excellent: on a set of 40 lung nodules of ITALUNG data, two radiologists produced identical results in repeated measurements. The scan–rescan variability of the characteristic scale was also investigated on 86 two-year-stable solid lung nodules (each one observed, on average, in four CT scans) identified in the ITALUNG screening trial: a coefficient of repeatability of about 0.9 mm was observed. Experimental evidence supports the clinical use of the ${LoG}$ characteristic scale to measure nodule size in CT imaging. ]]> 29 2 397 409 2130 A pressure ulcer is a clinical pathology of localized damage to the skin and underlying tissue caused by pressure, shear, or friction. Diagnosis, treatment, and care of pressure ulcers are costly for health services. Accurate wound evaluation is a critical task for optimizing the efficacy of treatment and care. Clinicians usually evaluate each pressure ulcer by visual inspection of the damaged tissues, which is an imprecise manner of assessing the wound state. Current computer vision approaches do not offer a global solution to this particular problem. In this paper, a hybrid approach based on neural networks and Bayesian classifiers is used in the design of a computational system for automatic tissue identification in wound images. A mean shift procedure and a region-growing strategy are implemented for effective region segmentation. Color and texture features are extracted from these segmented regions. A set of $k$ multilayer perceptrons is trained with inputs consisting of color and texture patterns, and outputs consisting of categorical tissue classes which are determined by clinical experts. This training procedure is driven by a $k$-fold cross-validation method. Finally, a Bayesian committee machine is formed by training a Bayesian classifier to combine the classifications of the $k$ neural networks. Specific heuristics based on the wound topology are designed to significantly improve the results of the classification. We obtain high efficiency rates from a binary cascade approach for tissue identification. Results are compared with other similar machine-learning approaches, including multiclass Bayesian committee machine classifiers and support vector machines. The different techniques analyzed in this paper show high global classification accuracy rates. - Our binary cascade approach gives high global performance rates (average sensitivity $=78.7%$ , specificity $=94.7%$ , and accuracy $=91.5%$ ) and shows the highest average sensitivity score ( $=$86.3%) when detecting necrotic tissue in the wound. ]]> 29 2 410 427 1142 Classifier design for a given classification task needs to take into consideration both the complexity of the classifier and the size of the dataset that is available for training the classifier. With limited training data, as often is the situation in computer-aided diagnosis of medical images, a classifier with simple structure (e.g., a linear classifier) is more robust and therefore preferred. We propose a novel two-class classifier, which we call a hybrid linear/nonlinear classifier (HLNLC), that involves two stages: the input features are linearly combined to form a scalar variable in the first stage and then the likelihood ratio of the scalar variable is used as the decision variable for classification. We first develop the theory of HLNLC by assuming that the feature data follow normal distributions. We show that the commonly used Fisher's linear discriminant function is generally not the optimal linear function in the first stage of the HLNLC. We formulate an optimization problem to solve for the optimal linear function in the first stage of the HLNLC, i.e., the linear function that maximizes the area under the receiver operating characteristic (ROC) curve of the HLNLC. For practical applications, we propose a robust implementation of the HLNLC by making a loose assumption that the two-class feature data arise from a pair of latent (rather than explicit) multivariate normal distributions. The novel hybrid classifier fills a gap between linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) in the sense that both its theoretical performance and its complexity lie between those of the LDA and those of the QDA. Simulation studies show that the hybrid linear/nonlinear classifier performs better than LDA without increasing the classifier complexity accordingly. With a finite number of training samples, the HLNLC can perform better than that of the ideal observer due to its simplicity. Finally, we demonstrate the application of the HL- NLC in computer-aided diagnosis of breast lesions in ultrasound images. ]]> 29 2 428 441 354 We present a nonparametric regression method for denoising 3-D image sequences acquired via fluorescence microscopy. The proposed method exploits the redundancy of the 3-D+time information to improve the signal-to-noise ratio of images corrupted by Poisson-Gaussian noise. A variance stabilization transform is first applied to the image-data to remove the dependence between the mean and variance of intensity values. This preprocessing requires the knowledge of parameters related to the acquisition system, also estimated in our approach. In a second step, we propose an original statistical patch-based framework for noise reduction and preservation of space-time discontinuities. In our study, discontinuities are related to small moving spots with high velocity observed in fluorescence video-microscopy. The idea is to minimize an objective nonlocal energy functional involving spatio-temporal image patches. The minimizer has a simple form and is defined as the weighted average of input data taken in spatially-varying neighborhoods. The size of each neighborhood is optimized to improve the performance of the pointwise estimator. The performance of the algorithm (which requires no motion estimation) is then evaluated on both synthetic and real image sequences using qualitative and quantitative criteria. ]]> 29 2 442 454 4983 Computer-aided detection (CAD) schemes are decision making support tools, useful to overcome limitations of problematic clinical procedures. Trans-rectal ultrasound image based CAD would be extremely important to support prostate cancer diagnosis. An effective approach to realize a CAD scheme for this purpose is described in this work, employing a multi-feature kernel classification model based on generalized discriminant analysis. The mutual information of feature value and tissue pathological state is used to select features essential for tissue characterization. System-dependent effects are reduced through predictive deconvolution of the acquired radio-frequency signals. A clinical study, performed on ground truth images from biopsy findings, provides a comparison of the classification model applied before and after deconvolution, showing in the latter case a significant gain in accuracy and area under the receiver operating characteristic curve. ]]> 29 2 455 464 525 A hybrid imaging system for simultaneous fluorescence tomography and X-ray computed tomography (XCT) of small animals has been developed and presented. The system capitalizes on the imaging power of a 360 $^{circ}$-projection free-space fluorescence tomography system, implemented within a microcomputed tomography scanner. Image acquisition is based on techniques that automatically adjust a series of imaging parameters to offer a high dynamic range dataset. Image segmentation further allows the incorporation of structural priors in the optical reconstruction problem to improve the imaging performance. The functional system characteristics are showcased, and images from a brain imaging study are shown, which are reconstructed using XCT-derived priors into the optical forward problem. ]]> 29 2 465 473 1328 The electric properties (EPs) of biological tissue, i.e., the electric conductivity and permittivity, can provide important information in the diagnosis of various diseases. The EPs also play an important role in specific absorption rate calculation, a major concern in high-field MRI, as well as in nonmedical areas such as wireless telecommunications. The high-field MRI system is accompanied by significant wave propagation effects, and the RF radiation is dependent on the EPs of biological tissue. On the basis of the measurement of the active transverse magnetic component of the applied RF field (known as ${rm B}_{1}$-mapping technique), we propose a dual-excitation algorithm, which uses two sets of measured ${rm B}_{1}$ data to noninvasively reconstruct the EPs of biological tissues. The finite-element method was utilized in 3-D modeling and ${rm B}_{1}$ field calculation. A series of computer simulations were conducted to evaluate the feasibility and performance of the proposed method on a 3-D head model within a TEM coil and a birdcage coil. Using a TEM coil, when noise free, the reconstructed EP distribution of tissues in the brain has relative errors of 12%–28% and correlated coefficients of greater than 0.91. Compared with other ${rm B}_{1}$-mapping-based reconstruction algorithms, our approach provides superior performance without the need for iterative computations. The present simulation results suggest that good reconstruction of EPs from B1 mapping can be achieved. ]]> 29 2 474 481 1947 Inkjet printing has been used to produce resonant radio frequency coils that are comparable to those produced by conventional printed circuit board (PCB) methods. The coils, which consist of a conductive loop and in-series capacitors, form part of a receiver circuit that is used for magnetic resonance imaging (MRI). The resonant circuit is selective at the predetermined frequency of 400 MHz. The required electrical components (resistor, capacitor, and inductor) were produced by inkjet printing, with scaling experiments for resistor and capacitor performed before the complete loops with integrated capacitors were printed. Numerical simulation was used to determine the required values for the components. The inkjet printed circuit was combined with a small tuning and matching board before being connected to a network analyzer and the MRI hardware. With a matching of ${-}$ 38 dB at 400 MHz the achieved results were comparable to those from standard PCB techniques. The performance of the inkjet printed component as a receiver device for nuclear magnetic resonance and MRI was verified by imaging reference phantoms and a whole kiwifruit; it compares favorably to standard MRI devices. Inkjet printing can, therefore, be considered a feasible technique for producing MRI receiver circuits on flexible substrates. ]]> 29 2 482 487 916 This paper presents a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We describe and evaluate the method with a specific focus on the detection of lesion regions in uterine cervix images. The watershed segmentation map of the input image is modeled using a Markov random field (MRF) in which watershed regions correspond to binary random variables indicating whether the region is part of the lesion tissue or not. The local pairwise factors on the arcs of the watershed map indicate whether the arc is part of the object boundary. The factors are based on supervised learning of a visual word distribution. The final lesion region segmentation is obtained using a loopy belief propagation applied to the watershed arc-level MRF. Experimental results on real data show state-of-the-art segmentation results on this very challenging task that, if necessary, can be interactively enhanced. ]]> 29 2 488 501 1920 In this paper, we propose the use of multiscale amplitude-modulation-frequency-modulation (AM-FM) methods for discriminating between normal and pathological retinal images. The method presented in this paper is tested using standard images from the early treatment diabetic retinopathy study. We use 120 regions of 40$,times,$40 pixels containing four types of lesions commonly associated with diabetic retinopathy (DR) and two types of normal retinal regions that were manually selected by a trained analyst. The region types included microaneurysms, exudates, neovascularization on the retina, hemorrhages, normal retinal background, and normal vessels patterns. The cumulative distribution functions of the instantaneous amplitude, the instantaneous frequency magnitude, and the relative instantaneous frequency angle from multiple scales are used as texture feature vectors. We use distance metrics between the extracted feature vectors to measure interstructure similarity. Our results demonstrate a statistical differentiation of normal retinal structures and pathological lesions based on AM-FM features. We further demonstrate our AM-FM methodology by applying it to classification of retinal images from the MESSIDOR database. Overall, the proposed methodology shows significant capability for use in automatic DR screening. ]]> 29 2 502 512 2245 Ultrasound B-mode scanning based on the echo intensity has become an important clinical tool for routine breast screening. The efficacy of the Nakagami parametric image based on the distribution of the backscattered signals for quantifying properties of breast tissue was recently evaluated. The B-mode and Nakagami images reflect different physical characteristic of breast tumors: the former describes the contour features, and the latter reflects the scatterer arrangement inside a tumor. The functional complementation of these two images encouraged us to propose a novel method of 2-D analysis based on describing the contour using the B-mode image and the scatterer properties using the Nakagami image, which may provide useful clues for classifying benign and malignant tumors. To validate this concept, raw data were acquired from 60 clinical cases, and five contour feature parameters (tumor circularity, standard deviation of the normalized radial length, area ratio, roughness index, and standard deviation of the shortest distance) and the Nakagami parameters of benign and malignant tumors were calculated. The receiver operating characteristic curve and fuzzy c-means clustering were used to evaluate the performances of combining the parameters in classifying tumors. The clinical results demonstrated the presence of a tradeoff between the sensitivity and specificity when either using a single parameter or combining two contour parameters to discriminate between benign and malignant cases. However, combining the contour parameters and the Nakagami parameter produces sensitivity and specificity that simultaneously exceed 80%, which means that the functional complementation from the B-scan and the Nakagami image indeed enhances the performance in diagnosing breast tumors. ]]> 29 2 513 522 786 The use of multiple independent simultaneous radio-frequency (RF) transmitters and coils, known as parallel transmission, has the potential to make multidimensional excitation applicable to a wide range of magnetic resonance imaging applications. The sensitivity profile of the RF coils in a parallel transmission system determines the performance of the system. We present a theoretical framework, allowing the evaluation of the performance of a coil array for parallel transmission. We show through theoretical analysis and Monte Carlo simulation that the proposed framework predicts the fidelity of excitation that can be achieved by a given coil configuration in the presence of noise in the measured coil sensitivity profiles. We evaluate the fidelity of excitation achieved by four candidate coil configurations for a four-channel parallel transmission system with noisy coil sensitivity estimates. Theoretical results are confirmed with Monte Carlo simulation. The results give insight into the design of coil configurations for parallel transmission. In particular, optimal fidelity of excitation for subsampled Cartesian excitation $k$ -space is achieved with a coil sensitivity profile having uniform amplitude and increasing linear phase for each channel. Such sensitivity profiles may be achieved with twisted birdcage coil designs. ]]> 29 2 523 530 1876 Classification of brain images obtained through functional magnetic resonance imaging (fMRI) poses a serious challenge to pattern recognition and machine learning due to the extremely large feature-to-instance ratio. This calls for revision and adaptation of the current state-of-the-art classification methods. We investigate the suitability of the random subspace (RS) ensemble method for fMRI classification. RS samples from the original feature set and builds one (base) classifier on each subset. The ensemble assigns a class label by either majority voting or averaging of output probabilities. Looking for guidelines for setting the two parameters of the method—ensemble size and feature sample size—we introduce three criteria calculated through these parameters: usability of the selected feature sets, coverage of the set of “important” features, and feature set diversity. Optimized together, these criteria work toward producing accurate and diverse individual classifiers. RS was tested on three fMRI datasets from single-subject experiments: the Haxby data (Haxby, 2001.) and two datasets collected in-house. We found that RS with support vector machines (SVM) as the base classifier outperformed single classifiers as well as some of the most widely used classifier ensembles such as bagging, AdaBoost, random forest, and rotation forest. The closest rivals were the single SVM and bagging of SVM classifiers. We use kappa-error diagrams to understand the success of RS. ]]> 29 2 531 542 1015 Interpolation is the means by which a continuously defined model is fit to discrete data samples. When the data samples are exempt of noise, it seems desirable to build the model by fitting them exactly. In medical imaging, where quality is of paramount importance, this ideal situation unfortunately does not occur. In this paper, we propose a scheme that improves on the quality by specifying a tradeoff between fidelity to the data and robustness to the noise. We resort to variational principles, which allow us to impose smoothness constraints on the model for tackling noisy data. Based on shift-, rotation-, and scale-invariant requirements on the model, we show that the $L_{p}$-norm of an appropriate vector derivative is the most suitable choice of regularization for this purpose. In addition to Tikhonov-like quadratic regularization, this includes edge-preserving total-variation-like (TV) regularization. We give algorithms to recover the continuously defined model from noisy samples and also provide a data-driven scheme to determine the optimal amount of regularization. We validate our method with numerical examples where we demonstrate its superiority over an exact fit as well as the benefit of TV-like nonquadratic regularization over Tikhonov-like quadratic regularization. ]]> 29 2 543 558 2124 We aim at improving quantitative measures of emphysema in computed tomography (CT) images of the lungs. Current standard measures, such as the relative area of emphysema (RA), rely on a single intensity threshold on individual pixels, thus ignoring any interrelations between pixels. Texture analysis allows for a much richer representation that also takes the local structure around pixels into account. This paper presents a texture classification-based system for emphysema quantification in CT images. Measures of emphysema severity are obtained by fusing pixel posterior probabilities output by a classifier. Local binary patterns (LBP) are used as texture features, and joint LBP and intensity histograms are used for characterizing regions of interest (ROIs). Classification is then performed using a $k$ nearest neighbor classifier with a histogram dissimilarity measure as distance. A 95.2% classification accuracy was achieved on a set of 168 manually annotated ROIs, comprising the three classes: normal tissue, centrilobular emphysema, and paraseptal emphysema. The measured emphysema severity was in good agreement with a pulmonary function test (PFT) achieving correlation coefficients of up to $vert rvert = 0.79$ in 39 subjects. The results were compared to RA and to a Gaussian filter bank, and the texture-based measures correlated significantly better with PFT than did RA. ]]> 29 2 559 569 1211 Background—Ultrasound elastography is now used worldwide in tissue characterization. The primary premises of elastography are that speckle kinematics reproduces underlying tissue kinematics and that tissue motion can be inferred from speckle tracking. This implicitly assumes that speckle pattern is a material property that can be tracked with respect to time and space. It is then convenient to express the motion of such a material property in terms of total derivative, also known as optical flow (OF) equations. Aims—The present paper introduces a new iterative OF-based elastography (OFBE) method devoted to B-mode data. The first OFBE iteration computes axial and lateral displacement fields. Such displacement fields are used for data rigid registration, prior to the second OFBE iteration which computes the 2-D strain tensor. Methods—The OFBE method was validated in the common carotid artery of rat hypertension models. The effect of aging on carotid stiffness was investigated in female recombinant inbred rats (RI-17, $({n}=2)$) in the first experiment. The outcomes of low/high-salt diets were examined in young male Dahl salt-sensitive rats (SS, ${ n}=6$; SM12, ${ n}=6$; SM9, ${ n}=6$) in the second experiment. Results—Good concordance was observed between left and right carotid axial strain measurements with 11.4% relative error, whereas 4.6% relative error occurred between diastolic and systolic axial strain measurements. Old (80 and 85 weeks) RI-17 carotids were determined to be twice as stiff with 5- .70 $pm$ 0.97% $({rm strain}pm{rm std})$ as young carotids (30 and 34 weeks) with 13.26 $pm$ 2.73%, $p< 0.001$. Carotid axial strain measurement also indicated that salt diets had a significant impact on SS $(p=0.008)$ and SM12 $(p< 0.001)$ but not on SM9 $(p=0.881)$ rats. ]]> 29 2 570 578 928 29 2 579 579 3107 29 2 580 580 319 29 2 C3 C3 26