Browsing by Subject "Medical imaging"

Now showing 1 - 20 of 20

Open Access
Advances in nanoparticle‐based medical diagnostic and therapeutic techniques
(John Wiley & Sons, 2016-03-11) Sardan, Melis; Özkan, Alper Devrim; Zengin, Aygül; Tekinay, Ayşe B.; Güler, Mustafa O.; Güler, Mustafa O.; Tekinay, Ayşe B.
Advances in modern medicine have eliminated several major causes of human mortality and considerably extended life expectancies around the world; however, this increase in the global age average has also boosted the incidences of age‐associated disorders. These conditions, such as cancer, neurodegenerative disorders, and cardiovascular disease, severely decrease the quality of life for the affected but are highly polymorphic and often difficult to treat. This chapter describes the characteristics of nanoparticle (NP) contrast agents (CAs) proposed for use in medical imaging, and details the surface modification methods used to designate specific targets for their attachment. It then compares their effectiveness and toxicity compared to conventional methods of contrast enhancement, and discusses the contribution that nanoscience has had, and will have, on medical imaging and disease diagnosis at large.
Open Access
Automated detection and enhancement of microcalcifications in mammograms using nonlinear subband decomposition
(IEEE, 1997) Ansari, R.; Gürcan, M. Nafi; Yardımcı, Yasemin; Çetin, A. Enis
In this paper, computer-aided detection and enhancement of microcalcifications in mammogram images are considered. The mammogram image is first decomposed into subimages using a `subband' decomposition filter bank which uses nonlinear filters. A suitably identified subimage is divided into overlapping square regions in which skewness and kurtosis as measures of the asymmetry and impulsiveness of the distribution are estimated. All regions with high positive skewness and kurtosis are marked as a regions of interest. Next, an outlier labeling method is used to find the locations of microcalcifications in these regions. An enhanced mammogram image is also obtained by emphasizing the microcalcification locations. Linear and nonlinear subband decomposition structures are compared in terms of their effectiveness in finding microcalcificated regions and their computational complexity. Simulation studies based on real mammogram images are presented.
Open Access
A comprehensive methodology for determining the most informative mammographic features
(2013) Wu, Y.; Alagoz O.; Ayvaci, M.U.S.; Munoz Del Rio, A.; Vanness, D.J.; Woods, R.; Burnside, E.S.
This study aims to determine the most informative mammographic features for breast cancer diagnosis using mutual information (MI) analysis. Our Health Insurance Portability and Accountability Act-approved database consists of 44,397 consecutive structured mammography reports for 20,375 patients collected from 2005 to 2008. The reports include demographic risk factors (age, family and personal history of breast cancer, and use of hormone therapy) and mammographic features from the Breast Imaging Reporting and Data System lexicon. We calculated MI using Shannon's entropy measure for each feature with respect to the outcome (benign/malignant using a cancer registry match as reference standard). In order to evaluate the validity of the MI rankings of features, we trained and tested naïve Bayes classifiers on the feature with tenfold cross-validation, and measured the predictive ability using area under the ROC curve (AUC). We used a bootstrapping approach to assess the distributional properties of our estimates, and the DeLong method to compare AUC. Based on MI, we found that mass margins and mass shape were the most informative features for breast cancer diagnosis. Calcification morphology, mass density, and calcification distribution provided predictive information for distinguishing benign and malignant breast findings. Breast composition, associated findings, and special cases provided little information in this task. We also found that the rankings of mammographic features with MI and AUC were generally consistent. MI analysis provides a framework to determine the value of different mammographic features in the pursuit of optimal (i.e., accurate and efficient) breast cancer diagnosis. © 2013 Society for Imaging Informatics in Medicine.
Open Access
Condition number in recovery of signals from partial fractional fourier domain information
(Optical Society of America, 2013-06) Oktem F. S.; Özaktaş, Haldun M.
The problem of estimating unknown signal samples from partial measurements in fractional Fourier domains arises in wave propagation. By using the condition number of the inverse problem as a measure of redundant information, we analyze the effect of the number of known samples and their distributions.
Open Access
Design and implementation of a PC based medical image workstation
(1993-07) Gerek, Ömer Nezih
In this thesis, the implementation of a compact medical image workstation for radiological image processing is described. The workstation is desired to contain sufficient amount of utilities for medical image displaying purposes. Furthermore, it should be affordable for a practicing radiologist. Because of this, the well standardized and cheap PC (Personal computer) mediáis selected for the workstation machine. In order to handle large amount of digital image data, image compression techniques are studied and an implementation of the .Joint Photographic Experts Group (JPEG) standard is used. Furthermore, a class of transform techniques, namely the Block Wavelet Transform (BWT) is experimented for substituting the role of the Discrete Cosine Transform (DCT). The peripheral devices such as a gray tone scanner and high capacity optical discs are then integrated to the computer by the developed software.
Open Access
Electrical impedance tomography of translationally uniform cylindrical objects with general cross-sectional boundaries
(Institute of Electrical and Electronics Engineers, 1990) Ider, Y. Z.; Gencer, N. G.; Atalar, Ergin; Tosun, H.
An algorithm is developed for electrical impedance tomography (EIT) of finite cylinders with general cross-sectional boundaries and translationally uniform conductivity distributions. The electrodes for data collection are assumed to be placed around a cross-sectional plane,- therefore the axial variation of the boundary conditions and also the potential field are expanded in Fourier series. For each Fourier component a two-dimensional (2-D) partial differential equation is derived. Thus the 3-D forward problem is solved as a succession of 2-D problems and it is shown that the Fourier series can be truncated to provide substantial saving in computation time. The finite element method is adopted and the accuracy of the boundary potential differences (gradients) thus calculated is assessed by comparison to results obtained using cylindrical harmonic expansions for circular cylinders. A 1016-element and 541-node mesh is found to be optimal. For a given cross-sectional boundary, the ratios of the gradients calculated for both 2-D and 3-D homogeneous objects are formed. The actual measurements from the 3-D object are multiplied by these ratios and thereafter the tomographic image is obtained by the 2-D iterative equipotential lines method. The algorithm is applied to data collected from phantoms, and the errors incurred from the several assumptions of the method are investigated. The method is also applied to humans and satisfactory images are obtained. It is argued that the method finds an “equivalent” translationally uniform object, the calculated gradients for which are the same as the actual measurements collected. In the absence of any other information about the translational variation of conductance this method is especially suitable for body parts with some translational uniformity. © 1990 IEEE
Open Access
Graph walks for classification of histopathological images
(IEEE, 2013) Olgun, Gülden; Sokmensuer, C.; Gündüz-Demir, Çiğdem
This paper reports a new structural approach for automated classification of histopathological tissue images. It has two main contributions: First, unlike previous structural approaches that use a single graph for representing a tissue image, it proposes to obtain a set of subgraphs through graph walking and use these subgraphs in representing the image. Second, it proposes to characterize subgraphs by directly using distribution of their edges, instead of employing conventional global graph features, and use these characterizations in classification. Our experiments on colon tissue images reveal that the proposed structural approach is effective to obtain high accuracies in tissue image classification. © 2013 IEEE.
Open Access
A hybrid method for 6-DOF tracking of MRI-compatible robotic interventional devices
(2006-05) Krieger, A.; Metzger, G.; Fichtinger, G.; Atalar, Ergin; Whitcomb L. L.
This paper reports a novel hybrid method of tracking the position and orientation of robotic medical instruments within the imaging volume of a magnetic resonance imaging (MRI) system. The method utilizes two complementary measurement techniques: passive MRI fiducial markers and MRI-compatible joint encoding. This paper reports an experimental evaluation of the tracking accuracy of this system. The accuracy of this system compares favorably to that of a previously reported active tracking system. Moreover, the hybrid system is quickly and easily deployed on different MRI scanner systems. © 2006 IEEE.
Open Access
Image reconstruction for Magnetic Particle Imaging using an Augmented Lagrangian Method
(IEEE, 2017) Ilbey S.; Top C.B.; Çukur, Tolga; Sarıtaş, Emine Ülkü; Guven H.E.
Magnetic particle imaging (MPI) is a relatively new imaging modality that images the spatial distribution of superparamagnetic iron oxide nanoparticles administered to the body. In this study, we use a new method based on Alternating Direction Method of Multipliers (a subset of Augmented Lagrangian Methods, ADMM) with total variation and l1 norm minimization, to reconstruct MPI images. We demonstrate this method on data simulated for a field free line MPI system, and compare its performance against the conventional Algebraic Reconstruction Technique. The ADMM improves image quality as indicated by a higher structural similarity, for low signal-to-noise ratio datasets, and it significantly reduces computation time. © 2017 IEEE.
Open Access
Learning-based reconstruction methods for magnetic particle imaging
(2023-01) Güngör, Alper
Magnetic particle imaging (MPI) is a novel modality for imaging of magnetic nanoparticles (MNP) with high resolution, contrast and frame rate. An inverse problem is usually cased for reconstruction, which requires a time-consuming calibration scan for measuring a system matrix (SM). Previous calibration procedures involve scanning an MNP filled sample with a size that matches desired resolution through field of view. This time-consuming calibration scan which accounts for both system and MNP response imperfections is a critical factor prohibiting its practical use. Moreover, the quality of the reconstructed images heavily depend on the prior information about the MNP distribution as well as the specific re-construction algorithm, since the inverse problem is highly ill-posed. Previous approaches commonly solve an optimization problem based on the measurement model that iteratively estimates the image while enforcing data consistency in an interleaved fashion. However, while conventional hand-crated priors do not fully capture the underlying complex features of MPI images, recently proposed learned priors suffer from limited generalization performance. To tackle these issues, we first propose a deep learning based technique for accelerated MPI calibration. The technique utilizes transformers for SM super-resolution (TranSMS) for accelerated calibration of SMs with high signal-to-noise-ratio. For signal-to-noise-ratio efficiency, we propose scanning a low resolution SM with larger MNP sample size. For improved SM estimation, TranSMS leverages the vision trans-former to capture global contextual information while utilizing the convolutional module for local high-resolution features. Finally, a novel data-consistency module enforces measurement fidelity. TranSMS is shown to outperform competing methods significantly in terms of both SM recovery and image reconstruction performance. Next, to improve image reconstruction quality, we propose a novel physics-driven deep equilibrium based technique with learned consistency block for MPI (DEQ-MPI). DEQ-MPI embeds deep network operators into iterative optimization procedures for improved modeling of image statistics. Moreover, DEQ-MPI utilizes learned consistency to better capture the data statistics which helps improve the overall image reconstruction performance. Finally, compared to previous unrolling-based techniques, DEQ-MPI leverages implicit layers which enables training on the converged output. Demonstrations on both simulated and experimental data show that DEQ-MPI significantly improves image quality and reconstruction time over state-of-the-art reconstructions based on hand-crafted or learned priors.
Open Access
Localization of diagnostically relevant regions of interest in whole slide images
(IEEE, 2014-08) Mercan, E.; Aksoy, Selim; Shapiro, L. G.; Weaver, D. L.; Brunye, T.; Elmore, J. G.
Whole slide imaging technology enables pathologists to screen biopsy images and make a diagnosis in a digital form. This creates an opportunity to understand the screening patterns of expert pathologists and extract the patterns that lead to accurate and efficient diagnoses. For this purpose, we are taking the first step to interpret the recorded actions of world-class expert pathologists on a set of digitized breast biopsy images. We propose an algorithm to extract regions of interest from the logs of image screenings using zoom levels, time and the magnitude of panning motion. Using diagnostically relevant regions marked by experts, we use the visual bag-of-words model with texture and color features to describe these regions and train probabilistic classifiers to predict similar regions of interest in new whole slide images. The proposed algorithm gives promising results for detecting diagnostically relevant regions. We hope this attempt to predict the regions that attract pathologists' attention will provide the first step in a more comprehensive study to understand the diagnostic patterns in histopathology.
Open Access
Localization of diagnostically relevant regions of interest in whole slide images: a comparative study
(Springer New York LLC, 2016-08) Mercan, E.; Aksoy, S.; Shapiro, L. G.; Weaver, D. L.; Brunyé, T. T.; Elmore, J. G.
Whole slide digital imaging technology enables researchers to study pathologists’ interpretive behavior as they view digital slides and gain new understanding of the diagnostic medical decision-making process. In this study, we propose a simple yet important analysis to extract diagnostically relevant regions of interest (ROIs) from tracking records using only pathologists’ actions as they viewed biopsy specimens in the whole slide digital imaging format (zooming, panning, and fixating). We use these extracted regions in a visual bag-of-words model based on color and texture features to predict diagnostically relevant ROIs on whole slide images. Using a logistic regression classifier in a cross-validation setting on 240 digital breast biopsy slides and viewport tracking logs of three expert pathologists, we produce probability maps that show 74 % overlap with the actual regions at which pathologists looked. We compare different bag-of-words models by changing dictionary size, visual word definition (patches vs. superpixels), and training data (automatically extracted ROIs vs. manually marked ROIs). This study is a first step in understanding the scanning behaviors of pathologists and the underlying reasons for diagnostic errors. © 2016, Society for Imaging Informatics in Medicine.
Open Access
Motion-compensated prediction based algorithm for medical image sequence compression
(Elsevier BV, 1995-09) Oǧuz, S. H.; Gerek, Ö. N.; Çetin, A. Enis
A method for irreversible compression of medical image sequences is described. The method relies on discrete cosine transform and motion-compensated prediction to reduce intra- and inter-frame redundancies in medical image sequences. Simulation examples are presented.
Open Access
The parallel surrogate constraint approach to the linear feasibility problem
(Springer, 1996) Özaktaş, Hakan; Akgül, Mustafa; Pınar, Mustafa Ç.
The linear feasibility problem arises in several areas of applied mathematics and medical science, in several forms of image reconstruction problems. The surrogate constraint algorithm of Yang and Murty for the linear feasibility problem is implemented and analyzed. The sequential approach considers projections one at a time. In the parallel approach, several projections are made simultaneously and their convex combination is taken to be used at the next iteration. The sequential method is compared with the parallel method for varied numbers of processors. Two improvement schemes for the parallel method are proposed and tested.
Open Access
Preface
(Springer Verlag, 2010) Ünay, Devrim; Çataltepe, Zehra; Aksoy, Selim
This book constitutes the refereed contest reports of the 20th International Conference on Pattern Recognition, ICPR 2010, held in Istanbul, Turkey, in August 2010. The 31 revised full papers presented were carefully reviewed and selected. The papers are organized in topical sections on BiHTR - Bi-modal handwritten Text Recognition, CAMCOM 2010 - Verification of Video Source Camera Competition, CDC - Classifier Domains of Competence, GEPR - Graph Embedding for Pattern Recognition, ImageCLEF@ICPR - Information Fusion Task, ImageCLEF@ICPR - Visual Concept Detection Task, ImageCLEF@ICPR - Robot Vision Task, MOBIO - Mobile Biometry Face and Speaker Verification Evaluation, PR in HIMA - Pattern Recognition in Histopathological Images, SDHA 2010 - Semantic Description of Human Activities.
Open Access
Relaxation-based color magnetic particle imaging for viscosity mapping
(American Institute of Physics, 2019) Utkur, Mustafa; Muslu, Yavuz; Sarıtaş, Emine Ülkü
Magnetic particle imaging (MPI) uses superparamagnetic iron oxide (SPIO) nanoparticles as biomedical imaging tracers. The potential applications of MPI have recently been broadened by the introduction of “color” MPI techniques that can distinguish different nanoparticles and/or environments, e.g., by exploiting the relaxation behavior of SPIOs. One of the important applications of color MPI techniques is viscosity mapping. In this work, we show relaxation-based color MPI experiments that can distinguish the biologically relevant viscosity range of up to 5 mPa s. To find the optimal drive field parameters for viscosity, we compare color MPI results at three different frequencies. We show that frequencies around 10 kHz are well-suited for viscosity mapping using the multicore cluster Nanomag-MIP nanoparticles, providing a one-to-one mapping between the estimated relaxation time constant and viscosity.
Open Access
A synthesis-based approach to compressive multi-contrast magnetic resonance imaging
(IEEE, 2017) Güngör, A.; Kopanoğlu, E.; Çukur, Tolga; Güven, H. E.
In this study, we deal with the problem of image reconstruction from compressive measurements of multi-contrast magnetic resonance imaging (MRI). We propose a synthesis based approach for image reconstruction to better exploit mutual information across contrasts, while retaining individual features of each contrast image. For fast recovery, we propose an augmented Lagrangian based algorithm, using Alternating Direction Method of Multipliers (ADMM). We then compare the proposed algorithm to the state-of-the-art Compressive Sensing-MRI algorithms, and show that the proposed method results in better quality images in shorter computation time.
Open Access
Uniqueness and reconstruction in magnetic resonance-electrical impedance tomography (MR-EIT)
(Institute of Physics Publishing, 2003) İder, Y. Z.; Onart, S.; Lionheart, W. R. B.
Magnetic resonance-electrical impedance tomography (MR-EIT) was first proposed in 1992. Since then various reconstruction algorithms have been suggested and applied. These algorithms use peripheral voltage measurements and internal current density measurements in different combinations. In this study the problem of MR-EIT is treated as a hyperbolic system of first-order partial differential equations, and three numerical methods are proposed for its solution. This approach is not utilized in any of the algorithms proposed earlier. The numerical solution methods are integration along equipotential surfaces (method of characteristics), integration on a Cartesian grid, and inversion of a system matrix derived by a finite difference formulation. It is shown that if some uniqueness conditions are satisfied, then using at least two injected current patterns, resistivity can be reconstructed apart from a multiplicative constant. This constant can then be identified using a single voltage measurement. The methods proposed are direct, non-iterative, and valid and feasible for 3D reconstructions. They can also be used to easily obtain slice and field-of-view images from a 3D object. 2D simulations are made to illustrate the performance of the algorithms.
Open Access
Unsupervised tissue image segmentation through object-oriented texture
(IEEE, 2010) Tosun, Akif Burak; Sokmensuer, C.; Gündüz-Demir, Çiğdem
This paper presents a new algorithm for the unsupervised segmentation of tissue images. It relies on using the spatial information of cytological tissue components. As opposed to the previous study, it does not only use this information in defining its homogeneity measures, but it also uses it in its region growing process. This algorithm has been implemented and tested. Its visual and quantitative results are compared with the previous study. The results show that the proposed segmentation algorithm is more robust in giving better accuracies with less number of segmented regions. © 2010 IEEE.
Open Access
VLSI circuits for adaptive digital beamforming in ultrasound imaging
(IEEE, 1993) Karaman, M.; Atalar, Abdullah; Köymen, Hayrettin
For phased-array ultrasound imaging, alternative beamforming techniques and their VLSI circuits are studied to form a fully digital receive front-end hardware. In order to increase the timing accuracy in beamforming, a computationally efficient interpolation scheme to increase the sampling rate is examined. For adaptive beamforming, a phase aberration correction method with very low computational complexity is described. Image quality performance of the method is examined by processing the non-aberrated and aberrated phased-array experimental data sets of an ultrasound resolution phantom. A digital beamforming scheme based on receive focusing at the raster focal points is examined. The sector images of the resolution phantom, reconstructed from the phased-array experimental data by beamforming at the radial and raster focal points, are presented for comparison of the image resolution performances of the two beamforming schemes. VLSI circuits and their implementations for the proposed techniques are presented.