By Topic

Medical Image Analysis and Clinical Applications (MIACA), 2010 International Conference on

Date 10-13 June 2010

Filter Results

Displaying Results 1 - 25 of 42
  • [Front cover]

    Publication Year: 2010 , Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (271 KB)  
    Freely Available from IEEE
  • [Title page]

    Publication Year: 2010 , Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (271 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2010 , Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (221 KB)  
    Freely Available from IEEE
  • Conference organization

    Publication Year: 2010 , Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (134 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2010 , Page(s): 1 - 3
    Save to Project icon | Request Permissions | PDF file iconPDF (342 KB)  
    Freely Available from IEEE
  • Improving low-dose X-ray CT images by Weighted Intensity Averaging over Large-scale Neighborhoods

    Publication Year: 2010 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (803 KB) |  | HTML iconHTML  

    How to reduce the radiation dose delivered to the patients is always an important concern since the introduction of computed tomography (CT). With respect to patients' care, the least possible radiation dose is demanded. Though clinically desired, low-dose CT (LDCT) images tend to be severely degraded by quantum noise and artifacts under low dose scan protocols. This paper proposes to improve the LDCT images by Weighted Intensity Averaging over Large-scale Neighborhoods (WIA-LN). In the implementation of the proposed WIA-LN method, the processed pixel intensities are from a selective weighted intensity averaging of the pixels belonging to different organs or attenuation tissues within large-scale neighborhoods. Effective suppression of noise and artifacts in LDCT images without obvious loss of fine anatomic features are realized. In experiment, CT images of different doses from a Siemens CT with 16 detector rows are used. Results validate an excellent performance of the proposed approach in improving clinical LDCT images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Medical image segmentation on the basic of a variational level set

    Publication Year: 2010 , Page(s): 5 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (620 KB) |  | HTML iconHTML  

    In this paper, on the basis of techniques of curve evolution, we propose a novel variational level set model for segmentation of intensity inhomogeneity images. The model is integrated with some advantages of fitting statistical model and region-based active contour model to the intensity in each of a set of regions. Furthermore, the experimental results show the validity of this model for various image modalities. All of these results may be useful in the study of the image segmentation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method to judge the pupil position and measure the eye rotational angle

    Publication Year: 2010 , Page(s): 9 - 11
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (419 KB) |  | HTML iconHTML  

    Traditional ENG technology got the recording from the eye movement displacement parameters through contacting with skin indirectly. Modern nystagmus gets the eye movement image through video camera, then calculates the eye movement displacement parameters. Difficulties of this technology in so big noise image environment are how to judge the accurate location of the pupil and how to measure the eye rotational angle. In this paper, we use the template matching method to solve how to judge the accurate positioning pupil in case of large noise image environment, followed by the use of mutual information in image registration to solve the problem of measuration of the eye rotational angle. We test these two methods in the simulated test images, and the results are content. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Medical image blind denoising using context bilateral filter

    Publication Year: 2010 , Page(s): 12 - 17
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1915 KB) |  | HTML iconHTML  

    Edge and detail preserving is a very important requirement in blind medical denoising since the details can help doctors diagnosis diseases. Bilateral filter (BF) is a famous filter in preserving details while smoothing. However, its performance in image denoising is unsatisfied. The main reason for this situation is that the bilateral filter uses gray levels of pixels directly, which causes the propagation of noise (PoN). In this paper, we propose a method, named context bilateral filter (CBF), which conditions the bilateral filter on the context. That is, the range filter is not defined on the gray levels directly while it is defined on the context! Since context can be defined as a smoother version for the image, the PoN can be suppressed greatly. In order to demonstrate the good performance for our method, experimental results using real medical images are given. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of X-ray in-line phase-contrast imaging in the study of small hepatic tumors

    Publication Year: 2010 , Page(s): 18 - 21
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (650 KB) |  | HTML iconHTML  

    Background: The spatial resolution of conventional imaging examinations is mostly millimeter level, which is difficult to implement the imaging of small hepatic tumors, thus the best time for treatment is bungled. The synchrotron radiation X-ray in-line phase-contrast imaging (IL-PCI) uses the phase information carried by X-rays after passing through the objects to image, and the spatial resolution is up to micron level. Methods: In this paper, the matrix scan imaging for the hepatic tumors model of nude mice is implemented by synchrotron radiation in-line phase-contrast imaging. Then we use image stitching technology to achieve a complete liver phase image. Two tumors with the diameter of less than 1mm are observed from the image. Conclusion: The small hepatic tumors imaging can be achieved by in-line phase-contrast imaging, which is conducive to the early diagnosis of hepatic tumors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Investigate intracranial EEG with conditional granger causality and PCA

    Publication Year: 2010 , Page(s): 22 - 25
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (450 KB) |  | HTML iconHTML  

    It's an important basic work to locate the propagation pathways of seizure, as it could bring a crucial effect to guide the clinical practice. This article develops a method for computing effective connectivity on intracranial electroencephalographic (IEEG) data, based on multivariate autoregressive model. We use Principal Component Analysis (PCA) technique on the condition variate sets while calculate the conditional Granger causality (cGC), in order to overcome the redundancy on the condition variate sets. We confirm the proposed approach is robust and feasible application on the simulation data which the condition variates are redundant for executing cGC analysis. The applicability and usefulness of this technique are illustrated using intracranial EEG data from one patient with epilepsy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reduced functinal connetivity between mediodorsal thalamic nucleus and anterior cingulated cortex in absence epilepsy

    Publication Year: 2010 , Page(s): 26 - 29
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB) |  | HTML iconHTML  

    Thalamus and its interaction with cerebral cortex are considered essential in the generation and propagation of spike and wave discharge (SWD). Our objective is to evaluate the spontaneous functional connectivity between the thalamus and cerebral cortex in absence epilepsy. We use the resting-state fMRI to determine the whole brain functional connectivity with the mediodorsal thalamic nucleus (MDTN) in 14 healthy controls and 12 absence epilepsy patients within interictal duration without epileptic discharge. Cross-correlation functional connectivity analysis reveals significant functional connectivities between MDTN and bilateral basal ganglia, insula, orbital frontal cortex, medial prefrontal cortex, anterior cingulated cortex (ACC), hippocampus, and midbrain in controls. Functional connectivity between thalamus and ACC is significantly lower in patients when compared with controls. Our finding, avoided IED effects, may reflect a permanent abnormality between thalamus and ACC in absence epilepsy patients. The abnormality may be considered as a substrate of seizure generation in absence epilepsy. The finding of this pilot study might contribute to the further investigation of the epileptogenic networks of generalized epilepsy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hemodynamic response function in temporal lobe epilepsy with interictal regional slow wave: An EEG-fMRI study

    Publication Year: 2010 , Page(s): 30 - 33
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (482 KB) |  | HTML iconHTML  

    The hemodynamic response function (HRF) describes the dynamic process of the blood oxygen level dependent (BOLD) signal evoked by a very short stimulus of unit intensity. Understanding HRF is a key issue for exploring the underlying dynamics of nervous system activation. Some researches suggested that the shape of HRF varied with different brain regions and different subjects, even at different time point in the same brain region of a subject. In this work, epilepsy discharges were adopted as markers of short stimuli, and then we use EEG-fMRI method to investigate HRF in temporal lobe epilepsy with interictal regional slow wave. Five patients with idiopathic temporal lobe epilepsy were enrolled in this study, the peak delay and amplitude of the estimated HRF was compared with Gamma, Glover and the SPM canonical HRF, and the results show that the delay of the estimated HRF is different from either one of the three theoretical model, thus further study on both theoretical model and real data estimation is needed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Medical image segmentation based on level set with new local fitting energy

    Publication Year: 2010 , Page(s): 34 - 37
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (596 KB) |  | HTML iconHTML  

    In this paper, we define the fitting energy by a new kernel function, which is to do in the range of an image what traditional filters do a small neighborhood of the same location. We combine the advantages of the LBF model and our model by taking domain and range kernel functions into account. The new level set method with domain and range kernel functions has been tested and assessed on different modalities of medical images. Experiments prove our simulation results demonstrate that our model has better segmentation results compared with the LBF model. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Abnormality detection on gastroscopic images using patches assembled by local weights

    Publication Year: 2010 , Page(s): 38 - 41
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (503 KB) |  | HTML iconHTML  

    Gastroscopy is important tool for the clinical examination of gastric diseases, and the abnormality detection on the gastroscopic images will help physicians to diagnose. An improved patches assembled by local weights is presented in this paper. First, a series of classifiers on image patches with different sizes have been analyzed to find the suitable size. The boosted stumps are employed as the image patch classifiers. At last, considering the relationship between the neighboring image patches, the patches assemble method based on the local information is applied to enhance the coherence of patches. The experiment results show that the assemble method the local weights get the true positive rate (TP) at 75.7%, the true negative rate (TN) at 86.4% and the mean error at 16.7%. Comparing with the other assemble methods like mean filter, local weights has better performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An interactive method for computing tooth-root orientation from 3D CT image

    Publication Year: 2010 , Page(s): 42 - 45
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (659 KB) |  | HTML iconHTML  

    In tooth implantation surgery, dentist or surgeon needs to derive quantitative information about the place each implant should be go, the length and width of each implant should be, as well as the angle each implant should be inserted, based on the 3D CT image of jaw of a patient. In existing techniques, the information is measured from such slices that are generated from virtually cutting teeth-ridge along the direction perpendicular to teeth-ridge. However, according to the clinical experience and anatomical knowledge, usually the largest length of each implant should be measured on such slice that is generated by cutting teeth-ridge along the tooth root direction. Besides, for each defect tooth, the most suitable angle or orientation to insert an implant is the tooth root orientation. Thus, in surgical planning of dental implant, it is much important to compute or estimate tooth root orientation from 3D CT image of jaw. To our knowledge, this problem is seldom studied in existing literature. In this paper, we try to discuss this problem. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image registration using the shift-insensitive discrete wavelet transform

    Publication Year: 2010 , Page(s): 46 - 49
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (785 KB) |  | HTML iconHTML  

    DWT (discrete wavelet transforms) has become an attractive tool in image registration, however, it is shift- sensitive, which is mainly caused by the aliasing term in downsampling process. Some modified schemes of DWT, such as DTCWT (dual-tree complex wavelet transform), always lead to high computational complexity in registration process because of redundancy. In this paper, a new scheme of discrete wavelet transform is proposed to approximately eliminate the aliasing term while the wavelet representation remains redundancy-free, by which the shift sensitivity of wavelet representations of original signal ca be reduced efficiently. The registration results of two medical images illustrate the superiority of the proposed wavelet decomposition scheme. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel graph cuts based liver segmentation method

    Publication Year: 2010 , Page(s): 50 - 53
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (632 KB) |  | HTML iconHTML  

    This paper presents a novel liver segmentation method based on the fast marching and graph cuts methods. The algorithm is composed of three main steps: first, rough edge of the liver is extracted from the CT image by fast marching method. Second, hard constrain of the foreground and background which is used for initial calculation of graph cut is obtained by mathematical morphology method. Third, based on the former calculation, the graph cuts are utilized to refine the segmentation boundary of the liver. The developed method greatly reduces the complexity of the commonly used graph cuts methods, which can obtain the hard constrains automatically. Also, the developed method reduces the dependence of empirical parameters of the fast marching based method. Experimental results show that the developed method is very effective for the segmentation of liver from CT images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification of imagery movement tasks for brain-computer interfaces based on energy

    Publication Year: 2010 , Page(s): 54 - 57
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (529 KB) |  | HTML iconHTML  

    In order to extract the feature of electroencephalogram (EEG) quickly and efficiently, to improve the classification accuracy rate, band-pass filter and wavelet package were used to get mu and beta rhythms. In the time domain, energy feature was formed by the squared-amplitude of electroencephalogram (EEG) samples over the trials. The subtracted energy value of lead C3 and C4 was averaged by each trial. The polarity (positive or negative) of subtracted value for each trial indicates the kind of imagery movement and was used to classify. The method is simple and the classification accuracy rate is up to 87.857%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fluid non-rigid registration combining SIFT and shape information for prostate treatment

    Publication Year: 2010 , Page(s): 58 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (611 KB) |  | HTML iconHTML  

    In image registration based on fluid model for prostate treatment, the body force that drives the deformation of the template images with only the term of intensity information may have problems in matching structure in prostate images. This paper introduces the fluid non-rigid registration combining SIFT and shape information and quantificational analysis the performance in prostate images to determine the corresponding parameters. Experiments on both synthetic and clinical images show the feasibility of improving the accuracy of prostate image registration, and the correlation coefficient (CC) value for the new method has been increased form 0.75 to 0.80. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tissue characterization: Influence of ultrasound setting on texture features in vivo

    Publication Year: 2010 , Page(s): 63 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (483 KB) |  | HTML iconHTML  

    In diagnostic ultrasound, the echo graphic B-scan texture is an important area of investigation since it can be analyzed to characterize the histological state of internal tissues. An important factor requiring consideration when evaluating ultrasonic tissue texture is the ultrasound setting parameters. The aim of this study is to investigate the effect of varying the gain and the dynamic range setting on the texture features in-vivo using a 3D ultrasound probe. The left leg medial head of the gastrocnemius muscle of 5 healthy subjects were scanned. A region of interest was defined on each slice. Texture features including first order statistics, second order statistics, autoregressive model and wavelet transform parameters were extracted from the images. One-way ANOVA was used to test the significant difference between the varying settings. Varying gain setting yielded a large variation on the first order statistics (CV ranging from 41.18% for skewness to 86% for kurtosis) and less variation on second order statistics, autoregressive model and wavelet (CV ranging from 1.34% for autoregressive model to 35.03% for gradient). Most of texture features did not show a significant difference when considering the gain varying form 75 dB to 85 dB except gray level, variance and run length. Varying the dynamic range from 70dB to 90 dB yielded a small variation on all texture features (CV less 7%) indicating that changing the dynamic range has no significant affect on texture features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Liver CT image retrieval based on non-tensor product wavelet

    Publication Year: 2010 , Page(s): 67 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1044 KB) |  | HTML iconHTML  

    This paper presents a content-based medical image retrieval (CBIR) method that used in medical CT images of liver lesions with a computer-assisted diagnosis. According to medical CT images characteristics of blurred boundaries and the unconspicuous region, the liver region of interest is extracted by using semi-automatic method. We extract local co-occurrence matrix texture features and intensity features, and use improved non-tensor product wavelet filter to extract the image global features. Experimental results show that this method can improve the detection rate of lesions. It obtains good results in hepatic hemangioma and HCC which are difficult differential diagnosis both of rich blood supply to tumors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image segmentation based on mutual information

    Publication Year: 2010 , Page(s): 71 - 74
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (812 KB) |  | HTML iconHTML  

    In the paper, Otsu's algorithm is combined with mutual information (MI) technique. The initial threshold can be chosen using Otsu algorithm, and in the iteration process, an optimal threshold will be determined by maximizing the MI between the original volume and the thresholded volume. We evaluate the effectiveness of the proposed approach by applying it to the medical images (MR, microphotographic) and license plate images. The experimental results indicate that the proposed method has not only visually better or comparable segmentation effect but also, more favorably, removal ability for noise. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid elastic registration using constrained free-form deformation

    Publication Year: 2010 , Page(s): 75 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1657 KB) |  | HTML iconHTML  

    In this paper we present a deformation registration technique that utilizes rigid registration for bony structures while allowing elastic transformation of soft tissue to more accurately register the entire image volume. The technique is applied to the registration of computed tomography images of the thoracic and abdominal regions. First, bony structures are segmented from the CT data. The landmarks are automatically obtained from the segmented data using boundary-detection techniques and random sampling from the boundary candidates. Each bone structure is then individually registered to the corresponding structure using Least Square Method. The whole transformation is obtained by using Thin Plate Spline interpolation. The resulting set of rigid transformations allows for accurate registration of the parts of the CT data representing the vertebrate but not the adjacent soft tissue. To align the soft tissue, a smoothly varying deformation to model different deformability for some structures is computed by means of B-Spline Free Form Deformations algorithm and a normalized mutual information image similarity measure. The advantage of these approaches is that they take into account rigid structures and the deformations applied to the images are continuous and smooth. We applied the proposed methodology to the clinical images. The results have been very positively evaluated by four medical experts. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of cortical thickness in patients with posttraumatic stress disorder due to mining disaster

    Publication Year: 2010 , Page(s): 79 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (552 KB) |  | HTML iconHTML  

    MRI studies in post-traumatic stress disorder (PTSD) have focused primarily on manually-based hippocampal volumetry. However, the variation in cortical thickness and the relationship between the cortical volume and thickness alteration has not been well investigated in PTSD. In this paper, Laplacian method was first utilized to estimate cortical thickness after automatic segmentation of grey matter from MR images. Then the thickness maps were analyzed by SPM5, as well as volumetric analysis. Comparison between 15 survivors of mining disaster with PTSD and 10 survivors without PTSD, from the same accident, indicates that in the superior frontal gyrus and cuneus, the cortical thickness of survivors with PTSD is significantly larger than those without PTSD. However, local reduction in cortical volume is observed in hippocampus, which suggests indirect relationship between the two kinds of structural alterations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.