By Topic

BioMedical Engineering and Informatics, 2008. BMEI 2008. International Conference on

Date 27-30 May 2008

Go

Filter Results

Displaying Results 1 - 25 of 192
  • [Front cover - Vol 2]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (646 KB)  
    Freely Available from IEEE
  • [Title page i - Volume 2]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (36 KB)  
    Freely Available from IEEE
  • [Title page iii - Volume 2]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (66 KB)  
    Freely Available from IEEE
  • [Copyright notice - Volume 2]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (58 KB)  
    Freely Available from IEEE
  • Table of contents - Volume 2

    Page(s): v - xvi
    Save to Project icon | Request Permissions | PDF file iconPDF (149 KB)  
    Freely Available from IEEE
  • Preface - Volume 2

    Page(s): xvii
    Save to Project icon | Request Permissions | PDF file iconPDF (71 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • Organizing Committee - Volume 2

    Page(s): xviii
    Save to Project icon | Request Permissions | PDF file iconPDF (73 KB)  
    Freely Available from IEEE
  • Program Committee - Volume 2

    Page(s): xix - xx
    Save to Project icon | Request Permissions | PDF file iconPDF (57 KB)  
    Freely Available from IEEE
  • list-reviewer

    Page(s): xxi - xxii
    Save to Project icon | Request Permissions | PDF file iconPDF (56 KB)  
    Freely Available from IEEE
  • An Algorithm Based on Girth-location for MR Head Image Segmentation

    Page(s): 3 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (686 KB) |  | HTML iconHTML  

    In this paper, a segmentation algorithm for MR Head image has been proposed based on Girth-Location information. In the new algorithm, the brain structure is segmented by counting the girth of boundary for connective areas with location information. Then the algorithm of region growing has been used to separate the white matter (WM) from gray matter (GM). Experimental results indicated that this new approach has made full usage of the location information and boundary information of MR images. Compared with other algorithms, the new algorithm is characterized by faster, robustness and accurateness. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis on Gender of Silkworms by MRI Technology

    Page(s): 8 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (375 KB) |  | HTML iconHTML  

    At present silkworm cocoons, dried, boiled and reeled, are the female and male mix, so it's very difficult to produce high grade raw silk in large quantity. In the progress of the silk reeling what we can do to separate the complex of female and male silkworms still encounters presently certain difficulties. In this paper the intrinsic relaxation time of the free water and the bound water in silkworms was analyzed and the relaxation model of silkworm was established by use of the proportion difference of the free water and the bound water in the silk gland tissue of the midriff. Finally the gender of the silkworm has been distinguished exactly without destruction by the T2 weighted imaging of magnetic resonance imaging (MRI) technology in the experiment designed. The result of experiment has enormous instruction significance to the production of the silkworm cocoon mixed at the present time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Segmentation of Micro-calcification Based on SIFT in Mammograms

    Page(s): 13 - 17
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (550 KB) |  | HTML iconHTML  

    Manual segmentation of micro-calcifications in mammogram can provide clinicians with useful information, such as an estimation of the quantification and the size of abnormalities. However, it is a time and labour consuming process. Automatic segmentation has the potential to assist both in the diagnosis of the disease and in treatment planning. This paper presents a novel mammogram image segmentation algorithm that makes use of Scale Invariant Feature Transform (SIFT) to compute the key point in the suspicious area of the mammograms. A database from MI AS is used in this approach. Initial results are presented to show that SIFT can be used to by computing the key-points to segment micro-calcifications of the mammograms. Further work will focus on finding the ways to set the threshold of the segmentation automatically. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Segmentation of Nasopharyngeal Carcinoma from CT Images

    Page(s): 18 - 22
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (663 KB) |  | HTML iconHTML  

    This paper presents an automatic segmentation technique for identifying nasopharyngeal carcinoma regions in CT images. The proposed technique is based on the region growing method by which an initial seed is automatically generated. A probabilistic map representing a chance of being the tumor pixel in each CT image will be created and used for initial seed determination. This map is generated from three probabilistic functions established upon location of the tumor considered, intensities of the tumor pixels, and asymmetry of organs respectively. A representative of potential tumor pixels will be selected as an initial seed. The experimental results showed that seeds were correctly determined with the percent accuracy of 84.32%. These seeds were grown in preprocessed CT images for identifying the nasopharyngeal carcinoma regions subsequently. The results showed that, for no metastasis cases, perfect match and corresponding ratio were 85.03% and 52.44% respectively and 29.26% and 28.03% correspondingly for metastasis cases. This resulted from a single seed generated in each CT image. It was unable to identify more than one tumor region. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Thresholding of Micro-CT Trabecular Bone Images

    Page(s): 23 - 27
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (531 KB) |  | HTML iconHTML  

    This paper considers the problem associated with the segmentation of trabecular bone image obtained from micro-computed tomography (microCT). The morphometric indices of a 3D bone image, which are associated with the trabecular bone strength, may play an important clinical role in early predictions of osteoporosis onset and in longitudinal studies of different medical treatments for osteoporosis. Correct estimation of morphologic parameters requires accurate segmentation of bone images. In the present approach, a connectivity-preserving threshold algorithm, connectivity stable thresholding (CST), is introduced. The algorithm is based on the coupling of topological parameter Conn.D and geometric parameter structure model index (SMI) to select an optimal threshold. The experimental results indicate that CST gives good results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Breast Tumor Identification in Ultrasound Images Using the Normalized Cuts with Partial Grouping Constraints

    Page(s): 28 - 32
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (515 KB) |  | HTML iconHTML  

    Breast cancer is one of the leading causes of death in women. Early detection and treatment plays an important role in decreasing the mortality rate. Ultrasound is increasingly been used as an adjunct to mammography to detect breast tumors. An accurate and reliable tool to assist physicians in making diagnosis and treatment decisions is essential and necessary. We propose the use of the normalized cuts (Shi, 2000) with partial grouping constraints (Yu and Shi, 2004) to segment breast tumors in cropped ultrasonic images. The experimental results indicated that the proposed approach was robust in identifying over 500 breast tumors in a wide variety of cancer types. We found that more than 90% of segmented tumors satisfied the clinical demand. We are developing it as an assistant tool to facilitate physicians in identifying breast tumors in ultrasonic images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitive Approach to Medical Pattern Recognition, Structure Modelling and Image Understanding

    Page(s): 33 - 37
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (576 KB) |  | HTML iconHTML  

    This paper presents some possibilities of applying mathematical linguistic formalisms, in the form of structural pattern recognition, in the development of a new class of intelligent medical diagnosis-support and image recognition systems - cognitive vision systems. Such methods are aimed at facilitating the semantic analysis of the meaning of some selected medical patterns based on the presence of cognitive resonance. When trying to apply this cognitive resonance to the automatic analysis and interpretation of image-type data, we propose a new class of information systems: UBIAS (understanding based image analysis systems). The procedures proposed are based on the cognitive resonance and categorization model. The application presented in this paper will show how great the opportunities are for automatically detecting lesions in the analysed structures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Color and Position versus Texture Features for Endoscopic Polyp Detection

    Page(s): 38 - 42
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1157 KB) |  | HTML iconHTML  

    This paper presents a comparison of texture based and color and position based methods for polyp detection in endoscopic video images. Two methods for texture feature extraction that presented good results in previous studies were implemented and their performance is compared against a simple combination of color and position features. Although this more simple approach produces a much higher number of features than the other approaches, a SVM with a KBF kernel is able to deal with this high dimensional input space and it turns out that it outperforms the previous approaches on the experiments performed in a database of 4620 images from endoscopic video. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combination of Local Invariants with an Active Shape Model

    Page(s): 43 - 47
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (728 KB) |  | HTML iconHTML  

    In this paper, a novel local invariant model based on scale invariant feature transform (SIFT) features is presented to accurately obtain and locate the local features of an image. After the local features of each image in the training set are extracted by the SIFT, we eliminate the unsteady factors in term of statistical results of all the SIFT features to establish the local invariant model. The experiments to evaluate the performance of the model are carried out, which prove that the method has the quality of high-repeatability and accuracy and achieves the power of accurately locating the similar objects in different scenes despite the rigid or non-rigid deformation on them. For further investigation, we combine the local invariant model with an active shape model for automatically initialization. Results show that the combined model achieves satisfactory performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison between Voxel-based Morphometry and Volumetric Analysis in Schizophrenia

    Page(s): 48 - 52
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB) |  | HTML iconHTML  

    This study compares the voxel-based morphometry (VBM) and region-of-interest (ROI)-based volumetric analysis in schizophrenia. Magnetic resonance imaging (MRI) data of 50 unmedicated schizophrenia patients and 82 healthy controls were examined. ROI- based volumetric analysis was performed by tracing caudates on anterior commissure and posterior commissure (ACPC)-positioned MRI. The comparison of 20 subjects in the lower and upper 25% for traced caudate size and the comparison between patients and controls revealed significantly reduced gray matter concentration in the caudate through VBM. Caudate volume (absolute and relative) revealed that patients with schizophrenia had smaller caudate nuclei than controls. The ROC results demonstrated that the performance of VBM (area under the curve (AUC): 61%) was similar to that of ROI-based volumetric analysis (AUC: 61% for relative ROI volume) and their correlation was 0.51 (p<0.05). These results suggest that to be an alternative to ROI-based volumetry in schizophrenia, cautious interpretation of VBM may be needed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparisons between Circle and Structural Models in Lung Ventilation Reconstruction by Electrical Impedance Tomography

    Page(s): 53 - 57
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (944 KB) |  | HTML iconHTML  

    In this paper, a set of electrical impedance tomography (EIT) system, EIT_TJU II system is presented. A physical model regarding the prior information of human thorax has been illustrated, and the sensitivities distribution comparing with the circle model is analyzed. By numerical analyzing the uniformity and the nonlinearity of the structural model are improved. The lung ventilation experiments are undertaken on the different models. The visualization results of lung ventilation indicate that EIT incorporating prior information is a promising technique which has the potential to be applied in future clinical diagnoses and monitoring. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computerized Segmentation and Classification of Breast Lesions Using Perfusion Volume Fractions in Dynamic Contrast-enhanced MRI

    Page(s): 58 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB) |  | HTML iconHTML  

    This study is designed to segment suspicious regions using automatic computerized procedures and to classify kinetic patterns using commercially available three-time-points (3TP) method of computer- aided diagnosis. A novel evaluation method using perfusion volume fractions is introduced for examining meaningful kinetic features in differentiation of benign and malignant breast lesions. Dynamic contrast- enhanced MRI was applied to 24 lesions (12 malignant, 12 benign). Thresholding for suspicious regions, region growing segmentation, hole-filling and 3D morphological erosion and dilation were performed for extracting final lesion volume. The lesion sphericity and center distance of mass to surface area ratio (CDMSAR) were considered in the process of automatic segmentation. The kinetic patterns for each lesion were classified into six classes by the 3TP method. Perfusion volume fraction for each class was calculated in three partitions of whole, rim and core volumes of a lesion. Receiver operating characteristic curve (ROC) analysis was performed using the perfusion volume fractions. When using perfusion volume fractions divided into rim and core lesion volume, the classes having more improved accuracy appeared than using perfusion volume fractions within whole lesion volume. This result indicates that lesion classification using local perfusion volume fractions is helpful in selecting meaningful kinetic patterns for differentiation of benign and malignant lesions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conductivity Reconstruction of Brain Edema Based on Improved Adaptive Genetic Algorithm

    Page(s): 63 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (294 KB) |  | HTML iconHTML  

    In order to estimate the progression or regression of edema at the bedside continuously, based the theoretic model, an improved Adaptive Genetic Algorithm(AGA) has been applied in optimization of conductivity reconstruction. Dynamic crossover and mutation operators, which are based on Maiming Distance, are brought forward in this paper to maintain generation's diversity. As a contrast, the Simple GA(SGA) has also been applied in same optimization of brain edema. It is shown the AGA not only has satisfied efficiency but also has enhanced the capability to converge to the best answer. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CT Image Processing and Medical Rapid Prototyping

    Page(s): 67 - 71
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (534 KB) |  | HTML iconHTML  

    In this paper, the three-dimensional (3D) models of body structures from computed tomography (CT) image are reconstructed in SolidWorks by using planar contour method and medical rapid prototyping (MRP) models are performed. This paper reports how to transfer CT image into digital binary matrixes; then, to capture section contour points from medical image per slice, to create B-spline curve with the control points in each layer, to produce 3D solid model construction in SoildWorks environment; finally, to build medical rapid prototyping models by Z corporation printer. This effort is the first to develop image processing 3D visualization in SolidWorks. MRP data from 3D models are created simultaneously. The system performance is tested using truth CT image, and MRP example models of teeth and knee joint were manufactured. The results reveal that the accuracy of 3D reconstruction is acceptable. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feasibility of Imaging Photoplethysmography

    Page(s): 72 - 75
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (391 KB) |  | HTML iconHTML  

    Contact and spot measurement have limited the application of photoplethysmography (PPG), thus an imaging PPG system comprising a digital CMOS camera and three wavelength light-emitting diodes (LEDs) is developed to detect the blood perfusion in tissue. With the means of the imaging PPG system, the ideally contactless monitoring with larger field of view and the different depth of tissue by applying multi- wavelength illumination can be achieved to understand the blood perfusion change. Corresponding to the individual wavelength LED illumination, the PPG signals can be derived in the both transmission and reflection modes, respectively. The outcome explicitly reveals the imaging PPG is able to detect blood perfusion in a illuminated tissue and indicates the vascular distribution and the blood cell response to individual wavelength LED. The functionality investigation leads to the engineering model for 3-D visualized blood perfusion of tissue and the development of imaging PPG tomography. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fluorescent Optical Imaging of Small Animals Using Filtered Back-projection 3D Surface Reconstruction Method

    Page(s): 76 - 80
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2325 KB) |  | HTML iconHTML  

    The CCD-based non-contact fluorescent optical imaging has got a promising progress in recent years. This imaging modality needs the 3D surface of the small animal, which is used for the forward model and inverse reconstruction. We propose a new 3D surface reconstruction method based on the back projection method using white/black images. After taking the surface images by CCD, the transverse reconstruction is completed using filter back-projection method. Based on the data of the edges and calibration operation, we reconstruct the 3D surface of the animals. To validate the accuracy of the optical method, we compared the external shape data of mouse phantom to that from the micro-CT system. Some in vivo fluorescence imaging results are also presented in this paper. View full abstract»

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