Home About us Contact
|
Home About us Contact | ||
|
|
||
Image Database (image + database)
Selected AbstractsParallel heterogeneous CBIR system for efficient hyperspectral image retrieval using spectral mixture analysisCONCURRENCY AND COMPUTATION: PRACTICE & EXPERIENCE, Issue 9 2010Antonio J. Plaza Abstract The purpose of content-based image retrieval (CBIR) is to retrieve, from real data stored in a database, information that is relevant to a query. In remote sensing applications, the wealth of spectral information provided by latest-generation (hyperspectral) instruments has quickly introduced the need for parallel CBIR systems able to effectively retrieve features of interest from ever-growing data archives. To address this need, this paper develops a new parallel CBIR system that has been specifically designed to be run on heterogeneous networks of computers (HNOCs). These platforms have soon become a standard computing architecture in remote sensing missions due to the distributed nature of data repositories. The proposed heterogeneous system first extracts an image feature vector able to characterize image content with sub-pixel precision using spectral mixture analysis concepts, and then uses the obtained feature as a search reference. The system is validated using a complex hyperspectral image database, and implemented on several networks of workstations and a Beowulf cluster at NASA's Goddard Space Flight Center. Our experimental results indicate that the proposed parallel system can efficiently retrieve hyperspectral images from complex image databases by efficiently adapting to the underlying parallel platform on which it is run, regardless of the heterogeneity in the compute nodes and communication links that form such parallel platform. Copyright © 2009 John Wiley & Sons, Ltd. [source] Large-scale screening of intracellular protein localization in living fission yeast cells by the use of a GFP-fusion genomic DNA libraryGENES TO CELLS, Issue 3 2000Da-Qiao Ding Background Intracellular localization is an important part of the characterization of a gene product. In an attempt to search for genes based on the intracellular localization of their products, we constructed a green fluorescent protein (GFP)-fusion genomic DNA library of S. pombe. Results We constructed the S. pombe GFP-fusion genomic DNA library by fusing, in all three reading frames, random fragments of genomic DNA to the 5, end of the GFP gene in such a way that expression of potential GFP-fusion proteins would be under the control of the own promoters contained in the genomic DNA fragments. Fission yeast cells were transformed with this plasmid library, and microscopic screening of 49 845 transformants yielded 6954 transformants which exhibited GFP fluorescence, of which 728 transformants showed fluorescence localized to distinct intracellular structures such as the nucleus, the nuclear membrane, and cytoskeletal structures. Plasmids were isolated from 516 of these transformants, and a determination of their DNA sequences identified 250 independent genes. The intracellular localizations of the 250 GFP-fusion constructs was categorized as an image database; using this database, DNA sequences can be searched for based on the localizations of their products. Conclusions A number of new intracellular structural components were found in this library. The library of GFP-fusion constructs also provides useful fluorescent markers for various intracellular structures and cellular activities, which can be readily used for microscopic observation in living cells. [source] Computer-aided diagnosis system for the detection of bronchiectasis in chest computed tomography imagesINTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, Issue 4 2009D. Shiloah Elizabeth Abstract A computer-aided diagnosis (CAD) system has been developed for the detection of bronchiectasis from computed tomography (CT) images of chest. A set of CT images of the chest with known diagnosis were collected and these images were first denoised using Wiener filter. The lung tissue was then segmented using optimal thresholding. The Pathology Bearing Regions (PBRs) were then extracted by applying pixel-based segmentation. For each PBR, a gray level co-occurrence matrix (GLCM) was constructed. From the GLCM texture features were extracted and feature vectors were constructed. A probabilistic neural network (PNN) was constructed and trained using this set of feature vectors. The images together with the PBRs and the corresponding feature vector and diagnosis were stored in an image database. Rules for diagnosis and for determining the severity of the disease were generated by analyzing the images known to be affected by bronchiectasis. The rules were then validated by a human expert. The validated rules were stored in the Knowledge Base. When a physician gives a CT image to the CAD system, it first transforms the image into a set of feature vectors, one for each PBR in the image. It then performs the diagnosis using two techniques: PNN and mahalanobis distance measure. The final diagnosis and the severity of the disease are determined by correlating the diagnosis determined by both the techniques in consultation with the knowledge base. The system also retrieves similar cases from the database. Thus, this system would aid the physicians in diagnosing bronchiectasis. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 290,298, 2009 [source] Does compression affect image retrieval performance?INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, Issue 2-3 2008Gerald Schaefer Abstract Image retrieval and image compression are both fields of intensive research. As lossy image compression degrades the visual quality of images and hence changes the actual pixel values of an image, low level image retrieval descriptors which are based on statistical properties of pixel values will change, too. In this article we investigate how image compression affects the performance of low-level colour descriptors. Several image retrieval algorithms are evaluated on a speciated image database compressed at different image quality levels. Extensive experiments reveal that while distribution-based colour descriptors are fairly stable with respect to image compression a drop in retrieval performance can nevertheless be observed for JPEG compressed images. On the other hand, after application of JPEG2000 compression only a negligible performance drop is observed even at high compression ratios. © 2008 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 18, 101,112, 2008 [source] Financial Impact of Emergency Department UltrasoundACADEMIC EMERGENCY MEDICINE, Issue 7 2009Olanrewaju A. Soremekun MD Abstract Objectives:, There is limited information on the financial implications of an emergency department ultrasound (ED US) program. The authors sought to perform a fiscal analysis of an integrated ED US program. Methods:, A retrospective review of billing data was performed for fiscal year (FY) 2007 for an urban academic ED with an ED US program. The ED had an annual census of 80,000 visits and 1,101 ED trauma activations. The ED is a core teaching site for a 4-year emergency medicine (EM) residency, has 35 faculty members, and has 24-hour availability of all radiology services including formal US. ED US is utilized as part of evaluation of all trauma activations and for ED procedures. As actual billing charges and reimbursement rates are institution-specific and proprietary information, relative value units (RVUs) and reimbursement based on the Centers for Medicare & Medicaid Services (CMS) 2007 fee schedule (adjusted for fixed diagnosis-related group [DRG] payments and bad debt) was used to determine revenue generated from ED US. To estimate potential volume, assumptions were made on improvement in documentation rate for diagnostic scans (current documentation rates based on billed volume versus diagnostic studies in diagnostic image database), with no improvements assumed for procedural ED US. Expenses consist of three components,capital costs, training costs, and ongoing operational costs,and were determined by institutional experience. Training costs were considered sunken expenses by this institution and were thus not included in the original return on investment (ROI) calculation, although for this article a second ROI calculation was done with training cost estimates included. For the purposes of analysis, certain key assumptions were made. We utilized a collection rate of 45% and hospitalization rates (used to adjust for fixed DRG payments) of 33% for all diagnostic scans, 100% for vascular access, and 10% for needle placement. An optimal documentation rate of 95% was used to estimate potential revenue. Results:, In FY 2007, 486 limited echo exams of abdomen (current procedural terminology [CPT] 76705) and 480 limited echo cardiac exams were performed (CPT 93308) while there were 78 exams for US-guided vascular access (CPT 76937) and 36 US-guided needle placements when performing paracentesis, thoracentesis, or location of abscess for drainage (CPT 76492). Applying the 2007 CMS fee schedule and above assumptions, the revenue generated was 578 RVUs and $35,541 ($12,934 in professional physician fees and $22,607 in facility fees). Assuming optimal documentation rates for diagnostic ED US scans, ED US could have generated 1,487 RVUs and $94,593 ($33,953 in professional physician fees and $60,640 in facility fees). Program expenses include an initial capital expense (estimated at $120,000 for two US machines) and ongoing operational costs ($68,640 per year to cover image quality assurance review, continuing education, and program maintenance). Based on current revenue, there would be an annual operating loss, and thus an ROI cannot be calculated. However, if potential revenue is achieved, the annual operating income will be $22,846 per year with an ROI of 4.9 years to break even with initial investment. Conclusions:, Determining an ROI is a required procedure for any business plan for establishing an ED US program. Our analysis demonstrates that an ED US program that captures charges for trauma and procedural US and achieves the potential billing volume breaks even in less than 5 years, at which point it would generate a positive margin. [source] Instrument-, age- and site-dependent variations of dermoscopic patterns of congenital melanocytic naevi: a multicentre studyBRITISH JOURNAL OF DERMATOLOGY, Issue 1 2006S. Seidenari Summary Background, Recently, we identified and described dermoscopic aspects, present with a higher frequency in congenital melanocytic lesions with respect to acquired naevi. We also classified small- and medium-sized congenital naevi (CN) into nine subtypes according to their macroscopic and dermoscopic aspects. Objectives, Because the recognition of dermoscopic features may be instrument dependent, in this study, we wanted to check whether dermoscopic patterns specific for CN can be identified in digital images acquired by means of different instruments. We also wanted to check the validity of our previously proposed classification and assess possible age- and site-dependent variations of dermoscopic patterns and naevus subtypes. Patients/methods, Images corresponding to 384 small- or medium-sized CN were collected in eight different centres employing four different instruments. Lesion images were evaluated and checked for the presence of specific dermoscopic criteria, classified, and compared with a database of 350 acquired naevi. Results, Specific and unspecific dermoscopic features were identifiable in images acquired by means of all four instrument types. The mean number of identified features per lesion did not vary according to the instrument employed for the acquisition of the images; however, it was lower for lesions recorded employing low magnifications. The previously proposed classification was easily applied to the whole image database. The variegated naevus type was identified as a highly specific clinical/dermoscopic pattern. Dermoscopic features varied according to age and location. The globular type prevailed in subjects under 11 years of age and on the trunk, whereas the majority of reticular lesions were located on the limbs. Conclusions, Because definite clinical and histological criteria for the diagnosis of the congenital nature of naevi are lacking, the use of dermoscopy can be of great help in identifying those lesions where the presence of specific dermoscopic features makes the diagnosis of CN more likely. Moreover, dermoscopy can be useful both for the classification of lesions already identified as congenital according to definite clinical and anamnestic data and for a possible correlation of naevus phenotype and dermoscopic patterns to the risk of developing a malignant melanoma in prospective studies. [source] | ||||||||||