Affiliations: PDPC – Parallel and Distributed Processing Center, Department of Computer Science and Information Engineering, Providence University, Shalu, Taichung 43301, Taiwan E-mail: [email protected] | Laboratory of Bioinformatics and Computational Biology, Department of Computer Science, National Tsing Hua University, Hsinchu 30013, Taiwan E-mail: {cnchen,cytang}@cs.nthu.edu.tw | Division of Allergy, Immunology and Rheumatology, Taichung Veterans General Hospital, Taichung 40705, Taiwan E-mail: {zyh,jllan,dychen}@vghtc.gov.tw | Institute of Medical Technology, National Chung-Hsing University, Taichung 40703, Taiwan | Department of Computer Science and Information Management, Providence University, Shalu, Taichung 43301, Taiwan E-mail: [email protected] | Department of Medicine, National Yang-Ming University, Taipei 112, Taiwan
Abstract: Nailfold capillary microscopy examination has been used since late 1950s as a non-invasive in-vivo technique for diagnosing and monitoring connective tissue disease in adults. Disorders such as Primary Raynaud's phenomenon, progressive systemic sclerosis, and rheumatoid arthritis were detected in more than 80% of adult patients, by analyzing such high resolution images. Internet computing and grid technologies have changed the way we tackle complex scientific problems. Grid computing environments are characterized by interconnecting a number of heterogeneous resources in geographically distributed domains. They enable large-scale aggregation and sharing of computational, data and other resources across institutional boundaries. In this paper, we discuss and develop a framework for nailfold capillary microscope image acquisition and analysis, using computational power provided by grid platforms. In this way, not only useful medical information can be extracted from large amount of history anamneses in an efficient way, with the use of a number of adequate techniques and methods in high performance computing, but also to diagnose abnormal nailfold capillary in far shorter time, to diagnose patient's disease in real-time basis. Based on the results of the classification, analysis of history anamneses are done to discover updated health information possibly hidden in patients' medical records.
