Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems. (C) 2009 Elsevier B.V. All rights reserved.

Evaluation of Adult Chronic Chagas` Heart Disease Diagnosis by Molecular and Serological Methods

Chagas` disease caused by Trypanosoma cruzi is endemic in Latin America. T. cruzi presents heterogeneous populations and comprises two main genetic lineages, named T. cruzi I and T. cruzi II. Diagnosis in the chronic phase is based on conventional serological tests, including indirect immunofluorescence (IIF) and enzyme-linked immunosorbent assay (ELISA), and diagnosis in the acute phase based on parasitological methods, including hemoculture. The objective of this study was to evaluate the diagnostic procedures of Chagas` disease in adult patients in the chronic phase by using a PCR assay and conventional serological tests, including TESA-blot as the gold standard. Samples were obtained from 240 clinical chronic chagasic patients. The sensitivities, compared to that of TESA-blot, were 70% for PCR using the kinetoplast region, 75% for PCR using the nuclear repetitive region, 99% for IIF, and 95% for ELISA. According to the serological tests results, we recommend that researchers assess the reliability and sensitivity of the commercial kit Chagatest ELISA recombinant, version 3.0 (Chagatest Rec v3.0; Wiener Lab, Rosario, Argentina), due to the lack of sensitivity. Based on our analysis, we concluded that PCR cannot be validated as a conventional diagnostic technique for Chagas` disease. These data have been corroborated by low levels of concordance with serology test results. It is recommended that PCR be used only for alternative diagnostic support. Using the nuclear repetitive region of T. cruzi, PCR could also be applicable for monitoring patients receiving etiologic treatment.

Evaluation of an Enzyme-Linked Immunosorbent Assay Based on Araraquara Virus Recombinant Nucleocapsid Protein

Laboratory diagnosis of hantavirus cardiopulmonary syndrome (HCPS) in Brazil has been performed mostly by a detection of IgM antibodies to recombinant antigen purified from Sin Nombre virus and Andes Virus (ANDV). Recently, a recombinant nucleocapsid (rN) protein of Argentina virus (ARAV), a Brazilian hantavirus, was Obtained in Escherichia coli. To evaluate ARAV rN as antigen for antibody detection, serum samples from 30 patients front Argentina seropositive for hantavirus were tested. All samples were positive for IgG and IgM by enzyme-linked immunosorbent assay (ELISA) using either ARAV rN or ANDV rN antigens. In Brazil, six of 00 serum samples from patients With suspected HCPS (10%) were positive for IgM by ELISA Using ARAV rN antigen and 7 were positive Using ANDV rN antigen. For results obtained with 90 serum samples analyzed by IgM ELISA with ANDV rN antigen, the sensitivity of the IgM ELISA using ARAV rN antigen was 97.2%,, the specificity was 100%, the positive predictive value was 100% and the negative predictive value was 98.1%. The results show that ARAV rN is a Suitable antigen for diagnosis Of hantavirus infection in Brazil and Argentina.

An association rule-based method to support medical image diagnosis with efficiency

In this paper, we propose a method based on association rule-mining to enhance the diagnosis of medical images (mammograms). It combines low-level features automatically extracted from images and high-level knowledge from specialists to search for patterns. Our method analyzes medical images and automatically generates suggestions of diagnoses employing mining of association rules. The suggestions of diagnosis are used to accelerate the image analysis performed by specialists as well as to provide them an alternative to work on. The proposed method uses two new algorithms, PreSAGe and HiCARe. The PreSAGe algorithm combines, in a single step, feature selection and discretization, and reduces the mining complexity. Experiments performed on PreSAGe show that this algorithm is highly suitable to perform feature selection and discretization in medical images. HiCARe is a new associative classifier. The HiCARe algorithm has an important property that makes it unique: it assigns multiple keywords per image to suggest a diagnosis with high values of accuracy. Our method was applied to real datasets, and the results show high sensitivity (up to 95%) and accuracy (up to 92%), allowing us to claim that the use of association rules is a powerful means to assist in the diagnosing task.

Role of Microparticles in the Hemostatic Dysfunction in Acute Promyelocytic Leukemia

Serious bleeding and thrombotic complications are frequent in acute promyelocytic leukemia (APL) and are major causes of morbidity and mortality. Microparticles (MP) have been used to study the risk and pathogenesis of thrombosis in many malignant disorders. To date, from published articles, this approach had not been applied to APL. In this article, the hemostatic dysfunction in this disorder is briefly reviewed. A study design to address this problem using MP is described. MP bearing tissue factor, profibrinolytic factors (tissue plasminogen activator and annexin A2), and the antifibrinolytic factor plasminogen activator inhibitor type 1 were measured using flow cytometry. The cellular origin of the MP was identified by specific cell surface markers. Comparison of the various populations of MP was made between samples collected at the time of diagnosis with those collected at molecular remission. Preliminary data suggest that this approach is feasible.

Clinical Evaluation of the NS1 Antigen-Capture ELISA for Early Diagnosis of Dengue Virus Infection in Brazil

The fact that the diagnosis of infection with dengue virus is usually made by detecting IgM antibodies during the convalescent phase of the disease interferes with disease management and, consequently, with reducing mortality rates. This study evaluated the sensitivity and specificity of detection of NS1 in samples of patients suspected of acute dengue virus infection in Brazil. The results were used to institute treatment and the sensitivity and specificity of detection of NS1 were compared to the results of detection of IgM, virus isolation, and RT-PCR. Detection of NS1 yielded better results than RTPCR and virus isolation. When considering IgM detection and RT-PCR positive results as ""gold standards,"" the sensitivity and specificity of the NS1 assay were 95.9% and 81.1%, respectively. All patients enrolled in the study were treated promptly and had an uneventful course of the disease. The detection of NS1 provided better results than the diagnostic techniques used currently during the acute phase of disease (RT-PCR and virus isolation). Detection of NS1 is an important tool for the diagnosis of acute dengue infection, particularly in highly endemic areas, allowing for rapid treatment of patients and reduction of disease burden. J. Med. Virol. 82: 1400-1405, 2010. (C) 2010 Wiley-Liss, Inc.

The application of adaptive partitioned random search in feature selection problem

Feature selection is one of important and frequently used techniques in data preprocessing. It can improve the efficiency and the effectiveness of data mining by reducing the dimensions of feature space and removing the irrelevant and redundant information. Feature selection can be viewed as a global optimization problem of finding a minimum set of M relevant features that describes the dataset as well as the original N attributes. In this paper, we apply the adaptive partitioned random search strategy into our feature selection algorithm. Under this search strategy, the partition structure and evaluation function is proposed for feature selection problem. This algorithm ensures the global optimal solution in theory and avoids complete randomness in search direction. The good property of our algorithm is shown through the theoretical analysis.