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.

GP5+/6+ SYBR Green methodology for simultaneous screening and quantification of human papillomavirus

Background: Detection and quantification of human papillomavirus (HPV) may help in predicting the evolution of HPV infection and progression of associated lesions. Objectives: We propose a novel protocol using consensus primers GP5+/6+ in a SYBR Green quantitative real-time (Q-RT) polymerase chain reaction (PCR). The strategy permits screening for HPV infection and viral load quantification simultaneously. Study design: DNA from 153 archived cervical samples, previously tested for HPV detection by GP5+/6+ PCR and typed by EIA-RLB (enzyme immunoassay-reverse line blot) or sequence analysis, was analysed using SYBR Green Q-RT PCR. Melting temperature assay (T(m)) and cycle threshold (C(t)) were used to evaluate HPV positivity and viral load. The T(m) in the range of 77-82 degrees C was considered to be positive for HPV-DNA. HPV results generated through GP5+/6+ conventional PCR were considered the gold standard against which sensitivity and specificity of our assay were measured. Results: Out of 104 HPV positive samples, 100 (96.2%) were also determined as positive by SYBR Green Q-RT PCR; of the 49 HPV-negative samples, all were determined as negative. There was an excellent positivity agreement (K = 0.94) between the SYBR Green Q-RT and the previous methods employed. The specificity and sensitivity were 100% and 96.2%, respectively. Comparison of SYBR Green Q-RT and TaqMan oligo-probe technologies gave an excellent concordance (pc = 0.95) which validated the proposed strategy. Conclusions: We propose a sensitive and easy-to-perform technique for HPV screening and viral load quantification simultaneously. (C) 2009 Elsevier B.V. All rights reserved.

Domestic objects and the taste epiphany - A resource for consumption methodology

The presentation of an aesthetic identity involves the accomplishment of a coherent, plausible narrative which links one's choices to desired characteristics of the self. As symbolic evidence of a person's taste, material culture is a vital component of a successful narrative. Via case studies of pivotal household objects, this paper uses face-to-face interview data as a way of investigating processes of aesthetic choice. Household objects are interpreted as material elements imbricated in the presentation of a socially plausible and internally consistent aesthetic self. Narrative analysis, and the concept of the epiphany-object, are proposed as useful ways of accounting for tastes in domestic material culture. Methodological questions of truth-telling and authenticity in the face-to-face context are considered, and the sociological problem of taste is scrutinized in light of ideas about social accountability and textual identity.