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.

Inflammatory and functional effects of increasing asthma treatment with formoterol or double dose budesonide

Adding a long-acting beta(2)-agonist to inhaled corticosteroids (ICS) for asthma treatment is better than increasing ICS dose in improving clinical status, although there is no consensus about the impact of this regimen on inflammation. In this double-blind, randomized, parallel group study, asthmatics with moderate to severe disease used budesonide (400 mcg/day) for 5 weeks (run-in period); then they were randomized to use budesonide (800 mcg/day - BUD group) or budesonide plus formoterol (400 mcg and 24 mcg/day, respectively - FORMO group) for 9 weeks (treatment period). Home PEF measurements, symptom daily reporting, spirometry, sputum induction (for differential cell counts and sputum cell cultures), and hypertonic saline bronchial challenge test were performed before and after treatments. TNF-alpha, IL-4 and eotaxin-2 levels in the sputum and cell culture supernatants were determined. Morning and night PEF values increased in the FORMO group during the treatment period (p < 0.01), from 435 +/- 162 to 489 +/- 169 and 428 +/- 160 to 496 +/- 173 L/min, respectively. The rate of exacerbations in the FORMO group was lower than in the BUD group (p < 0.05). Neutrophil counts in sputum increased in both groups (p < 0.05) and leukocyte viability after 48 h-culture increased in the FORMO group (p < 0.05). No other parameter changed significantly in either group. This study showed that adding formoterol to budesonide improved home PEF and provided protection from exacerbations, although increase of leukocyte viability in cell culture may be a matter of concern and needs further investigation. (C) 2008 Elsevier Ltd. All rights reserved.