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.

Enhanced concentrations of relevant markers of nitric oxide formation after exercise training in patients with metabolic syndrome

Metabolic syndrome (MetS) denotes a clustering of risk factors that may affect nitric oxide (NO) bioavailability and predispose to cardiovascular diseases, which are delayed by exercise training. However, no previous study has examined how MetS affects markers of NO formation, and whether exercise training increases NO formation in MetS patients. Here, we tested these two hypotheses. We studied 48 sedentary individuals: 20 healthy controls and 28 MetS patients. Eighteen MetS patients were subjected to a 3-month exercise training (E+group), while the remaining 10 MetS patients remained sedentary (E-group). The plasma concentrations of nitrite, cGMP, and ADMA (asymmetrical dimethylarginine: an endogenous nitric oxide synthase inhibitor), and the whole blood nitrite concentrations were determined at baseline and after exercise training using an ozone-based chemiluminescence assay, and commercial enzyme immunoassays. Thiobarbituric acid reactive species (TBA-RS) were measured in the plasma to assess oxidative stress using a fluorometric method. We found that, compared with healthy subjects, patients with MetS have lower concentrations of markers of NO formation, including whole blood nitrite, plasma nitrite, and plasma cGMP, and increased oxidative stress (all P < 0.05). Exercise training increased the concentrations of whole blood nitrite and cGMP, and decreased both oxidative stress and the circulating concentrations of ADMA (both P < 0.05). These findings show clinical evidence for lower endogenous NO formation in patients with MetS, and for improvements in NO formation associated with exercise training in MetS patients. (C) 2008 Elsevier Inc. All rights reserved.

Dimensional Accuracy of Computer-Aided Design/Computer-Assisted Manufactured Orbital Prostheses

Purpose: The aim of this research was to assess the dimensional accuracy of orbital prostheses based on reversed images generated by computer-aided design/computer-assisted manufacturing (CAD/CAM) using computed tomography (CT) scans. Materials and Methods: CT scans of the faces of 15 adults, men and women older than 25 years of age not bearing any congenital or acquired craniofacial defects, were processed using CAD software to produce 30 reversed three-dimensional models of the orbital region. These models were then processed using the CAM system by means of selective laser sintering to generate surface prototypes of the volunteers` orbital regions. Two moulage impressions of the faces of each volunteer were taken to manufacture 15 pairs of casts. Orbital defects were created on the right or left side of each cast. The surface prototypes were adapted to the casts and then flasked to fabricate silicone prostheses. The establishment of anthropometric landmarks on the orbital region and facial midline allowed for the data collection of 31 linear measurements, used to assess the dimensional accuracy of the orbital prostheses and their location on the face. Results: The comparative analyses of the linear measurements taken from the orbital prostheses and the opposite sides that originated the surface prototypes demonstrated that the orbital prostheses presented similar vertical, transversal, and oblique dimensions, as well as similar depth. There was no transverse or oblique displacement of the prostheses. Conclusion: From a clinical perspective, the small differences observed after analyzing all 31 linear measurements did not indicate facial asymmetry. The dimensional accuracy of the orbital prostheses suggested that the CAD/CAM system assessed herein may be applicable for clinical purposes. Int J Prosthodont 2010;23:271-276.