In this paper, a method that combines image analysis techniques, such as segmentation and registration, is proposed for an advanced and progressive evaluation of thermograms. The method is applied for the prevention of muscle injury in high-performance athletes, in collaboration with a Brazilian professional soccer club. The goal is to produce information on spatio-temporal variations of thermograms favoring the investigation of the athletes’ conditions along the competition. The proposed method improves on current practice by providing a means for automatically detecting adaptive body-shaped regions of interest, instead of the manual selection of simple shapes. Specifically, our approach combines the optimization features in Otsu’s method with a correction factor and post-processing techniques, enhancing thermal-image segmentation when compared to other methods. Additional contributions resulting from the combination of the segmentation and registration steps of our approach are the progressive analyses of thermograms in a unique spatial coordinate system and the accurate extraction of measurements and isotherms.

Chronic periodontitis is a multifactorial inflammatory disease that affects supporting structures of the teeth. Although the gingival response is largely described, little is known about the immune changes in the alveolar bone and neighboring tissues that could indicate periodontal disease (PD) activity. Then, in this study we identified the ongoing inflammatory changes and novel biomarkers for periodontitis in the tissues directly affected by the destructive disease in PD patients. Samples were collected by osteotomy in 17 control subjects during extraction of third molars and 18 patients with advanced PD, in which alveoloplasty was necessary after extraction of teeth with previous extensive periodontal damage. Patients presented mononuclear cells infiltration in the connective tissue next to the bone and higher fibrosis area, along with increased accumulation of IL‐17⁺ and TRAP⁺ cells. The levels of TNF‐α and MMP‐2 mRNA were also elevated compared to controls and a positive and significant correlation was observed between TNF‐α and MMP‐2 mRNA expression, considering all samples evaluated. In conclusion, nongingival tissues neighboring large periodontal pockets present inflammatory markers that could predict ongoing bone resorption and disease spreading. Therefore, we suggested that the detailed evaluation of these regions could be of great importance to the assessment of disease progression.

This work presents a multi-dimensional similarity modeling strategy and relevance feedback technique for minimizing the semantic gap intrinsic problem of CBIR systems by allowing users to customize their queries according to their requirements and preferences. We propose a composite strategy using a multi-dimensional, vectorial, spatially clustered, and relevance-ordered approach. Given a set of k features which represents the images in an image database, the similarity measure between a query image and another from the image collection is analyzed in k components, and the images are ranked on a A dimensional space according to their projections over the axis x_n, where n = 1,2,... k. System experimentation was executed thoroughly using a test image database containing up to 12,000 pictures. The experimental results have shown that the presented approach can substantially improve the outcome in image retrieval systems.

In this work a variational model is proposed for simultaneous smoothing and multiphase image segmentation. By assuming that the pixel intensities are independent samples from a mixture of Gaussians, and by interpreting the phase fields as probabilities of pixels belonging to a certain phase, the model formulation is obtained by maximizing the mutual information between image features and phase fields. The proposed energy functional J_e consists of three parts: the smoothing term for the reconstructed image, the regularization for the boundaries in hard segmentation, and a likelihood estimator based on the density function. The segmentation and image denoising are performed simultaneously through the flow equation obtained by minimizing the energy functional with respect to the mixture of Gaussian coefficients and variance. Some experimental results on segmenting synthetic and natural color images are presented to illustrate the effectiveness of the proposed model.

In this paper the authors present a novel variational method for the reconstruction of images corrupted by non-uniformly distributed noise. The additive noise model has been studied extensively, using variational techniques such as the Rudin, Osher and Fatemi model. However, the reconstruction of images corrupted by non-Gaussian noise has not yet been thoroughly studied. The proposed model includes a balance between the data term and the regularization term in the energy functional, taking into account the statistical control of the parameters and the position of the noisy points related to the edges presented in the image. The parameters are determined by the given observed noisy image. The obtained results have shown the effectiveness and robustness in restoring images with multiplicative noise or mixed Gaussian noise, while preserving edges and small structures belonging to the image.