Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

Obstacle Crossing With Dual Tasking Is A Danger For Individuals With Alzheimer's Disease And For Healthy Older People.

The aim of this study was to analyze the effects of dual tasking on obstacle crossing during walking by individuals with Alzheimer's disease (AD) and by healthy older people. Thirty four elderly individuals (16 healthy subjects and 18 individuals with AD) were recruited to participate in this study. Three AD individuals and one control participant were excluded due to exclusion criteria. The participants were instructed to walk barefoot at their own speed along an 8 m long pathway. Each participant performed five trials for each condition (unobstructed walking, unobstructed walking with dual tasking, and obstacle crossing during walking with dual tasking). The trials were completely randomized for each participant. The mid-pathway stride was measured in the unobstructed walking trials and the stride that occurred during the obstacle avoidance was measured in the trials that involved obstacle crossing. The behavior of the healthy elderly subjects and individuals with AD was similar for obstacle crossing during walking with dual tasking. Both groups used the posture first strategy to prioritize stability and showed decreased attention to executive tasking while walking. Additionally, AD had a strong influence on the modifications that are made by the elderly while walking under different walking conditions.

Whey And Soy Protein Supplements Changes Body Composition In Patients With Crohn's Disease Undergoing Azathioprine And Anti-tnf-alpha Therapy.

Crohn´s disease (CD) is a chronic transmural inflammation of the gastrointestinal tract of unknown cause. Malnutrition associated with active CD has been reduced although obesity has increased. Dietary strategies such as those with high-protein have been proposed to reduce body fat. This study compares the effects of two supplements on the nutritional status of CD patients. 68 CD patients were randomized in two groups: whey protein group (WP) and soy protein group (SP). Using bioimpedance analysis, anthropometry and albumin and pre-albumin dosages the nutritional status was measured before starting the intervention and after 8 and 16 weeks. The disease activity was determined by Crohn's Disease Activity Index and serum C-reactive protein dosage and dietary intake by 24h dietary recalls. Forty-one patients concluded the study and both supplements changed body composition similarly. Triceps skin fold thickness (p< 0.001) and body fat percentage (p=0.001) decreased, whereas mid-arm muscle circumference (p=0.004), corrected arm muscle area (p=0.005) and body lean percentage (p=0.001) increased. For Crohn's disease patients undergoing anti TNF-alpha and azatioprine therapies, supplementation with whey and soy proteins changes body composition through reduction of body fat and thus contributes to control inflammation.

Refletindo sobre o caso celobar®

By mid 2003, the Brazilian people accompanied astonished, in the press, the news about the death of more than 20 persons due to ingestion of a pharmaceutical product containing a suspension of barium sulfate (Celobar®) commonly used as a radiological contrast. Analysis of the product indicated the presence of barium carbonate (about 13% weight/weight) which reacts easily with the hydrochloric acid in the stomach liberating barium ions, a severe poison. In this article, we briefly discuss the possible economic, personal and technical causes that led to this disaster.

Sensores ópticos com detecção no infravermelho próximo e médio

Optical chemical sensors with detection in the near and mid infrared region are reviewed. Fundamental concepts of infrared spectroscopy and optical chemical sensors are briefly described, before presenting some aspects on optical chemical sensors, such as synthesis of NIR and IR reagents, preparation of new materials as well as application in determinations of species of biological, industrial and environmental importance.

Experimento didático de quimiometria para análise exploratória de óleos vegetais comestíveis por espectroscopia no infravermelho médio e análise de componentes principais: um tutorial, parte I

This manuscript aims to show the basic concepts and practical application of Principal Component Analysis (PCA) as a tutorial, using Matlab or Octave computing environment for beginners, undergraduate and graduate students. As a practical example it is shown the exploratory analysis of edible vegetable oils by mid infrared spectroscopy.

Avaliação de técnicas de classificação digital de imagens landsat em diferentes padrões de cobertura da terra em Rondônia

Remotely sensed imagery has been widely used for land use/cover classification thanks to the periodic data acquisition and the widespread use of digital image processing systems offering a wide range of classification algorithms. The aim of this work was to evaluate some of the most commonly used supervised and unsupervised classification algorithms under different landscape patterns found in Rondônia, including (1) areas of mid-size farms, (2) fish-bone settlements and (3) a gradient of forest and Cerrado (Brazilian savannah). Comparison with a reference map based on the kappa statistics resulted in good to superior indicators (best results - K-means: k=0.68; k=0.77; k=0.64 and MaxVer: k=0.71; k=0.89; k=0.70 respectively for three areas mentioned). Results show that choosing a specific algorithm requires to take into account both its capacity to discriminate among various spectral signatures under different landscape patterns as well as a cost/benefit analysis considering the different steps performed by the operator performing a land cover/use map. it is suggested that a more systematic assessment of several options of implementation of a specific project is needed prior to beginning a land use/cover mapping job.

Flora arbórea da bacia do rio Tibagi (Paraná, Brasil): Celastrales sensu Cronquist

A study of the tree species of the order Celastrales sensu Cronquist from the Tibagi river basin, Paraná state, Brazil, is presented, based on herbarium material. This basin is subdivided into three zones, from north to south: lower Tibagi (BT), mid Tibagi (MT) and upper Tibagi (AT), each with different environmental conditions and vegetation types. The order Celastrales is represented in the basin by 15 tree species belonging to three families: Aquifoliaceae, Celastraceae and Icacinaceae. Icacinaceae has only two species, Citronella gongonha and C. paniculata. The former is distinguished by a glabrous ovary and leaves that usually bear thorns. Aquifoliaceae has six species: Ilex brasiliensis, I. brevicuspis, I. chamaedryfolia, I. dumosa, I. paraguariensis and I. theezans. These species are found mainly in AT and MT and are distinguished by leaf size, indument, apices and margins, and by sepal features. Celastrales is represented by seven species and two genera; Plenckia populnea, a Brazilian savannah species found only in MT, and six species of Maytenus (M. evonymoides, M. robusta, M. dasyclada, M. salicifolia, M. ilicifolia and M. aquifolia) distinguished by leaf size and margins, branch shape and number of flowers per inflorescence.

Fatores de stress em jogadores de futebol profissional

Universidade Estadual de Campinas . Faculdade de Educação Física