CLARE-XR: explainable regression-based classification of chest radiographs with label embeddings.

An automatic system for pathology classification in chest X-ray scans needs more than predictive performance, since providing explanations is deemed essential for fostering end-user trust, improving decision-making, and regulatory compliance. CLARE-XR is a novel methodology that, when presented with an X-ray image, identifies the associated pathologies and provides explanations based on the presentation of similar cases. The diagnosis is achieved using a regression model that maps an image into a 2D latent space containing the reference coordinates of all findings.

Distribution-based detection of radiographic changes in pneumonia patterns: A COVID-19 case study.

Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns.

Practices developed by nurses in primary health care in southern Brazil.

Objective: To understand the practices developed by nurses in primary care in southern Brazil.

Method: Qualitative study, with data collection via online interviews, conducted between October 2020 and May 2021, and recorded. 174 nurses from 24 municipalities in southern Brazil participated.

Social participation in Anvisa's regulations: hybrid, colloquial, and scientific evidence for democratic decision-making.

Anvisa's public consultation (PC) is the most widely used social participation mechanism in current health regulations, which was based on antagonistic movements: the democratization of decision-making and State counter-reformation. Starting from the concept of social participation, defined as various actions from society related to public decision-making, which values diversity and the exercise of citizenship, the present article discusses the possibility of PCs configuring a democratic regulation process by considering popular beliefs and colloquial evidence, and promoting the creation of hybrid evidence in an evidence-moderated model. Despite the different interests, the PCs open the door to opportunities for democratic deliberation by society in the search of understanding, where it is expected that the State will make the best decision and justify it.

Human versus Artificial Intelligence: Validation of a Deep Learning Model for Retinal Layer and Fluid Segmentation in Optical Coherence Tomography Images from Patients with Age-Related Macular Degeneration.

Artificial intelligence (AI) models have received considerable attention in recent years for their ability to identify optical coherence tomography (OCT) biomarkers with clinical diagnostic potential and predict disease progression. This study aims to externally validate a deep learning (DL) algorithm by comparing its segmentation of retinal layers and fluid with a gold-standard method for manually adjusting the automatic segmentation of the Heidelberg Spectralis HRA + OCT software Version 6.16.

Chemical composition and antimicrobial activity of Cordiera myrciifolia leaves against pathogenic bacteria and fungi: Drug potentiation ability and inhibition of virulence.

Cordiera myrciifolia is an abundant species in Northeast Brazil that presents metabolites of biological/therapeutic interest. From this perspective, the present study aimed to investigate the chemical constituents and evaluate the in vitro antimicrobial activity of hexane (HECM) and ethanolic (EECM) extracts of C. myrciifolia leaves.

Deposition of collagen III and alterations in basement membrane integrity as candidate prognostic markers in prostate cancer.

The extracellular matrix surrounding the tumor undergoes changes in its organization during the metastasis process. The present study aims to quantify total collagen, collagen I (Col I) and collagen III (Col III), analyze the alignment of collagen fibers and assess the basement membrane integrity in samples from patients with metastatic and non-metastatic prostate cancer. Tissue samples from 60 patients were classified into groups based on prognostic parameters: better prognosis (n = 20), worse prognosis without metastasis (n = 23) and metastatic (n = 17).

Automated image label extraction from radiology reports - A review.

Machine Learning models need large amounts of annotated data for training. In the field of medical imaging, labeled data is especially difficult to obtain because the annotations have to be performed by qualified physicians. Natural Language Processing (NLP) tools can be applied to radiology reports to extract labels for medical images automatically.

Neuroimaging characterization of multiple sclerosis lesions in pediatric patients: an exploratory radiomics approach.

Introduction: Multiple sclerosis (MS), a chronic inflammatory immune-mediated disease of the central nervous system (CNS), is a common condition in young adults, but it can also affect children. The aim of this study was to construct radiomic models of lesions based on magnetic resonance imaging (MRI, T2-weighted-Fluid-Attenuated Inversion Recovery), to understand the correlation between extracted radiomic features, brain and lesion volumetry, demographic, clinical and laboratorial data.

Methods: The neuroimaging data extracted from eleven scans of pediatric MS patients were analyzed.

Neural leprosy investigation using electroneuromyography and the ML Flow rapid test: a case report.

Neural leprosy, which is characterized by nerve involvement without visible skin lesions, presents a diagnostic challenge. This case report examined the significance of diverse diagnostic modalities in the identification of pure neural leprosy. A 28-year-old patient with symptoms of edema, pain, paresthesia, and diminished sensitivity in the lower limbs underwent various tests.

Responding to STI epidemics among young people: a characterization of the language employed in educational materials.

This article aims to characterize the language employed in educational and communications materials about STIs, HIV/AIDS and viral hepatitis produced by the Ministry of Health between 2010 and 2019, identifying elements related to health promotion and disease prevention. We conducted an exploratory descriptive study. The materials were selected by performing a systematic search of the Ministry of Health website focusing on the period 2010-2019.

STERN: Attention-driven Spatial Transformer Network for abnormality detection in chest X-ray images.

Chest X-ray scans are frequently requested to detect the presence of abnormalities, due to their low-cost and non-invasive nature. The interpretation of these images can be automated to prioritize more urgent exams through deep learning models, but the presence of image artifacts, e.g.

Evaluation of the effects of COVID-19 on semen parameters and male infertility.

The new coronavirus pandemic resulted in millions of deaths in Brazil and around the world, and presented substantial challenges to society. The shortand long-term clinical manifestations tied to COVID-19 are still poorly understood, and may involve several organs and systems, including the male genital tract, which may lead to impaired fertility. The present study aimed to analyze, through an integrative literature review of articles available in databases, the effects of COVID-19 on parameters related to human semen quality.

Allelic variants and immunostaining profile in CXCL12/CXCR4 axis: An investigation of association with prognosis in prostate cancer.

Prostate cancer (PCa) is the malignant neoplasm that most commonly affects men and is an important cause of death. It can be detected by changes in serum levels of Prostate Specific Antigen (PSA) and digital rectal examination, but often symptoms do not appear until advanced stages and metastases. The C-X-C Motif Chemokine Ligand 12/C-X-C Motif Chemokine Receptor 4 (CXCL12/CXCR4) axis acts in cell migration and may be involved in the metastatic process.

Evaluation of primary health care by users during the COVID-19 pandemic: A cross-sectional study.

Objective: To evaluate the primary health care (PHC) attributes and associated factors during the COVID-19 pandemic using the perspective of users.

Methods: This cross-sectional, quantitative study included 422 PHC users from 96 Family Health Teams in a city in Brazil. The assessment used the Primary Care Assessment Tool (PCATool) and a structured questionnaire on the sociodemographic and epidemiological characteristics of users and basic health units (BHU).

Weighted capitation incentive (Previne Brasil Program): impacts on the evolution of the population register in PHC.

In Brazil, consistent advances occurred towards universal coverage after the creation of the Family Health Program (FHP), the main strategy for expanding first contact access and changing the care model in Brazil, strengthened from the creation of The Primary Care Floor (PAB), with resources exclusively for Primary Care, transferred to the municipalities on a regular and automatic basis. The registration of the population is one of the fundamentals of work in the Family Health Strategy (ESF), aiming to know the families enrolled in the teams. The institution of the Previne Brasil Program in November 2019 established a new funding model for PHC, with weighted capitation as one of its components, whose remuneration model is calculated based on the number of people registered.

Aspergillus clavatus UEM 04: An efficient producer of glucoamylase and α-amylase able to hydrolyze gelatinized and raw starch.

The best amylolytic activity production by Aspergillus clavatus UEM 04 occurred in submersed culture, with starch, for 72 h, at 25 °C, and 100 rpm. Exclusion chromatography partially purified two enzymes, which ran as unique bands in SDS-PAGE with approximately 84 kDa. LC-MS/MS identified a glucoamylase (GH15) and an α-amylase (GH13_1) as the predominant proteins and other co-purified proteins.

Lightweight multi-scale classification of chest radiographs via size-specific batch normalization.

Background And Objective: Convolutional neural networks are widely used to detect radiological findings in chest radiographs. Standard architectures are optimized for images of relatively small size (for example, 224 × 224 pixels), which suffices for most application domains. However, in medical imaging, larger inputs are often necessary to analyze disease patterns.

Hemodialysis vascular access coordinator: Three-level model for access management.

Management of vascular access is a challenge for the dialysis team, particularly to keep the arteriovenous access working. The vascular access coordinator can positively contribute to increase the number of arteriovenous fistulas and reduce central venous catheters. In this article, we introduce a new approach to vascular access management centered on (the results of setting up) the role of vascular access coordinator.

Retinal layer and fluid segmentation in optical coherence tomography images using a hierarchical framework.

Purpose: The development of accurate methods for retinal layer and fluid segmentation in optical coherence tomography images can help the ophthalmologists in the diagnosis and follow-up of retinal diseases. Recent works based on joint segmentation presented good results for the segmentation of most retinal layers, but the fluid segmentation results are still not satisfactory. We report a hierarchical framework that starts by distinguishing the retinal zone from the background, then separates the fluid-filled regions from the rest, and finally, discriminates the several retinal layers.

Effects of the addition of fatty acid from soybean oil sludge in recycled asphalt mixtures.

Recycling agents provide better additions of reclaimed asphalt pavement (RAP) in the production of new asphalt mixtures. Alternative and residual materials that have the potential as asphalt binder viscosity reducers have gained visibility in the field of paving due to the perspective of circular economy in recycled mixtures. Soybean oil sludge fatty acid is a material produced from soybean oil sludge, a waste generated in the soybean oil refining step.