Siamese pyramidal deep learning network for strain estimation in 3D cardiac cine-MR.

Strain represents the quantification of regional tissue deformation within a given area. Myocardial strain has demonstrated considerable utility as an indicator for the assessment of cardiac function. Notably, it exhibits greater sensitivity in detecting subtle myocardial abnormalities compared to conventional cardiac function indices, like left ventricle ejection fraction (LVEF). Nonetheless, the estimation of strain poses considerable challenges due to the necessity for precise tracking of myocardial motion throughout the complete cardiac cycle. This study introduces a novel deep learning-based pipeline, designed to automatically and accurately estimate myocardial strain from three-dimensional (3D) cine-MR images. Consequently, our investigation presents a comprehensive pipeline for the precise quantification of local and global myocardial strain. This pipeline incorporates a supervised Convolutional Neural Network (CNN) for accurate segmentation of the cardiac muscle and an unsupervised CNN for robust left ventricle motion tracking, enabling the estimation of strain in both artificial phantoms and real cine-MR images. Our investigation involved a comprehensive comparison of our findings with those obtained from two commonly utilized commercial software in this field. This analysis encompassed the examination of both intra- and inter-user variability. The proposed pipeline exhibited demonstrable reliability and reduced divergence levels when compared to alternative systems. Additionally, our approach is entirely independent of previous user data, effectively eliminating any potential user bias that could influence the strain analyses.

ClinicalPath: A Visualization Tool to Improve the Evaluation of Electronic Health Records in Clinical Decision-Making.

Physicians work at a very tight schedule and need decision-making support tools to help on improving and doing their work in a timely and dependable manner. Examining piles of sheets with test results and using systems with little visualization support to provide diagnostics is daunting, but that is still the usual way for the physicians' daily procedure, especially in developing countries. Electronic Health Records systems have been designed to keep the patients' history and reduce the time spent analyzing the patient's data. However, better tools to support decision-making are still needed. In this article, we propose ClinicalPath, a visualization tool for users to track a patient's clinical path through a series of tests and data, which can aid in treatments and diagnoses. Our proposal is focused on patient's data analysis, presenting the test results and clinical history longitudinally. Both the visualization design and the system functionality were developed in close collaboration with experts in the medical domain to ensure a right fit of the technical solutions and the real needs of the professionals. We validated the proposed visualization based on case studies and user assessments through tasks based on the physician's daily activities. Our results show that our proposed system improves the physicians' experience in decision-making tasks, made with more confidence and better usage of the physicians' time, allowing them to take other needed care for the patients.

Automatic myocardium strain quantification in MR synthetic images with Deep Leaning.

Accurate quantification of myocardium strain in magnetic resonance images is important to correctly diagnose and monitor cardiac diseases. Currently, available methods to estimate motion are based on tracking brightness pattern differences between images. In cine-MR images, the myocardium interior presents an inhered homogeneity, which reduces the accuracy in estimated motion, and consequently strain. Neural networks have recently been shown to be an important tool for a variety of applications, including motion estimation. In this work, we investigate the feasibility of quantifying myocardium strain in cardiac resonance synthetic images using motion generated by a compact and powerful network called Pyramid, Warping, and Cost Volume (PWC). Using the motion generated by the neural network, the radial myocardium strain obtained presents a mean average error of 12.30% +- 6.50%, and in the circumferential direction 1.20% +-0.61 %, better than the two classical methods evaluated. Clinical Relevance- This work demonstrates the feasibility of estimating myocardium strain using motion estimated by a convolutional neural network.

Improving the generalization of deep learning methods to segment the left ventricle in short axis MR images.

Cardiovascular disease is one of the major health problems worldwide. In clinical practice, cardiac magnetic resonance imaging (CMR) is considered the gold-standard imaging modality for the evaluation of the function and structure of the left ventricle (LV). More recently, deep learning methods have been used to segment LV with impressive results. On the other hand, this kind of approach is prone to overfit the training data, and it does not generalize well between different data acquisition centers, thus creating constraints to the use in daily routines. In this paper, we explore methods to improve the generalization in the segmentation performed by a convolutional neural network. We applied a U-net based architecture and compared two different pre-processing methods to improve uniformity in the image contrast between five cross-dataset training and testing. Overall, we were able to perform the segmentation of the left ventricle using multiple cross-dataset combinations of train and test, with a mean endocardium dice score of 0.82.Clinical Relevance- This work improves the result between the cross-dataset evaluation of the left ventricle segmentation, reducing the constraints for daily clinical adoption of a fully-automatic segmentation method.

Fully Automated Quantification of Cardiac Indices from Cine MRI Using a Combination of Convolution Neural Networks.

Cardiovascular magnetic resonance imaging (CMRI) is one of the most accurate non-invasive modalities for evaluation of cardiac function, especially the left ventricle (LV). In this modality, the manual or semi-automatic delineation of LV by experts is currently the standard clinical practice for chambers segmentation. Despite these efforts, global quantification of LV remains a challenge. In this work, a combination of two convolutional neural network (CNN) architectures for quantitative evaluation of the LV is described, which estimates the cavity and the myocardium areas, endocardial cavity dimensions in three directions, and the myocardium regional wall thickness in six radial directions. The method was validated in CMRI exams of 56 patients (LVQuan19 dataset) and evaluated by metrics Dice Index, Mean Absolute Error, and Correlation with superior performance compared to the state-of-the-art methods. The combination of the CNN architectures provided a simpler yet fully automated approach, requiring no specialist interaction.Clinical Relevance- With the proposed method, it is possible to perform automatically the full quantification of regional clinically relevant parameters of the left ventricle in short-axis CMRI images with superior performance compared to state-of-the-art methods.

Transforming Two Decades of ePR Data to OMOP CDM for Clinical Research.

This paper presents the extract-transform-and-load (ETL) process from the Electronic Patient Records (ePR) at the Heart Institute (InCor) to the OMOP Common Data Model (CDM) format. We describe the initial database characterization, relational source mappings, selection filters, data transformations and patient de-identification using the open-source OHDSI tools and SQL scripts. We evaluate the resulting InCor-CDM database by recreating the same patient cohort from a previous reference study (over the original data source) and comparing the cohorts' descriptive statistics and inclusion reports. The results exhibit that up to 91% of the reference patients were retrieved by our method from the ePR through InCor-CDM, with AUC=0.938. The results indicate that the method that we employed was able to produce a new database that was both consistent with the original data and in accordance to the OMOP CDM standard.

Integrating planning perception and action for informed object search.

This paper presents a method to reduce the time spent by a robot with cognitive abilities when looking for objects in unknown locations. It describes how machine learning techniques can be used to decide which places should be inspected first, based on images that the robot acquires passively. The proposal is composed of two concurrent processes. The first one uses the aforementioned images to generate a description of the types of objects found in each object container seen by the robot. This is done passively, regardless of the task being performed. The containers can be tables, boxes, shelves or any other kind of container of known shape whose contents can be seen from a distance. The second process uses the previously computed estimation of the contents of the containers to decide which is the most likely container having the object to be found. This second process is deliberative and takes place only when the robot needs to find an object, whether because it is explicitly asked to locate one or because it is needed as a step to fulfil the mission of the robot. Upon failure to guess the right container, the robot can continue making guesses until the object is found. Guesses are made based on the semantic distance between the object to find and the description of the types of the objects found in each object container. The paper provides quantitative results comparing the efficiency of the proposed method and two base approaches.

A Passive Learning Sensor Architecture for Multimodal Image Labeling: An Application for Social Robots.

Object detection and classification have countless applications in human-robot interacting systems. It is a necessary skill for autonomous robots that perform tasks in household scenarios. Despite the great advances in deep learning and computer vision, social robots performing non-trivial tasks usually spend most of their time finding and modeling objects. Working in real scenarios means dealing with constant environment changes and relatively low-quality sensor data due to the distance at which objects are often found. Ambient intelligence systems equipped with different sensors can also benefit from the ability to find objects, enabling them to inform humans about their location. For these applications to succeed, systems need to detect the objects that may potentially contain other objects, working with relatively low-resolution sensor data. A passive learning architecture for sensors has been designed in order to take advantage of multimodal information, obtained using an RGB-D camera and trained semantic language models. The main contribution of the architecture lies in the improvement of the performance of the sensor under conditions of low resolution and high light variations using a combination of image labeling and word semantics. The tests performed on each of the stages of the architecture compare this solution with current research labeling techniques for the application of an autonomous social robot working in an apartment. The results obtained demonstrate that the proposed sensor architecture outperforms state-of-the-art approaches.

Georeferenced and secure mobile health system for large scale data collection in primary care.

INTRODUCTION: Mobile health consists in applying mobile devices and communication capabilities for expanding the coverage and improving the effectiveness of health care programs. The technology is particularly promising for developing countries, in which health authorities can take advantage of the flourishing mobile market to provide adequate health care to underprivileged communities, especially primary care. In Brazil, the Primary Care Information System (SIAB) receives primary health care data from all regions of the country, creating a rich database for health-related action planning. Family Health Teams (FHTs) collect this data in periodic visits to families enrolled in governmental programs, following an acquisition procedure that involves filling in paper forms. This procedure compromises the quality of the data provided to health care authorities and slows down the decision-making process. OBJECTIVES: To develop a mobile system (GeoHealth) that should address and overcome the aforementioned problems and deploy the proposed solution in a wide underprivileged metropolitan area of a major city in Brazil. METHODS: The proposed solution comprises three main components: (a) an Application Server, with a database containing family health conditions; and two clients, (b) a Web Browser running visualization tools for management tasks, and (c) a data-gathering device (smartphone) to register and to georeference the family health data. A data security framework was designed to ensure the security of data, which was stored locally and transmitted over public networks. RESULTS: The system was successfully deployed at six primary care units in the city of Sao Paulo, where a total of 28,324 families/96,061 inhabitants are regularly followed up by government health policies. The health conditions observed from the population covered were: diabetes in 3.40%, hypertension (age >40) in 23.87% and tuberculosis in 0.06%. This estimated prevalence has enabled FHTs to set clinical appointments proactively, with the aim of confirming or detecting cases of non-communicable diseases more efficiently, based on real-time information. CONCLUSION: The proposed system has the potential to improve the efficiency of primary care data collection and analysis. In terms of direct costs, it can be considered a low-cost solution, with an estimated additional monthly cost of U$ 0.040 per inhabitant of the region covered, or approximately U$ 0.106 per person, considering only those currently enrolled in the system.

Ambiente para extração de informações de saúde a partir de bases de dados do SUS / Environment for extracting health information starting from the SUS database

A aplicação de técnicas para produção de informação gerencial e descoberta de conhecimentos em grandes bases de dados, como as existentes nos sistemas de informação do DATASUS, pode representar um avanço substancial na gestão do Sistema Único de Saúde (SUS). Os dados da saúde pública são produzidos por vários sistemas isolados e não integrados, tornando mais difícil a tarefa de produzir informação gerencial. Essa dificuldade motivou este trabalho, cujo objetivo é criar um ambiente (MinerSUS) para extração de informação, a partir da mineração das bases de dados do SUS no Estado de São Paulo. Nesse sentido, foi implantado um ambiente adequado às peculiaridades da Saúde Pública e dos sistemas de informações do SUS, com as seguintes características: 1) Data Warehouse (DW) reunindo e integrando os dados dos sistemas do SUS; 2) processo de coleta, limpeza, integração e carga das bases de dados do SUS no DW; 3) componente para produção de informação gerencial; 4) metodologia para identificar o paciente em seus diversos atendimentos no Sistema Público de Saúde. Foram realizados diversos testes para avaliar a funcionalidade e a efetividade das ferramentas criadas, com ênfase em aplicações de cardiologia. Os resultados evidenciaram a efetividade das ferramentas nos aspectos mais complexos da gestão de informações para desenvolver conhecimentos, a partir das bases de dados do DATASUS

Medical Image distribution and visualization in a hospital using CORBA.

In this work it is presented the solution adopted by the Heart Institute (InCor) of Sao Paulo for medical image distribution and visualization inside the hospital's intranet as part of the PACS system. A CORBA-based image server was developed to distribute DICOM images across the hospital together with the images' report. The solution adopted allows the decoupling of the server implementation and the client. This gives the advantage of reusing the same solution in different implementation sites. Currently, the PACS system is being used on two different hospitals each one with three different environments: development, prototype and production.

Managing medical images and clinical information: InCor's experience.

Patients usually get medical assistance in several clinics and hospitals during their lifetime, archiving vital information in a dispersed way. Clearly, a proper patient care should take into account that information in order to check for incompatibilities, avoid unnecessary exams, and get relevant clinical history. The Heart Institute (InCor) of São Paulo, Brazil, has been committed to the goal of integrating all exams and clinical information within the institution and other hospitals. Since InCor is one of the six institutes of the University of São Paulo Medical School and each institute has its own information system, exchanging information among the institutes is also a very important aspect that has been considered. In the last few years, a system for transmission, archiving, retrieval, processing, and visualization of medical images integrated with a hospital information system has been successfully created and constitutes the InCor's electronic patient record (EPR). This work describes the experience in the effort to develop a functional and comprehensive EPR, which includes laboratory exams, images (static, dynamic, and three dimensional), clinical reports, documents, and even real-time vital signals. A security policy based on a contextual role-based access control model was implemented to regulate user's access to EPR. Currently, more than 10 TB of digital imaging and communications in medicine (DICOM) images have been stored using the proposed architecture and the EPR stores daily more than 11 GB of integrated data. The proposed storage subsystem allows 6 months of visibility for rapid retrieval and more than two years for automatic retrieval using a jukebox. This paper addresses also a prototype for the integration of distributed and heterogeneous EPR.

Quantificaçäo do movimento 3D do miocárdio em Gated SPECT / Quantifies 3D motion of myocardial in Gated SPECT

Os métodos convencionais para análise do movimento do ventrículo esquerdo (VE) são baseados em imagens planas e considerações geométricas que, em geral, são inválidas em ventrículos anormais. Propõe-se, neste trabalho, a quantificação do movimento 3D do VE em imagens de Medicina Nuclear (gated-SPECT), através da técnica de Fluxo Óptico estendida para o espaço voxel. O movimento das paredes do VE é representado por uma série de campos de vetores de velocidade 3D, os quais são calculados automaticamente para cada voxel na seqüência de volumes cardíacos.

The conventional methods for analysis of L V wall motion abnormalities are based on planar images and geometrical analysis with many hardly fulfilled assumptions. This work describes a method which quantifies 3D L V motion by means of the optical flow technique extended to the voxel space. The LV wall motion is represented by a series of 3D velocity vector field which is computed automatically by the proposed method for each voxel on the sequence of cardiac volumes.