RAMON ALFREDO MORENO
Índice h a partir de 2011
4
Projetos de Pesquisa
Unidades Organizacionais
Instituto do Coração, Hospital das Clínicas, Faculdade de Medicina
LIM/65, Hospital das Clínicas, Faculdade de Medicina
LIM/65, Hospital das Clínicas, Faculdade de Medicina
9 resultados
Resultados de Busca
Agora exibindo 1 - 9 de 9
conferenceObject Fully Automated Quantification of Cardiac Indices from Cine MRI Using a Combination of Convolution Neural Networks(2020) PEREIRA, Renato F.; REBELO, Marina S.; MORENO, Ramon A.; MARCO, Anderson G.; LIMA, Daniel M.; ARRUDA, Marcelo A. F.; KRIEGER, Jose E.; GUTIERREZ, Marco A.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.- Siamese pyramidal deep learning network for strain estimation in 3D cardiac cine-MR(2023) GRAVES, Catharine V.; REBELO, Marina F. S.; MORENO, Ramon A.; DANTAS-JR, Roberto N.; JR, Antonildes N. Assuncao; NOMURA, Cesar H.; GUTIERREZ, Marco A.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.
- Cardiac Motion Estimation using Pyramid, Warping, and Cost Volume Neural Network(2021) GRAVES, Catharine V.; MORENO, Ramon A.; REBELO, Marina F. S.; BORDIGNOM, Adriano; NOMURA, Cesar H.; GUTIERREZ, Marco A.Cardiac motion quantification in magnetic resonance (MR) images provides vital information to diagnose and evaluate cardiovascular diseases. Motion quantification can be obtained from routinely acquired MR images. However, the methods available for motion estimation present many sources of inconsistencies, thus creating constraints to use it as a reliable diagnostic technique. Recently, convolutional neural networks (CNNs) have demonstrated to be a powerful tool for many different imaging tasks, including optical flow estimation, a technique widely used for motion estimation. In this work, we evaluate the suitability of a compact and powerful CNN architecture based on Pyramid, Warping, and Cost Volume (PWC) for motion estimation in synthetic cardiac resonance images. The synthetic images were generated using the extended cardiac-torso (XCAT) and MRXCAT software, which generates temporal series of highly detailed MR images and their corresponding ground-truth motion field, which would be impossible to obtain in real-life data. The CNN training was unsupervised, simulating real data. The ground-truth provided by the synthetic images was used to evaluate the PWC performance, determining its reliability. The CNN achieved an average end-point-error of 0.61 +/- 0.25 pixel and a mean absolute error of 0.38 +/- 0.15 pixel in the test set, surpassing state-of-the-art methods. The results obtained in this work indicate a high potential of the unsupervised PWC network for future applications in real cardiac images.
conferenceObject Improving the generalization of deep learning methods to segment the left ventricle in short axis MR images(2020) GRAVES, Catharine V.; MORENO, Ramon A.; REBELO, Marina S.; NOMURA, Cesar H.; GUTIERREZ, Marco A.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.- MedCast - A discussion support system for cooperative work(2012) MORENO, Ramon A.; LIMA, Vinicius; LOPES, Isidro; GUTIERREZ, Marco A.The availability of low cost Internet connections and specialized hardware, like webcams and headsets, makes possible the development of solutions for remote collaborative work. These solutions can provide advantages compared to presential meetings, such as: availability of experts on remote locations; lower price compared to presential meetings; creation of online didactic material (e.g. video-classes); richer forms of interaction between participants. These technologies are particularly interesting for continent-sized countries where typically there is a short number of skilled people in remote areas. However, the application of these technologies in medical field represents a special challenge due to the more complex requirements of this area, such as: Provide confidentiality (patient de-identification) and integrity of patient data; Guarantee availability of the system; Guarantee authenticity of data and users; Provide simple and effective user interface; Be compliant with medical standards such as DICOM and HL7. In order to satisfy those requirements a prototype called MedCast is under development whose architecture allows the integration of the Hospital Information System (HIS) with a collaborative tool in compliance with the HIPAA rules. Some of the MedCast features are: videoconferencing, chat, recording of the sessions, sharing of documents and reports and still and dynamic images presentation. Its current version allows the remote discussion of clinical cases and the remote ECG evaluation.
- Estimation of 3D Biomechanics Parameters of Patellar Movement using Dynamic CT Images(2014) REBELO, Marina A.; MORENO, Ramon A.; GOBBI, Riccardo G.; CAMANHO, Gilberto L.; AVILA, Luiz F. R.; DEMANGE, Marco K.; PECORA, Jose R.; GUTIERREZ, Marco A.Multislice CT scanners have characteristics that offer advantages in clinical applications. The technology is particularly suited for medical applications that require high time performance and high spatial resolution. Patellofemoral tracking is one application that can benefit from multi slice CT characteristics. It is performed to study disturbances in the normal tracking mechanism of the patellar femoral joint. The patellofemoral instability is one condition that generates pain, functional impairment and often requires surgery as part of orthopedic treatment. The analysis of the patellofemoral dynamics has been performed by several medical image modalities. However, most of the methods are based on measurements in 2D images, such as the patellar tilt angle and the lateral shift. Besides, the acquisition protocols are mostly performed at fixed angles. The use of helical multislice CT scanner can allow the capture and display of the joint's movement performed actively by the patient. In this work we evaluate the use of multi slice high resolution CT technology to evaluate the biomechanics of the patellofemoral joint. The quantitative analysis of the movement is performed by extracting displacement parameters in 3D images between different knee positions. Analyses of these parameters for all frames provided real 3D information about the patellar displacement.
- 2D Image-Based Atrial Fibrillation Classification(2021) DIAS, Felipe M.; SAMESIMA, Nelson; RIBEIRO, Adele; MORENO, Ramon A.; PASTORE, Carlos A.; KRIEGER, Jose E.; GUTIERREZ, Marco A.Atrial fibrillation (AF) is a common arrhythmia (0.5% worldwide prevalence) associated with an increased risk of various cardiovascular disorders, including stroke. Automated routine AF detection by Electrocardiogram (ECG) is based on the analysis of one-dimensional ECG signals and requires dedicated software for each type of device, limiting its wide use, especially with the rapid incorporation of telemedicine into the healthcare system. Here, we implement a machine learning method for AF classification using the region of interest (ROI) corresponding to the long DII lead automatically extracted from DICOM 12-lead ECG images. We observed 94.3%, 98.9%, 99.1%, and 92.2% for sensitivity, specificity, AUC, and F1 score, respectively. These results indicate that the proposed methodology performs similar to one-dimensional ECG signals as input, but does not require a dedicated software facilitating the integration into clinical practice, as ECGs are typically stored in PACS as 2D images.
- A combined deep-learning approach to fully automatic left ventricle segmentation in cardiac magnetic resonance imaging(2019) MORENO, Ramon A.; REBELO, Marina F. S. de Sa; CARVALHO, Talles; ASSUNCAO-JR, Antonildes N.; JR, Roberto N. Dantas; VAL, Renata do; MARIN, Angela S.; BORDIGNOM, Adriano; NOMURA, Cesar H.; GUTIERREZ, Marco A.In clinical practice, cardiac magnetic resonance imaging (CMR) is considered the gold-standard imaging modality for the evaluation of function and structure of the left ventricle (LV). However, the quantification of LV parameters in all frames, even when performed by experienced radiologists, is very time consuming mainly due to the inhomogeneity of cardiac structures within each image, the variability of the cardiac structures across subjects and the complicated global/regional temporal deformation of the myocardium during the cardiac cycle. In this work, we employed a combination of two convolutional neural networks (CNN) to develop a fully automatic LV segmentation method for Short Axis CMR datasets. The first CNN defines the region of interest (ROI) of the cardiac chambers based on You Only Look Once (YOLO) network. The output of YOLO net is used to filter the image and feed the second CNN, based on U-Net network, which segments the myocardium and the blood pool. The method was validated in CMR exams of 59 individuals from an institutional clinical protocol. Segmentation results, evaluated by metrics Percentage of Good Contours, Dice Index and Average Perpendicular distance, were 98,59% +/- 4,28%, 0,93 +/- 0,06 and 0,72 mm +/- 0,62 mm, respectively, for the LV epicardium, and 94,98% +/- 14,04%, 0,86 +/- 0,13 and 1,19 mm +/- 1,29 mm, respectively, for the LV endocardium. The combination of two CNNs demonstrated good performance in terms of the evaluated metrics when compared to literature results.
- Analysis of grid performance using an Optical Flow algorithm for Medical Image processing(2014) MORENO, Ramon A.; CUNHA, Rita de Cassio Porfirio; GUTIERREZ, Marco A.The development of bigger and faster computers has not yet provided the computing power for medical image processing required nowadays. This is the result of several factors, including: i) the increasing number of qualified medical image users requiring sophisticated tools; ii) the demand for more performance and quality of results; iii) researchers are addressing problems that were previously considered extremely difficult to achieve; iv) medical images are produced with higher resolution and on a larger number. These factors lead to the need of exploring computing techniques that can boost the computational power of Healthcare Institutions while maintaining a relative low cost. Parallel computing is one of the approaches that can help solving this problem. Parallel computing can be achieved using multi-core processors, multiple processors, Graphical Processing Units (GPU), clusters or Grids. In order to gain the maximum benefit of parallel computing it is necessary to write specific programs for each environment or divide the data in smaller subsets. In this article we evaluate the performance of the two parallel computing tools when dealing with a medical image processing application. We compared the performance of the EELA-2 (E-science grid facility for Europe and Latin-America) grid infrastructure with a small Cluster (3 nodes x 8 cores = 24 cores) and a regular PC (Intel i3 - 2 cores). As expected the grid had a better performance for a large number of processes, the cluster for a small to medium number of processes and the PC for few processes.