Highlights • Proposing an accurate intersubject registration for cardiac CT images. • Proposing and analyzing a hybrid similarity measure that was applied within the registration procedure. • ...Corroborating on the appliance of classification algorithms for image segmentation. • Analyzing the performance and accuracy of various classifiers for the problem. • Proposing a unified and fully automatic segmentation method for both epicardial and mediastinal fats on cardiac CT images.
We propose a methodology to predict the cardiac epicardial and mediastinal fat volumes in computed tomography images using regression algorithms. The obtained results indicate that it is feasible to ...predict these fats with a high degree of correlation, thus alleviating the requirement for manual or automatic segmentation of both fat volumes. Instead, segmenting just one of them suffices, while the volume of the other may be predicted fairly precisely. The correlation coefficient obtained by the Rotation Forest algorithm using MLP Regressor for predicting the mediastinal fat based on the epicardial fat was 0.9876, with a relative absolute error of 14.4% and a root relative squared error of 15.7%. The best correlation coefficient obtained in the prediction of the epicardial fat based on the mediastinal was 0.9683 with a relative absolute error of 19.6% and a relative squared error of 24.9%. Moreover, we analysed the feasibility of using linear regressors, which provide an intuitive interpretation of the underlying approximations. In this case, the obtained correlation coefficient was 0.9534 for predicting the mediastinal fat based on the epicardial, with a relative absolute error of 31.6% and a root relative squared error of 30.1%. On the prediction of the epicardial fat based on the mediastinal fat, the correlation coefficient was 0.8531, with a relative absolute error of 50.43% and a root relative squared error of 52.06%. In summary, it is possible to speed up general medical analyses and some segmentation and quantification methods that are currently employed in the state-of-the-art by using this prediction approach, which consequently reduces costs and therefore enables preventive treatments that may lead to a reduction of health problems.
Three aspects of texture are distinguished by fractal geometry: Fractal Dimension (FD), Lacunarity and Succolarity. Although, FD has been well studied and Lacunarity has been more and more used, ...Succolarity, until now, has not been considered. This work presents a method to compute Succolarity. The proposed approach, for this computation, is based on the evaluation of a proposed equation that employ the FD Box Counting idea adapted to the concept of Succolarity. Simple examples, on 2D and 3D images, are considered to easily explain, step by step, how to compute the Succolarity. To illustrate this approach examples are shown, they range form satellite to ultrasound images. The proposed form of Succolarity evaluation is a unique feature usable whether it is relevant differentiate images with some directional or flow information associated with it. Therefore it could be used as a new feature in pattern recognition processes for the identification of natural textures. Furthermore, it works very well when is relevant differentiate images with some characteristics (e.g. directional information) that can not be discriminate by FD or Lacunarity.
The major goal of this paper is to help detect breast cancer early based on infrared images. Some procedures, protocols and numerical simulations were developed or performed. Two different issues are ...presented. The first is the development of a standardized protocol for the acquisition of breast thermal images including the design, construction and installation of mechanical apparatus. The second part is related to the greatest difficulty for the numerical computation of breast temperature profiles that is caused by the uncertainty of the real values of the thermophysical parameters of some tissues. Then, a methodology for estimating thermal properties based on these infrared images is presented. The commercial software FLUENTTM was used for the numerical simulation. A Sequential Quadratic Programming (SQP) method was used to solve the inverse problem and to estimate the thermal conductivity and blood perfusion of breast tissues. The results showed that it is possible to estimate the thermophysical properties using the thermography. The next stage will be to use the geometry of a real breast for the numerical simulation in conjunction with a linear mapping of the temperatures measured over the breast volume.
► Design of a mechanical apparatus for the acquisition of breast infrared images. ► Apparatus installation in a public hospital located in a tropical climate region. ► Establishment of a new protocol for the acquisition of breast thermal images. ► Standardized breast thermal images to be used in automatic image processing. ► Estimation of some breast thermophysical parameters using breast infrared images.
Thyroid nodules are common, and their investigation is very important to exclude the possibility of cancer. The increase in blood vessels of malignant tumours may be related to local temperature ...augmentation detectable on the skin surface. The objective of this paper is to evaluate the feasibility of Infrared Thermography for cancer identification. For this purpose, two studies were performed. One used numerical modelling to simulate regional metabolic temperature propagation to evaluate whether a nodule is perceptible on the skin surface. A second study considered thyroid nodule identification by using convolutional neural networks (CNNs). First, variations in nodular size and fat thickness were investigated, showing that the fat layer has an important role in regional heat transfer. In the second study, the training process achieved accuracy of 96% for in-sample and 95% for validation. In the testing phase, 92% accuracy, 100% precision and 80% recall were achieved. Thus, the presented studies suggest the feasibility of using Infrared Thermography with the CNN Artificial Intelligence technique as additional information in the investigation of thyroid nodules for patients without a very thick subcutaneous fat layer.
The manuscript offers a methodology to solve an analytical model of a heterogeneous elastic problem for curvilinear layered structures, using the two scales asymptotic homogenization method (AHM). ...The local problems and the mechanical properties of the local functions were derived. The analytical modeling for the linear elastic problem considering quasi-periodic multi-layered curvilinear composites and the corresponding homogenized problem were obtained. The analytic expression of the effective stress for curvilinear composites is presented. In order to validate the presented model, comparisons with a computational modeling and experimental results for Fibonacci laminated composite and wavy laminated structure are given. The methodology is applied to composites with thickness variation where the effective coefficients were computed and a comparison between the results reported by AHM and numerical analysis given by finite element method (FEM) is presented. Finally, the aorta is studied as a curvilinear laminated shell composite and the above results were used to determinate the effective elastic tensor for healthy and unhealthy aorta using AHM and FEM.
Abstract This work proposes the use of Genetic Algorithms (GA) in tracing and recognizing the pericardium contour of the human heart using Computed Tomography (CT) images. We assume that each slice ...of the pericardium can be modelled by an ellipse, the parameters of which need to be optimally determined. An optimal ellipse would be one that closely follows the pericardium contour and, consequently, separates appropriately the epicardial and mediastinal fats of the human heart. Tracing and automatically identifying the pericardium contour aids in medical diagnosis. Usually, this process is done manually or not done at all due to the effort required. Besides, detecting the pericardium may improve previously proposed automated methodologies that separate the two types of fat associated to the human heart. Quantification of these fats provides important health risk marker information, as they are associated with the development of certain cardiovascular pathologies. Finally, we conclude that GA offers satisfiable solutions in a feasible amount of processing time.
Interest in the application of computer vision techniques to automatic video-based analysis of traffic is high at present. This is due in part to the capabilities of video sensors, as well as to ...social demands for traffic safety. In general, these systems are cheaper and less disruptive than other kinds of devices like loop detectors for traffic monitoring. Automatic traffic surveillance is, however, still a challenging problem when we consider many of the practical difficulties involved (i.e. limited number of cameras and positions of these with respect to the scene, variable illumination and weather conditions, intrinsic complexity of analyzed traffic events, need for a real-time frame rate processing, among others). In this paper, we propose a multi-level framework for automatic analysis of complex traffic videos which present different kind of variations. The accurate and efficient extraction of relevant scene information from the video frames is performed in a hierarchical bottom-up form using the system presented. First of all, foreground moving pixels are detected in each frame using a proposed method of adaptive background subtraction. After that, these pixels are grouped into blobs if they share some common properties. Blobs detected in predefined scene entry regions are identified as vehicles and these are tracked along the controlled road area. At the upper level, some traffic monitoring statistics and also related linguistic reports on the evolution of traffic in the scene are generated periodically. Experimental results on the adaptive background method proposed, as well as regarding its integration in the multi-level traffic analysis system, are very satisfactory for the traffic videos analyzed.
Morphological classifiers Rodrigues, É.O.; Conci, A.; Liatsis, P.
Pattern recognition,
December 2018, 2018-12-00, Volume:
84
Journal Article
Peer reviewed
Open access
•Classification framework proposal that uses mathematical morphology.•Mathematical morphology is sensitive to shapes, density and fractal information in datasets.•Experiments indicate that ...morphological approaches are tangible.•Generated predictive models are fast and visual oriented.
This work proposes a new type of classifier called Morphological Classifier (MC). MCs aggregate concepts from mathematical morphology and supervised learning. The outcomes of this aggregation are classifiers that may preserve shape characteristics of classes, subject to the choice of a stopping criterion and structuring element. MCs are fundamentally based on set theory, and their classification model can be a mathematical set itself. Two types of morphological classifiers are proposed in the current work, namely, Morphological k-NN (MkNN) and Morphological Dilation Classifier (MDC), which demonstrate the feasibility of the approach. This work provides evidence regarding the advantages of MCs, e.g., very fast classification times as well as competitive accuracy rates. The performance of MkNN and MDC was tested using p-dimensional datasets. MCs tied or outperformed 14 well established classifiers in 5 out of 8 datasets. In all occasions, the obtained accuracies were higher than the average accuracy obtained with all classifiers. Moreover, the proposed implementations utilize the power of the Graphics Processing Units (GPUs) to speed up processing.
Abstract We propose a methodology to predict the cardiac epicardial and mediastinal fat volumes in Computed Tomography images using regression algorithms. We conclude that it is feasible to predict ...these fats with a high degree of correlation, thus alleviating the requirement for manual or automatic segmentation of both fat volumes. Instead, segmenting just one of them suffices, while the volume of the other may be predicted fairly precisely. The correlation coefficient obtained by the Rotation Forest algorithm using the MLP Regressor in predicting the mediastinal fat based on the epicardial fat is 0.9876, with a relative absolute error of 14.4% and a root relative squared error of 15.7%. The best correlation coefficient obtained in predicting the epicardial fat based on the mediastinal information is 0.9683 with a relative absolute error of 19.6% and a relative squared error of 24.9%. Moreover, we analysed the feasibility of using linear regressors, which provide an intuitive interpretation of the underlying approximations. Specifically, when using linear regression for prediction of the mediastinal fat based on the epicardial fat the correlation coefficient is 0.9534, with a relative absolute error of 31.6% and a root relative squared error of 30.1%. In the case of prediction of the epicardial fat based on the mediastinal fat using the linear regressor, the correlation coefficient is 0.8531, with a relative absolute error of 50.43% and a root relative squared error of 52.06%. Using this approach, it is possible to speed up some segmentation and quantification methods, currently employed in the state-of-the-art, as well as subsequent medical analysis, thus supporting the prevention of health problems and reducing undesirable outcomes.