Aura Conci

Hybrid analysis for indicating patients with breast cancer using temperature time series

Breast cancer is the most common cancer among women worldwide. Diagnosis and treatment in early stages increase cure chances. The temperature of cancerous tissue is generally higher than that of healthy surrounding tissues, making thermography an option to be considered in screening strategies of this cancer type. This paper proposes a hybrid methodology for analyzing dynamic infrared thermography in order to indicate patients with risk of breast cancer, using unsupervised and supervised machine learning techniques, which characterizes the methodology as hybrid. The dynamic infrared thermography monitors or quantitatively measures temperature changes on the examined surface, after a thermal stress. In the dynamic infrared thermography execution, a sequence of breast thermograms is generated. In the proposed methodology, this sequence is processed and analyzed by several techniques. First, the region of the breasts is segmented and the thermograms of the sequence are registered. Then, temperature time series are built and the k-means algorithm is applied on these series using various values of k. Clustering formed by k-means algorithm, for each k value, is evaluated using clustering validation indices, generating values treated as features in the classification model construction step. A data mining tool was used to solve the combined algorithm selection and hyperparameter optimization (CASH) problem in classification tasks. Besides the classification algorithm recommended by the data mining tool, classifiers based on Bayesian networks, neural networks, decision rules and decision tree were executed on the data set used for evaluation. Test results support that the proposed analysis methodology is able to indicate patients with breast cancer. Among 39 tested classification algorithms, K-Star and Bayes Net presented 100% classification accuracy. Furthermore, among the Bayes Net, multi-layer perceptron, decision table and random forest classification algorithms, an average accuracy of 95.38% was obtained.

A new measure for comparing biomedical regions of interest in segmentation of digital images

The segmentation of the region of interest (ROI) of digital images is generally the first step in the pattern recognition (PR) procedure. Automatic segmentation of biomedical images is desirable and comparisons among new approaches, by using available databases, are important. We present a new approach to compute the Hausdorff distance (HD) between digital images. Although HD is the most used distance estimator among sets, we show why it is not suitable for biomedical applications. In this paper, a new technique to define the degree of correction of the ROI is developed to serve as a basis for the comparisons used to validate works on segmentation of biomedical images. As for online diagnosis, the comparison among possible techniques must be efficient enough to: (1) be done in real time (i.e. during the examination), (2) allow the inclusion of priority aspects, and (3) be intuitive and simple enough to be easily followed by people with no computational or mathematical background. We develop a new index by considering the expectations of the medical doctors who are using computer systems for diagnostic aids, and take into consideration how these systems use ROIs to extract feature properties from the examinations. We discuss conditions for empirically defining a measure for calculating similarities and differences between ROIs. The proposed method is applied to both real and simulated data examples.

Towards the automated segmentation of epicardial and mediastinal fats: A multi-manufacturer approach using intersubject registration and random forest

The amount of fat on the surroundings of the heart is correlated to several health risk factors such as carotid stiffness, coronary artery calcification, atrial fibrillation, atherosclerosis, cancer incidence and others. Furthermore, the cardiac fat varies unrelated to the overall fat of the subject, and, therefore, it reinforces the quantitative analysis of these adipose tissues as being essential. Clinical decision support systems are computer programs capable of evaluating information and providing a corresponding diagnosis or data to complement the physicists analyses. The aim of this work is to propose a method capable of fully automatically segmenting two types of cardiac adipose tissues that stand apart from each other by the pericardium on CT images obtained by the standard acquisition protocol used for coronary calcium scoring. Much effort was devoted to promote minimal user intervention and ease of reproducibility. The methodology proposed in this work consists of a registration, which will roughly adjust input images to a standard, an extraction of features related to pixels and their surrounding area and a segmentation step based on data mining classification algorithms that define if an incoming pixel is of a certain type. Experimentations showed that the achieved mean accuracy for the epicardial and mediastinal fats was 98.4% with a mean true positive rate of 96.2%. In average, the Dice similarity index was equal to 96.8%.

Segmentation of infrared images: A new technology for early detection of breast diseases

In a first stage a cancer promotes an intense process of vascularization at the affected area increasing blood flow and modifying the local temperature of the body. Using a thermal camera, the infrared radiation emitted by the human body can be captured and then used in the measuring of body temperature, turning the results into an image. Moreover, thermography can detect suspicious regions in patients of any age, even in cases of dense breasts, where the detection of an abnormality cannot be accomplished by others exams. A fundamental step in the use of thermal images is the development of computer aided diagnosis (CAD) systems. These could allow the execution of exams by technicians, following well established routines and protocols, as already occurs in mammography exams, allowing doctors to have a greater possibility of dedication in the analysis and in the meaning of the exams. In this work, an automatic detection of the regions of interest (ROI) is proposed and compared with segmentations performed manually. This work presents a methodology for the automatic segmentation of lateral breast thermal images. For the evaluation of the results, different groups of ground truth are generated, which are available on the internet, in order to allow the verification of the results correctness. Finally, the obtained results by the proposed methodology for the 328 images used in this work are demonstrated. The results showed average values of accuracy.

Automatic Segmentation and Analysis of Thermograms Using Texture Descriptors for Breast Cancer Detection

Breast cancer is one of the leading causes for high mortality rates among young women, in the developing countries. In Latin American this is an important health problem, for instance in Brazil and Ecuador this is the leading cause of cancer among women around 35 years old. Currently mammography is used as the gold standard for screening breast cancer. However, for young women mammograms are not recommended due the low contrast it presents on dense breasts and alternative techniques must be considered for this purpose. The World Health Organization states that screening programs are the more efficient way to combat this disease. Therefore it is fundamental to address new researches on early detection that are cost-effective and present advantages over the current method (based on the self-examination and mammography). The identification of such disease in early stage increases the prognosis and the survival rate. This article proposes to incorporate a low-cost and non-invasive diagnostic technique based on the use of thermal imaging. A textural analysis (by using statistical descriptors for automatic detection of abnormality in breast thermo grams) is considered for features as well as statistics measures computed from thermo grams ROI (region of interest). Theses features feed a Nearest Neighbors classifier, where abnormal breasts are was identified with an accuracy of 94.44 %. The results of the study show that using simple textures descriptors, appropriate filtering and enhancement techniques it is possible to detected early onset of breast tumor in women of any age, with breasts of any density or size and even in pregnant women.

Automated recognition of the pericardium contour on processed CT images using genetic algorithms

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.

A simple approach for biometrics: Finger-knuckle prints recognition based on a Sobel filter and similarity measures

The objective of this work is to propose a novel methodology for the finger knuckle print recognition, which is essentially a digital photo of the finger-knuckle region. We have employed very simple concepts of visual computing such as a filter based on the Sobel operator for finding edges and a simple noise reduction algorithm. These operations are exceptionally fast and produce binary images, which are very efficient to process and to store. Furthermore, alongside this preprocessing, some similarity measures were also regarded and evaluated for the task. After preprocessing an input finger it is compared to all the images of fingers in the dataset, one by one. We have obtained up to 17.02% of successful recognitions (true positive rate) with a large dataset.

Machine learning in the prediction of cardiac epicardial and mediastinal fat volumes

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.

Automatic detection of injuries in mammograms using image analysis techniques

Breast cancer is the most common cancer and the second cause of cancer death among women. Early detection is the key to reducing the associated mortality rate, for this identify the presence of microcalcifications is very important. This paper presents an approach for micro calcification detection in mammography based on the following steps: noise reduction, image segmentation, extraction of the region of interest (ROI) and features that describe the possible asymmetries between the ROI of both breasts. The new aspect of our work is how we detect the microcalcifications by using wavelet decomposition. All decompositions were conducted using orthogonal wavelet filter set to computes the four filters associated with the scaling filter corresponding to a wavelet: low-pass filter and high-pass filter. Several mother families have been tested and we are confident to recommend the coiflets as the best one.

Using wavelets on denoising infrared medical images

This work presents the conclusions of an experimental study that intends to find the best procedure for reducing the noise of medium resolution infrared images. The goal is to find a good scheme for an image database suitable for use in developing a system to aid breast disease diagnostics. In particular, to use infrared images in the screening and postoperative follow-up in the UFF university hospital, and to combine this with other types of image based diagnoses. Seven wavelet types (Biorthogonal, Coiflets, Daubechies, Haar, Meyer, Reverse Biorthogonal and Symmlets) with various vanishing moments (such as Symmlets, where this number goes from 2 to 28, Daubechies from 1 to 45 and Coiflets 1 to 5) comprising a total of 108 different variations of wavelet functions are compared in a denoising scheme to explore their difference with respect to image quality. Three groups of Additive White Gaussian Noise levels (σ = 5, 25 and 50) are used to evaluate the relations among the approaches to threshold the wavelet coefficient (hard or soft), and the image quality after transformation-denoising-storage-decompression. Levels of decomposition are investigated in a new thresholding scheme, where the decision about the coefficient to be eliminated considers all variation, aiming for the best quality of reconstruction. Eight images of the same type and resolution are used in order to find the mean, median, range and standard deviation of the 432 combinations for each level of noise. Moreover, three evaluators (Normalized Cross-Correlation, Signal to Noise Ratio and Root Mean Squared Error) are considered for recommendation of the best possible combination of parameters.