A computing platform to analyze breast abnormalities using infrared images.

The present work shows a computational tool developed in the MATLAB platform. Its main functionality is to evaluate a thermal model of the breast. This computational infrastructure consists of modules in which manipulate the infrared images and calculate breast temperature profiles. It also allows the analysis of breast nodules. The different modules of the framework are interconnected through an interface which the major purpose is to automatize the whole process of the infrared image analysis, in a quick and organized way. The tool is initially supplied with a three-dimensional mesh that represents the substitute geometry of the patient's breast together with her infrared images which are transformed into temperature matrices. Through these matrices, the frontal and lateral mappings are performed by specified modules. This process generates an image and a text file with all the temperatures associated to the nodes of the surface mesh. The developed tool is also able to manage the use of a commercial mesh generation program and a computational fluid dynamics code, the FLUENT, in order to validate the technique by the use of a parametric analysis. In these analyses, the tumor may have several geometric shapes and different locations within the breast.

Computational method for aid in the diagnosis of sixth optic nerve palsy through digital videos.

The sixth cranial nerve, also known as the abducens nerve, is responsible for controlling the movements of the lateral rectus muscle. Palsies on the sixth nerve prevent some muscles that control eye movements from proper functioning, causing headaches, migraines, blurred vision, vertigo, and double vision. Hence, such palsy should be diagnosed in the early stages to treat it without leaving any sequela. The usual methods for diagnosing the sixth nerve palsy are invasive or depend on expensive equipment, and computer-based methods designed specifically to diagnose the aforementioned palsy were not found until the publication of this work. Therefore, a low-cost, non-invasive method can support or guide the ophthalmologist's diagnosis. In this context, this work presents a computational methodology to aid in diagnosing the sixth nerve palsy using videos to assist ophthalmologists in the diagnostic process, serving as a second opinion. The proposed method uses convolutional neural networks and image processing techniques to track both eyes' movement trajectory during the video. With this trajectory, it is possible to calculate the average velocity (AV) in which each eye moves. Since it is known that paretic eyes move slower than healthy eyes, comparing the AV of both eyes can determine if the eye is healthy or paretic. The results obtained with the proposed method showed that paretic eyes move at least 19.65% slower than healthy ones. This threshold, along with the AV of the movement of the eyes, can help ophthalmologists in their analysis. The proposed method reached 92.64% accuracy in diagnosing the sixth optic nerve palsy (SONP), with a Kappa index of 0.925, which highlights the reliability of the results and gives favorable perspectives for further clinical application.

Automatic method for classifying COVID-19 patients based on chest X-ray images, using deep features and PSO-optimized XGBoost.

The COVID-19 pandemic, which originated in December 2019 in the city of Wuhan, China, continues to have a devastating effect on the health and well-being of the global population. Currently, approximately 8.8 million people have already been infected and more than 465,740 people have died worldwide. An important step in combating COVID-19 is the screening of infected patients using chest X-ray (CXR) images. However, this task is extremely time-consuming and prone to variability among specialists owing to its heterogeneity. Therefore, the present study aims to assist specialists in identifying COVID-19 patients from their chest radiographs, using automated computational techniques. The proposed method has four main steps: (1) the acquisition of the dataset, from two public databases; (2) the standardization of images through preprocessing; (3) the extraction of features using a deep features-based approach implemented through the networks VGG19, Inception-v3, and ResNet50; (4) the classifying of images into COVID-19 groups, using eXtreme Gradient Boosting (XGBoost) optimized by particle swarm optimization (PSO). In the best-case scenario, the proposed method achieved an accuracy of 98.71%, a precision of 98.89%, a recall of 99.63%, and an F1-score of 99.25%. In our study, we demonstrated that the problem of classifying CXR images of patients under COVID-19 and non-COVID-19 conditions can be solved efficiently by combining a deep features-based approach with a robust classifier (XGBoost) optimized by an evolutionary algorithm (PSO). The proposed method offers considerable advantages for clinicians seeking to tackle the current COVID-19 pandemic.

Classification of malignant and benign lung nodules using taxonomic diversity index and phylogenetic distance.

Lung cancer presents the highest cause of death among patients around the world, in addition of being one of the smallest survival rates after diagnosis. Therefore, this study proposes a methodology for diagnosis of lung nodules in benign and malignant tumors based on image processing and pattern recognition techniques. Mean phylogenetic distance (MPD) and taxonomic diversity index (Δ) were used as texture descriptors. Finally, the genetic algorithm in conjunction with the support vector machine were applied to select the best training model. The proposed methodology was tested on computed tomography (CT) images from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), with the best sensitivity of 93.42%, specificity of 91.21%, accuracy of 91.81%, and area under the ROC curve of 0.94. The results demonstrate the promising performance of texture extraction techniques using mean phylogenetic distance and taxonomic diversity index combined with phylogenetic trees. Graphical Abstract Stages of the proposed methodology.

3D shape analysis to reduce false positives for lung nodule detection systems.

Using images from the Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), we developed a methodology for classifying lung nodules. The proposed methodology uses image processing and pattern recognition techniques. To classify volumes of interest into nodules and non-nodules, we used shape measurements only, analyzing their shape using shape diagrams, proportion measurements, and a cylinder-based analysis. In addition, we use the support vector machine classifier. To test the proposed methodology, it was applied to 833 images from the LIDC-IDRI database, and cross-validation with k-fold, where [Formula: see text], was used to validate the results. The proposed methodology for the classification of nodules and non-nodules achieved a mean accuracy of 95.33 %. Lung cancer causes more deaths than any other cancer worldwide. Therefore, precocious detection allows for faster therapeutic intervention and a more favorable prognosis for the patient. Our proposed methodology contributes to the classification of lung nodules and should help in the diagnosis of lung cancer.

Computer-aided diagnosis system for lung nodules based on computed tomography using shape analysis, a genetic algorithm, and SVM.

Lung cancer is the major cause of death among patients with cancer worldwide. This work is intended to develop a methodology for the diagnosis of lung nodules using images from the Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The proposed methodology uses image processing and pattern recognition techniques. To differentiate the patterns of malignant and benign forms, we used a Minkowski functional, distance measures, representation of the vector of points measures, triangulation measures, and Feret diameters. Finally, we applied a genetic algorithm to select the best model and a support vector machine for classification. In the test stage, we applied the proposed methodology to 1405 (394 malignant and 1011 benign) nodules from the LIDC-IDRI database. The proposed methodology shows promising results for diagnosis of malignant and benign forms, achieving accuracy of 93.19 %, sensitivity of 92.75 %, and specificity of 93.33 %. The results are promising and demonstrate a good rate of correct detections using the shape features. Because early detection allows faster therapeutic intervention, and thus a more favorable prognosis for the patient, herein we propose a methodology that contributes to the area.

Detection of masses based on asymmetric regions of digital bilateral mammograms using spatial description with variogram and cross-variogram functions.

A mammogram is an examination of the breast intended to prevent and diagnose breast cancer. In this work we propose a methodology for detecting masses by determining certain asymmetric regions between pairs of mammograms of the left and the right breast. The asymmetric regions are detected by means of structural variations between corresponding regions, defined by a spatial descriptor called cross-variogram function. After determining the asymmetric regions of a pair of images, the variogram function is applied to each asymmetric region separately, for classification as either mass or non-mass. The first stage of the methodology consists in preprocessing the images to make them adequate for registration. The following step performs the bilateral registration of pairs of left and right breasts. Pairs of corresponding regions are listed and their variations are measured by means of the cross-variogram spatial descriptor. Next, a model is created to train a Support Vector Machine (SVM) using the values of the cross-variogram function of each pair of windows as features. The pairs of breasts containing lesions are classified as asymmetric regions; the remaining ones are classified as symmetric regions. From the asymmetric regions, features are extracted from the variogram function to be used as tissue texture descriptors. The regions containing masses are classified as mass regions, and the other ones as non-mass regions. Stepwise linear discriminant analysis is used to select the most statistically significant features. Tests are performed with new cases for the final classification as either mass or non-mass by the trained SVM. The best results presented in the final classification were 96.38% of accuracy, 100% of sensitivity and 95.34% of specificity. The worst case presented 70.21% of accuracy, 100% of sensitivity and 67.56% of specificity. The average values for all tests were 90.26% of accuracy, 100% of sensitivity and 85.37% of specificity.

Detection of masses in mammogram images using CNN, geostatistic functions and SVM.

Breast cancer occurs with high frequency among the world's population and its effects impact the patients' perception of their own sexuality and their very personal image. This work presents a computational methodology that helps specialists detect breast masses in mammogram images. The first stage of the methodology aims to improve the mammogram image. This stage consists in removing objects outside the breast, reducing noise and highlighting the internal structures of the breast. Next, cellular neural networks are used to segment the regions that might contain masses. These regions have their shapes analyzed through shape descriptors (eccentricity, circularity, density, circular disproportion and circular density) and their textures analyzed through geostatistic functions (Ripley's K function and Moran's and Geary's indexes). Support vector machines are used to classify the candidate regions as masses or non-masses, with sensitivity of 80%, rates of 0.84 false positives per image and 0.2 false negatives per image, and an area under the ROC curve of 0.87.

Methodology for automatic detection of lung nodules in computerized tomography images.

Lung cancer is a disease with significant prevalence in several countries around the world. Its difficult treatment and rapid progression make the mortality rates among people affected by this illness to be very high. Aiming to offer a computational alternative for helping in detection of nodules, serving as a second opinion to the specialists, this work proposes a totally automatic methodology based on successive detection refining stages. The automated lung nodules detection scheme consists of six stages: thorax extraction, lung extraction, lung reconstruction, structures extraction, tubular structures elimination, and false positive reduction. In the thorax extraction stage all the artifacts external to the patient's body are discarded. Lung extraction stage is responsible for the identification of the lung parenchyma. The objective of the lung reconstruction stage is to prevent incorrect elimination of portions belonging to the parenchyma. Structures extraction stage comprises the selection of dense structures from inside the lung parenchyma. The next stage, tubular structures elimination eliminates a great part of the pulmonary trees. Finally, the false positive stage selects only structures with great probability to be nodule. Each of the several stages has very specific objectives in detection of particular cases of lung nodules, ensuring good matching rates even in difficult detection situations. We use 33 exams with diversified diagnosis and slices numbers for validating the methodology. We obtained a false positive per exam rate of 0.42 and false negative rate of 0.15. The total classification sensitivity obtained, measured out of the nodule candidates, was 84.84%. The specificity achieved was 96.15% and the total accuracy of the method was 95.21%.

Diagnosis of solitary lung nodules using the local form of Ripley's K function applied to three-dimensional CT data.

This paper analyzes the application of Ripley's K function to characterize lung nodules as malignant or benign in computerized tomography images. The proposed characterization method is based on a selection of measures from Ripley's K function to discriminate between benign and malignant nodules, using stepwise discriminant analysis. Based on the selected measures, a linear discriminant analysis procedure is performed once again in order to predict the classification of each nodule. To evaluate the ability of these features to discriminate the nodules, a set of tests was carried out using a sample of 39 pulmonary nodules, 29 benign and 10 malignant. A leave-one-out procedure was used to provide a less biased estimate of the linear discriminator's performance. The best setting of the analyzed function in the tested sample presented 70.0% of sensitivity but with 100.0% of specificity and 92.3% of accuracy. Thus, preliminary results of this approach are very promising regarding its contribution to the diagnosis of pulmonary nodules, but it still needs to be tested with larger series and associated to other quantitative imaging methods in order to improve global performance.