RESUMO
BACKGROUND AND OBJECTIVES: Pneumonia is a disease that affects the lungs, making breathing difficult. Nowadays, pneumonia is the disease that kills the most children under the age of five in the world, and if no action is taken, pneumonia is estimated to kill 11 million children by the year 2030. Knowing that rapid and accurate diagnosis of pneumonia is a significant factor in reducing mortality, acceleration, or automation of the diagnostic process is highly desirable. The use of computational methods can decrease specialists' workload and even offer a second opinion, increasing the number of accurate diagnostics. METHODS: This work proposes a method for constructing a specific convolutional neural network architecture to detect pneumonia and classify viral and bacterial types using Bayesian optimization from pre-trained networks. RESULTS: The results obtained are promising, in the order of 0.964 accuracy for pneumonia detection and 0.957 accuracy for pneumonia type classification. CONCLUSION: This research demonstrated the efficiency of CNN architecture estimation for detecting and diagnosing pneumonia using Bayesian optimization. The proposed network proved to have promising results, despite not using common preprocessing techniques such as histogram equalization and lung segmentation. This fact shows that the proposed method provides efficient and high-performance neural networks since image preprocessing is unnecessary.
Assuntos
Aprendizado Profundo , Pneumonia , Teorema de Bayes , Criança , Humanos , Pulmão/diagnóstico por imagem , Redes Neurais de Computação , Pneumonia/diagnóstico por imagemRESUMO
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.
RESUMO
At the end of 2019, the World Health Organization (WHO) reported pneumonia that started in Wuhan, China, as a global emergency problem. Researchers quickly advanced in research to try to understand this COVID-19 and sough solutions for the front-line professionals fighting this fatal disease. One of the tools to aid in the detection, diagnosis, treatment, and prevention of this disease is computed tomography (CT). CT images provide valuable information on how this new disease affects the lungs of patients. However, the analysis of these images is not trivial, especially when researchers are searching for quick solutions. Detecting and evaluating this disease can be tiring, time-consuming, and susceptible to errors. Thus, in this study, we aim to automatically segment infections caused by COVID19 and provide quantitative measures of these infections to specialists, thus serving as a support tool. We use a database of real clinical cases from Pedro Ernesto University Hospital of the State of Rio de Janeiro, Brazil. The method involves five steps: lung segmentation, segmentation and extraction of pulmonary vessels, infection segmentation, infection classification, and infection quantification. For the lung segmentation and infection segmentation tasks, we propose modifications to the traditional U-Net, including batch normalization, leaky ReLU, dropout, and residual block techniques, and name it as Residual U-Net. The proposed method yields an average Dice value of 77.1% and an average specificity of 99.76%. For quantification of infectious findings, the proposed method achieves results like that of specialists, and no measure presented a value of ρ < 0.05 in the paired t-test. The results demonstrate the potential of the proposed method as a tool to help medical professionals combat COVID-19. fight the COVID-19.
RESUMO
Strabismus is an eye disease that affects about 0.12%-9.86% of the population, which can cause irreversible sensory damage to vision and psychological problems. The most severe cases require surgical intervention, despite other less invasive techniques being available for a more conservative approach. As for surgeries, the treatment goal is to align the eyes to recover binocular vision, which demands knowledge, training, and experience. One of the leading causes of failure is human error during the measurement of deviation. Thus, this work proposes a new method based on the Decision Tree Regressor algorithms to assist in the surgical planning for horizontal strabismus to predict recoil and resection measures in the lateral and medial rectus muscles. In the presented method, two application approaches were taken, being in the form of multiple single target models, one procedure at a time, and the form of one multiple target model or all surgical procedures together. The method's efficiency is indicated by the average difference between the value indicated by the method and the physician's value. In our most accurate model, an average error of 0.66 mm was obtained for all surgical procedures, both for resection and recoil in the indication of the horizontal strabismus surgical planning. The results present the feasibility of using Decision Tree Regressor algorithms to perform the planning of strabismus surgeries, making it possible to predict correction values for surgical procedures based on medical data analysis and exceeding state-of-art.
Assuntos
Procedimentos Cirúrgicos Oftalmológicos , Estrabismo , Humanos , Músculos Oculomotores/cirurgia , Estudos Retrospectivos , Estrabismo/cirurgia , Resultado do Tratamento , Visão BinocularRESUMO
Dry eye syndrome is one of the most frequently reported eye diseases in ophthalmological practice. The diagnosis of this disease is a challenging task due to its multifactorial etiology. One of the most applied tests is the manual classification of tear film images captured with the Doane interferometer. The interference phenomena in these images can be characterized as texture patterns, which can be automatically classified into one of the following categories: strong fringes, coalescing strong fringes, fine fringes, coalescing fine fringes, and debris. This work presents a method for classifying tear film images based on texture analysis using phylogenetic diversity indexes and Ripley's K function. The proposed method consists of six main steps: acquisition of the image dataset; segmentation of the region of interest; feature extraction using phylogenetic diversity indexes and Ripley's K function; feature selection using Greedy Stepwise; classification using the algorithms Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), Multilayer Perceptron (MLP), Random Tree (RT) and Radial Basis Function Network (RBFNet); and (6) validation of results. The best result, using the RF classifier, we obtained classification rates higher than 99% of accuracy with 0.843% of standard deviation, 0.999 of the area under the Receiver Operating Characteristics (ROC) curve, 0.995 of Kappa and 0.996 of F-Measure. The experimental results demonstrate that the proposed method is promising and can potentially be used by experts to accurately diagnose dry eye syndrome in tear film images.
Assuntos
Síndromes do Olho Seco/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Interferometria/métodos , Lágrimas/diagnóstico por imagem , Adolescente , Adulto , Algoritmos , Síndromes do Olho Seco/fisiopatologia , Humanos , Pessoa de Meia-Idade , Máquina de Vetores de Suporte , Lágrimas/fisiologia , Adulto JovemRESUMO
Background and Objective Dry eye syndrome disease negatively impacts many people in various ways. Several tests are required to diagnose it for evaluating different physiological characteristics. One of the most applied tests for this is the manual classification of tear film images captured with Doane interferometer. Interferometry images can be categorized into five groups: debris, fine fringes, coalescing fine fringes, strong fringes, and coalescing strong fringes. Instability in the tear film creates the need for an automatic system to provide experts with diagnostic support. Therefore, the purpose of this study was to propose a method for automatic classification of the tear film lipid layer using phylogenetic diversity indexes for feature extraction and several classifiers. Methods The proposed method consisted of five main steps: (1) acquisition of VOPTICAL_GCU image dataset, (2) segmentation of the region of interest, (3) feature extraction using phylogenetic diversity indexes, (4) classification using the algorithms Support Vector Machines, Random Forest, Naive Bayes, Multilayer Perceptron, Random Tree, and RBFNetwork, and, (5) validation of results. Results The best result was obtained using Random Forest classifier, reaching an accuracy of over 97%, standard deviation of 0.51%, an area under the receiver operating characteristic curve of 0.99, a Kappa index of 0.96, and an F-Measure of 0.97. Conclusions The proposed method demonstrated that the tear film lipid layer classification problem can be resolved efficiently by using phylogenetic diversity indexes.