Lung disease detection using feature extraction and extreme learning machine

Ramalho, Geraldo Luis Bezerra; Filho, Pedro Pedrosa Rebouças; Medeiros, Fátima N. S. de; Cortez, Paulo César

doi:10.1590/rbeb.2014.019

Cited by 40 publications

(28 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os recursos decorrentes de cálculos de matrizes de co-ocorrência (GLCM -Gray Level Cooccurrence Matrix) são definidos no lugar de uma imagem em determinado sentido. Estas matrizes consistem em uma contagem da quantificação de combinações diferentes de níveis de cinza e são fundamentais, pois elas são a base para a preparação de várias medidas estatísticas conhecidas como Descritores Haralick [30,31,32].…”

Section: Extração De Característicasunclassified

Classificaçâo automatica do tipo de ferro fundido utilizando reconhecimento de padrões em imagens de microscopia

et al. 2017

Self Cite

View full text Add to dashboard Cite

RESUMOOs ferros fundidos possuem uma microestrutura, na qual, o formato da grafita presente tem direta influência na classificação entre os diversos tipos deste material. A classificação é feita, tradicionalmente, a partir da análise visual realizada por um especialista através do auxílio de um microscópio ótico. O presente trabalho propõe a utilização da Inteligência Computacional Aplicada em conjunto com extratores de informações em imagens de metalografia. A finalidade é auxiliar profissionais da área das Ciências dos Materiais na classificação de ferros fundidos de maneira automática e reduzir o tempo de classificação, restringindo o máximo possível as falhas presentes durante a classificação. Foram realizadas duas etapas para a análise. Na primeira foram consideradas as grafitas separadamente. Em uma segunda etapa, a imagem completa foi analisada considerando todas as grafitas extraídas da mesma, em que o tipo de objeto com maior incidência na análise seria o reconhecimento adotado para toda a amostra. Em ambas as etapas o classificador Support Vector Machine obteve os melhores resultados no reconhecimento do tipo de ferro fundido, com resultados próximos a 100%, e com redução média do tempo de classificação em 92%. Tanto os resultados como o tempo das classificações são comparados com a análise do especialista, como também aos resultados obtidos em classificações do ferro fundido que utilizam uma abordagem com redes neurais e uma classificação supervisionada utilizando apenas os descritores de forma. A partir dos resultados apresentados, conclui-se que a abordagem é promissora podendo incorporar softwares comerciais para auxiliar especialistas da área. Palavras-chave:Ferro fundido, Processamento Digital de Imagens, Reconhecimento de Padrões, Inteligên-cia Computacional Aplicada. ABSTRACTThe cast iron has a microstructure in which the shape of the contained graphite has direct influence in the classification between the several types of this material. The classification is usually made through a visual analysis performed by a specialist using an optical microscope. This work proposes the use of Applied Computational Intelligence in conjunction with extractors of information in metallographic images. The purpose is to assist professionals in the field of Materials Science in the classification of cast iron automatically and reduce the time for classification, restricting as much as possible the faults presented during classification. Two steps were performed for the analysis. In the first one we considered the graphites separately. In a second step, we analyzed the complete image considering all the graphite extracted from it, in which the type of object with greater incidence in the analysis would be the recognition adopted for the whole sample. In both steps, the classifier Support Vector Machine obtained the best results in the recognition of the type of cast iron, with results close to 100%, with a mean reduction of the classification time by 92%. Both the results and the time of the classifications are ...

show abstract

Section: Extração De Característicasunclassified

Classificaçâo automatica do tipo de ferro fundido utilizando reconhecimento de padrões em imagens de microscopia

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lung disease are disorders affecting the lungs which include asthma, chronic obstructive pulmonary (COPD) disease, tuberculosis, influenza, lung cancer, pneumonia and other breathing problems. Worldwide population are affected by huge number of related lung diseases [1] and respiratory tract infections are the top cause of death and disability [2 World Health Organization estimates that by 2030, lung diseases such as Chronic Obstructive Pulmonary Disease will be one of the leading cause of mortality. Timely treatment and to prevent further death, accurate and timely diagnosis of pulmonary disease is needed [1].…”

Section: Introductionmentioning

confidence: 99%

“…Worldwide population are affected by huge number of related lung diseases [1] and respiratory tract infections are the top cause of death and disability [2 World Health Organization estimates that by 2030, lung diseases such as Chronic Obstructive Pulmonary Disease will be one of the leading cause of mortality. Timely treatment and to prevent further death, accurate and timely diagnosis of pulmonary disease is needed [1]. Hence, to cure the disease, its detection in its earlier phase is essential [3].…”

Section: Introductionmentioning

confidence: 99%

“…al, a new approach was proposed for classification of lung illnesses. CXR images were segmented using Adaptive Crisp Active Contours Models(ACACM) and a novel method for lung illness identification using feature extraction for segmented lung structure [1]. In the study of Abiyev and Ma'aitah, they demonstrated that classifying chest pathologies in CXR utilizing conventional and deep learning strategy is viable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

U-Net Based Lung Image Segmentation for Lung Disease Detection

2019

IJRTE

View full text Add to dashboard Cite

Lung diseases are becoming a worldwide health problem. World Health Organization estimates that by 2030, lung diseases such as Chronic Obstructive Pulmonary Disease will be one of the leading cause of mortality. Accurate and timely detection of lung diseases may prevent further death. It is therefore vital that its early detection will lead to treatment and prevention of mortality among patients. However, the scarcity of expert or well-trained radiologists reading CXR images might delay the timely diagnosis of lung diseases especially in rural areas where the scarcity is felt. In order to aid radiologist in reading CXR images, a computer aided tool is proposed for faster and more accurate reading of CXR images. To prepare the image for processing, it need to be segmented to make it easier for the computer to understand. The goal of image segmentation in medical field is to extract the region of interest in the organ. This study is focused on developing a model that will segment the lung from CXR images. Using U-Net architecture based semantic segmentation, the researchers were able to develop and train a model using a set of 562 CXR images and lung mask images, 70 percent of the images were used for training and 30 percent for testing. The developed model achieved a final training accuracy of 97.55 percent and validation accuracy of 97.37 percent. Validation loss and training loss are also low which indicates that the model can segment lung from CXR images with minimal error. The developed model can then be used in classifying lung diseases by focusing on the segmented image rather than focusing on the entire CXR image.

show abstract

“…Several diseases that affect the world population are related to the lungs, for example: asthma (Kwan et al, 2015;Wisniewski and Zielinski, 2015), bronchiectasis (Arunkumar, 2012) and chronic obstructive pulmonary disease (COPD) (Mieloszyk et al, 2014;Ramalho et al, 2014;Spina et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Novel and powerful 3D adaptive crisp active contour method applied in the segmentation of CT lung images

Filho

Cortez

Barros

et al. 2017

Medical Image Analysis

Self Cite

102

View full text Add to dashboard Cite

The World Health Organization estimates that 300 million people have asthma, 210 million people have Chronic Obstructive Pulmonary Disease (COPD), and, according to WHO, COPD will become the third major cause of death worldwide in 2030. Computational Vision systems are commonly used in pulmonology to address the task of image segmentation, which is essential for accurate medical diagnoses. Segmentation defines the regions of the lungs in CT images of the thorax that must be further analyzed by the system or by a specialist physician. This work proposes a novel and powerful technique named 3D Adaptive Crisp Active Contour Method (3D ACACM) for the segmentation of CT lung images. The method starts with a sphere within the lung to be segmented that is deformed by forces acting on it towards the lung borders. This process is performed iteratively in order to minimize an energy function associated with the 3D deformable model used. In the experimental assessment, the 3D ACACM is compared against three approaches commonly used in this field: the automatic 3D Region Growing, the level-set algorithm based on coherent propagation and the semi-automatic segmentation by an expert using the 3D OsiriX toolbox. When applied to 40 CT scans of the chest the 3D ACACM had an average F-measure of 99.22%, revealing its superiority and competency to segment lungs in CT images.

show abstract

Lung disease detection using feature extraction and extreme learning machine

Cited by 40 publications

References 13 publications

Classificaçâo automatica do tipo de ferro fundido utilizando reconhecimento de padrões em imagens de microscopia

Classificaçâo automatica do tipo de ferro fundido utilizando reconhecimento de padrões em imagens de microscopia

U-Net Based Lung Image Segmentation for Lung Disease Detection

Novel and powerful 3D adaptive crisp active contour method applied in the segmentation of CT lung images

Contact Info

Product

Resources

About