Open AccessPulmonary Disease Pattern Recognition on X-Ray Radiography Image Using Artificial Neural Network (ANN) Method
Author(s) -
Nur Qodariyah Fitriyah,
Lia Dessy Kurniawati,
Endah Purwanti,
Setia Astuti
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1505/1/012065
Subject(s) - artificial intelligence , pattern recognition (psychology) , artificial neural network , adaptive histogram equalization , histogram equalization , computer science , backpropagation , feature (linguistics) , feature extraction , radiography , histogram , gray level , computer vision , medicine , radiology , image (mathematics) , linguistics , philosophy
This research aims to recognize the pattern of pulmonary disease on x-ray radiography image using artificial neural network (ANN) method. The images, which were used such as images of healthy pulmonary, pulmonary tuberculosis, and pulmonary tumour. Pattern recognition was using an extraction feature of GLCM (Gray Level Co-occurrence Matrix) and back propagation method. Before being identified, the images were processed by median filter and adaptive histogram equalization. The GLCM features that used were homogeneity, energy, contrast, variance and correlation. The parameters were learning rate and hidden layer. Learning rate was 0.3 and hidden layer was 25. Back propagation training showed 100% accuracy, which all of 44 images were used had been successfully identified. From the result, the healthy pulmonary showed 60% accuracy, 83.3% for pulmonary tuberculosis and 100% for pulmonary tumor. Hence, the overall result showed 81.25% accuracy, which 13 of 16 images had been successfully identified. From these result, extraction feature of GLCM using back propagation method was capable to recognize the pattern of pulmonary disease. However, due to narrow range of the feature, this application may not be used optimally for comparing features in every category of images. Therefore, the further research is needed to determine the best features and parameters of training back propagation.