Penerapan Convolutional Neural Network pada Citra Rontgen Paru-Paru untuk Deteksi SARS-CoV-2

COVID-19 was officially declared as a pandemic by the WHO on March 11, 2020. For COVID-19, the testing methods commonly used are the Antibody Testing and RT-PCR Testing. Both methods are considered to be the most effective in determining whether a person has been suffered from COVID-19 or not. However, alternative testing methods need to be tried. One of them is using the Convolutional Neural Network. This study aims to measure the performance of CNN in classifying x-ray image of a person’s chest to determine whether the person is suffered from COVID-19 or not. The CNN model that was built consists of 1 convolutional 2D layer, 2 activation layers, 1 maxpooling layer, 1 dropout layer, 1 flatten layer, and 1 dense layer. Meanwhile, the chest x-ray image dataset used is the COVID-19 Radiography Database. This dataset consists of 3 classes, i.e. COVID-19 class, NORMAL class, and VIRAL_PNEUMONIA. The experiments consisted of 4 scenarios and were carried out using Google Colab. Based on the experiments, the CNN model can achieve an accuracy of 98.69%, a sensitivity of 97.71%, and a specificity of 98.90%. Thus, CNN has a very good performance to classify the disease based on a person’s chest x-ray.

Download Full-text

Predicting COVID-19 pneumonia severity on chest X-ray with convolutional neural network: A retrospective study

Indian Journal of Medical Sciences ◽

10.25259/ijms_349_2020 ◽

2020 ◽

Vol 72 ◽

pp. 132-140

Author(s):

Vishal Rao ◽

M. S. Priyanka ◽

A. Lakshmi ◽

A. G. J. Faheema ◽

Alex Thomas ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Decision Fusion ◽

Rt Pcr ◽

X Ray ◽

Detection Techniques ◽

Screening Model ◽

Chest X Ray ◽

Output Information

Objectives: Radiological lung changes in COVID-19 infections present a noteworthy avenue to develop chest X-ray (CXR) -based testing models to support existing rapid detection techniques. The purpose of this study is to evaluate the accuracy of artificial intelligence (AI) -based screening model employing deep convolutional neural network for lung involvement. Material and Methods: An AI-based screening model was developed with state-of-the-art neural networks using Indian data sets from COVID-19 positive patients by authors of CAIR, DRDO, in collaboration with the other authors. Our dataset was comprised of 1324 COVID-19, 1108 Normal, and 1344 Pneumonia CXR images. Transfer learning was carried out on Indian dataset using popular deep neural networks, which includes DenseNet, ResNet50, and ResNet18 network architectures to classify CXRs into three categories. The model was retrospectively used to test CXRs from reverse transcriptase-polymerase chain reaction (RT-PCR) proven COVID-19 patients to test positive predictive value and accuracy. Results: A total of 460 RT-PCR positive hospitalized patients CXRs in various stages of disease involvement were retrospectively analyzed. There were 248 males (53.92%) and 212 females (46.08%) in the cohort, with a mean age of 50.1 years (range 12–89 years). The commonly observed alterations included lung consolidations, ground-glass opacities, and reticular–nodular opacities. Bilateral involvement was more common compared to unilateral involvement. Of the 460 CXRs analyzed, the model reported 445 CXRs as COVID -19 with an accuracy of 96.73%. Conclusion: Our model, based on a two-level classification decision fusion and output information computation, makes it a robust, accurate and reproducible tool. Based on the initial promising results, our application can be used for mass screening.

Download Full-text