Network for subclinical prognostication of COVID 19 Patients from data of thoracic roentgenogram: A feasible alternative screening technology

Background and Study Aim: COVID 19 is the terminology driving peoples life in the year 2020 without a supportive globally high mortality rate. Coronavirus lead pandemic is a new found disease with no gold standard diagnostic and therapeutic guideline across the globe. Amidst this scenario our aim is to develop a prediction model that makes mass screening easy on par with reducing strain on hospitals diagnostic facility and doctors alike. For this prediction model, a neural network based on Chest X-ray images has been developed. Alongside the aim is also to generate a case record form that would include prediction model result along with few other subclinical factors for generating disease identification. Once found positive then only it will proceed to RT-PCR for final validation. The objective was to provide a cheap alternative to RT-PCR for mass screening and to reduced burden on diagnostic facility by keeping RT-PCR only for final confirmation. Methods: Datasets of chest X-ray images gathered from across the globe has been used to test and train the network after proper dataset curing and augmentation. Results: The final neural network-based prediction model showed an accuracy of 81% with sensitivity of 82% and specificity of 90%. The AUC score obtained is 93.7%. Discussion and Conclusion: The above results based on the existing datasets showcase our model capability to successfully distinguish patients based on Chest X-ray (a non-invasive tool) and along with the designed case record form it can significantly contribute in increasing hospitals monitoring and health care capability.

Download Full-text

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

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v5i4.3153 ◽

2021 ◽

Vol 5 (4) ◽

pp. 747-759

Author(s):

Bambang Pilu Hartato

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Dense Layer ◽

Rt Pcr ◽

Testing Methods ◽

Antibody Testing ◽

X Ray ◽

Layer 2 ◽

Chest X Ray ◽

Alternative Testing

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

Novel Multi-Modal Throat Inflammation and Chest Radiography based Early-Diagnosis and Mass-Screening of COVID-19

The Open Biomedical Engineering Journal ◽

10.2174/1874120702115010226 ◽

2021 ◽

Vol 15 (1) ◽

pp. 226-235

Author(s):

Ojas A. Ramwala ◽

Poojan Dalal ◽

Parima Parikh ◽

Upena Dalal ◽

Mita C. Paunwala ◽

...

Keyword(s):

Mass Screening ◽

Chest Radiography ◽

Fine Tuning ◽

Rt Pcr ◽

Close Collaboration ◽

X Ray ◽

Non Invasive ◽

Life Threatening ◽

Chest X Ray ◽

Future Direction

Background: The upsurge of COVID-19 has received significant international contemplation considering its life-threatening ramifications. To ensure that the susceptible patients can be quarantined to control the spread of the disease during the incubation period of the coronavirus, it becomes imperative to automatically and non-invasively mass screen patients. The diagnosis using RT-PCR is arduous and time-consuming. Currently, the non-invasive mass screening of susceptible cases is being performed by utilizing the thermal screening technique. However, with the consumption of paracetamol, the symptoms of fever can be suppressed. Methods: A novel multi-modal approach has been proposed. Throat inflammation-based mass screening and early prediction followed by Chest X-Ray based diagnosis have been proposed. Depth-wise separable convolutions have been utilized by fine-tuning Xception Net and Mobile Net architectures. NADAM optimizer has been leveraged to promote faster convergence. Results: The proposed method achieved 91% accuracy on the throat inflammation identification task and 96% accuracy on chest radiography conducted on the dataset. Conclusion: Evaluation of the proposed method indicates promising results and henceforth validates its clinical reliability. The future direction could be working on a larger dataset in close collaboration with the medical fraternity.

Download Full-text