COVID-19 crisis

In the last few months, VARPA directed its research against COVID-19 by means of radiological image analysis and Artificial Intelligence. In this sense, the group presented to the Carlos III Health Institute its project "Artificial Intelligence vs COVID-19: Improvements in the detection, evaluation and personalized follow-up of the affected people" through the Professor Novoa Santos Foundation, in order to expose the development of a distributed web tool that allows managing heterogeneous data of patients, initially information from RT-PCR tests and radiological image tests and, through the use of deep learning techniques, allows improving the diagnosis of the COVID-19 disease, the estimation of its severity and the prediction of its evolution.

Moreover, making use of the COVID-19 web tool, more variables of interest will be incorporated to allow the follow-up and personalized treatment of the patient, since it will incorporate the knowledge acquired by means of a study at 9 months of the evolution of a cohort of patients for convariable correlation, both clinical and of serology, essential as it shows us the recent clinical literature, as well as of derived pathologies what will allow to know in detail the behavior of the infection in the patients for typology and previous characteristics.

This project was positively evaluated by the ISCIII and is selected to receive funding from the GAIN for a value of just over 250,000 euros. Moreover, as a result of this work, the group received official recognition as one of the outstanding groups in Galicia in the fight against COVID-19, in an official act of the Real Academia Gallega das Ciencias (Galician Royal Academy of Sciences). On the other hand, as an example of the group's commitment to its duty of public service in the transfer of knowledge, the current developments of automatic systems to support the diagnosis of COVID-19 are being implemented in the CHUAC hospital as part of a pilot project with which it had strengthened the response capacity of the national health system in the management of the pandemic. This project was positively evaluated by the ISCIII and is selected to receive funding from the GAIN for a value of just over 250,000 euros. Moreover, as a result of this work, the group received official recognition as one of the outstanding groups in Galicia in the fight against COVID-19 , in an official act of the Real Academia Gallega das Ciencias (Galician Royal Academy of Sciences). On the other hand, as an example of the group's commitment to its duty of public service in the transfer of knowledge, the current developments of automatic systems to support the diagnosis of COVID-19 are being implemented in the CHUAC hospital as part of a pilot project with which it had strengthened the response capacity of the national health system in the management of the pandemic.

Collaborations

Main publications

• J. de Moura, L. Ramos, P. L. Vidal, M. Cruz, L. Abeilairas, E. Castro, J. Novo, M. Ortega, "Deep convolutional approaches for the analysis of Covid-19 using chest X-Ray images from portable devices", IEEE Access, 8, 195594-195607, IEEE, ISSN: 2169-3536, DOI 10.1109/ACCESS.2020.3033762, 2020.
  
• P. L. Vidal, J. de Moura, J. Novo, M. Ortega, "Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19", Expert Systems with Applications, 173, 114677, Elsevier, ISSN: 0957-4174, DOI 10.1016/j.eswa.2021.114677, 2021.
  
• J. de Moura, J. Novo, M. Ortega, "Fully automatic deep convolutional approaches for the analysis of COVID-19 using chest X-ray images", Applied Soft Computing , 2021. (pending of acceptation).
  
• D. I. Morís, J. de Moura, J. Novo, M. Ortega, "Cycle Generative Adversarial Network Approaches to Produce Novel Portable Chest X-rays Images for COVID-19 Diagnosis ", 2021 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP'21, 06/06/2021-11/06/2021, Toronto, Canada, 2021. (pending of publication).
  
• P. L. Vidal, J. de Moura, L. Ramos, J. Novo, M. Ortega, "Study on relevant features in COVID-19 PCR tests", Proceedings, 54 (1), 143-145, MDPI, ISSN: 2504-3900, ISBN: 978-3-03943-492-3, III XoveTIC 2020, 08/10/2020-09/10/2020, A Coruña, 2020.
  
• J. de Moura, L. Ramos, P. L. Vidal, J. Novo, M. Ortega, "Analysis of Separability of COVID-19 and Pneumonia in Chest X-Ray Images by means of Convolutional Neural Networks", Proceedings, 54 (1), 101-103, MDPI, ISSN: 2504-3900, ISBN: 978-3-03943-492-3, III XoveTIC 2020, 08/10/2020-09/10/2020, A Coruña, 2020.
  

Funding