A Proposal for the Deep Unsupervised Identification of Relevant Areas in X-Rays for Covid Detection

Jose Martinez, Orietta Nicolis, Luis Caro, Billy Peralta

Resultado de la investigación: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

Resumen

Since the beginning of 2020, the diagnosis of the COVID-19 virus has been a major problem that has affected the lives of millions of people around the world. The detection time for COVID-19 with a standard detection method ranges from approximately 1 to 5 days. An efficient and fast way to detect the presence of both the COVID-19 virus is through the use of artificial intelligence (AI) techniques applied to images obtained by lung radiography. Typically, AI algorithms to detect COVID-19 consider the whole picture. However, there may be parts that affect the performance of the classifier. Furthermore, these algorithms do not indicate which is the most relevant area of this disease. In this work, we propose a deep learning approach to detect the presence of COVID-19 in lung images by recognizing the most relevant areas affected by the virus without considering human supervision. In the experiment, we considered different proposals, where the best one obtained an 88% reduction of the logit loss with respect to the baseline based on random regions near the center of the image.

Idioma originalInglés
Título de la publicación alojada2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9781665408738
DOI
EstadoPublicada - 2021
Evento2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021 - Virtual, Online, Chile
Duración: 6 dic. 20219 dic. 2021

Serie de la publicación

Nombre2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021

Conferencia

Conferencia2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
País/TerritorioChile
CiudadVirtual, Online
Período6/12/219/12/21

Áreas temáticas de ASJC Scopus

  • Inteligencia artificial
  • Redes de ordenadores y comunicaciones
  • Hardware y arquitectura
  • Sistemas de información
  • Gestión y sistemas de información
  • Ingeniería energética y tecnologías de la energía
  • Ingeniería eléctrica y electrónica
  • Control y optimización

Huella

Profundice en los temas de investigación de 'A Proposal for the Deep Unsupervised Identification of Relevant Areas in X-Rays for Covid Detection'. En conjunto forman una huella única.

Citar esto