TY - GEN
T1 - A Proposal for the Deep Unsupervised Identification of Relevant Areas in X-Rays for Covid Detection
AU - Martinez, Jose
AU - Nicolis, Orietta
AU - Caro, Luis
AU - Peralta, Billy
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Artificial vision
KW - COVID detection
KW - Object detection
UR - http://www.scopus.com/inward/record.url?scp=85127003657&partnerID=8YFLogxK
U2 - 10.1109/CHILECON54041.2021.9703054
DO - 10.1109/CHILECON54041.2021.9703054
M3 - Conference contribution
AN - SCOPUS:85127003657
T3 - 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
BT - 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
Y2 - 6 December 2021 through 9 December 2021
ER -
