New patch-based strategy for COVID-19 automatic identification using chest x-ray images.

Autor: Portal-Diaz JA; Informatic Office, Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba., Lovelle-Enríquez O; Radiology Department, Hospital Comandante Manuel Fajardo, Santa Clara, Cuba., Perez-Diaz M; Automatic Department, Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba., Lopez-Cabrera JD; Universidad Central Marta Abreu de Las Villas, Informatic Research Center, Santa Clara, Cuba., Reyes-Cardoso O; Universidad de Ciencias Médicas de Villa Clara, Roberto Fleites Policlinics, Santa Clara, Cuba., Orozco-Morales R; Automatic Department, Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba.
Jazyk: angličtina
Zdroj: Health and technology [Health Technol (Berl)] 2022; Vol. 12 (6), pp. 1117-1132. Date of Electronic Publication: 2022 Nov 10.
DOI: 10.1007/s12553-022-00704-4
Abstrakt: Purpose: The development of a robust model for automatic identification of COVID-19 based on chest x-rays has been a widely addressed topic over the last couple of years; however, the scarcity of good quality images sets, and their limited size, have proven to be an important obstacle to obtain reliable models. In fact, models proposed so far have suffered from over-fitting erroneous features instead of learning lung features, a phenomenon known as shortcut learning. In this research, a new image classification methodology is proposed that attempts to mitigate this problem.
Methods: To this end, annotation by expert radiologists of a set of images was performed. The lung region was then segmented and a new classification strategy based on a patch partitioning that improves the resolution of the convolution neural network is proposed. In addition, a set of native images, used as an external evaluation set, is released.
Results: The best results were obtained for the 6-patch splitting variant with 0.887 accuracy, 0.85 recall and 0.848 F1score on the external validation set.
Conclusion: The results show that the proposed new strategy maintains similar values between internal and external validation, which gives our model generalization power, making it available for use in hospital settings.
Supplementary Information: The online version contains supplementary material available at 10.1007/s12553-022-00704-4.
Competing Interests: Conflict of interestThe authors declare that there is no conflict of interest.
(© The Author(s) under exclusive licence to International Union for Physical and Engineering Sciences in Medicine (IUPESM) 2022, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.)
Databáze: MEDLINE
Externí odkaz: