About: The Covid-19 first occurs in Wuhan, China in December 2019. After that the virus spread all around the world and at the time of writing this paper the total number of confirmed cases are above 4 million with over 297000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is twofold. First, a quantitative analysis where we evaluate 12 off-the-shelf convolutional neural networks (CNNs) and proposed a simple CNN architecture with less parameters and computational power that can perform as good as Xception and DenseNet architectures if trained on small dataset of chest X-ray images. Secondly, a qualitative investigation to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed most to the decision of CNNs back to the original image to visualize the most discriminating regions in the input image. Chest X-ray images used in this work are coming from multiple sources which comprises of 154 confirmed COVID-19 images and over 5000 X-rays of normal, bacterial and other viral (non-COVID-19) infections. We conclude that CNN decisions should not be taken into consideration until radiologist/clinicians can visually inspect the region(s) of the input image used by CNNs that lead to its prediction. This work also reports the necessity of segmenting the region of interest (ROI) to prevent CNNs building their decision from features outside ROI.   Goto Sponge  NotDistinct  Permalink

An Entity of Type : fabio:Abstract, within Data Space : covidontheweb.inria.fr associated with source document(s)

AttributesValues
type
value
  • The Covid-19 first occurs in Wuhan, China in December 2019. After that the virus spread all around the world and at the time of writing this paper the total number of confirmed cases are above 4 million with over 297000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is twofold. First, a quantitative analysis where we evaluate 12 off-the-shelf convolutional neural networks (CNNs) and proposed a simple CNN architecture with less parameters and computational power that can perform as good as Xception and DenseNet architectures if trained on small dataset of chest X-ray images. Secondly, a qualitative investigation to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed most to the decision of CNNs back to the original image to visualize the most discriminating regions in the input image. Chest X-ray images used in this work are coming from multiple sources which comprises of 154 confirmed COVID-19 images and over 5000 X-rays of normal, bacterial and other viral (non-COVID-19) infections. We conclude that CNN decisions should not be taken into consideration until radiologist/clinicians can visually inspect the region(s) of the input image used by CNNs that lead to its prediction. This work also reports the necessity of segmenting the region of interest (ROI) to prevent CNNs building their decision from features outside ROI.
subject
  • Virology
  • Machine learning
  • Medical physics
  • Recipients of the Four Freedoms Award
part of
is abstract of
is hasSource of
Faceted Search & Find service v1.13.91 as of Mar 24 2020


Alternative Linked Data Documents: Sponger | ODE     Content Formats:       RDF       ODATA       Microdata      About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data]
OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software