Open Science Slovenia
New in RUL
Musculoskeletal images classification for detection of fractures using transfer learning
PDF - Presentation file,
The classification of the musculoskeletal images can be very challenging, mostly when it is being done in the emergency room, where a decision must be made rapidly. The computer vision domain has gained increasing attention in recent years, due to its achievements in image classification. The convolutional neural network (CNN) is one of the latest computer vision algorithms that achieved state-of-the-art results. A CNN requires an enormous number of images to be adequately trained, and these are always scarce in the medical field. Transfer learning is a technique that is being used to train the CNN by using fewer images. In this paper, we study the appropriate method to classify musculoskeletal images by transfer learning and by training from scratch. We applied six state-of-the-art architectures and compared their performance with transfer learning and with a network trained from scratch. From our results, transfer learning did increase the model performance significantly, and, additionally, it made the model less prone to overfitting.
1.01 - Original Scientific Article
EF - Faculty of Economics
Number of pages:
Vol. 6, iss 11 (art. 127)
ISSN on article:
This work is available under this license:
Creative Commons Attribution 4.0 International
Voting is allowed only to
Cite this work
Record is a part of a journal
Journal of imaging
Document is financed by a project
ARRS - Agencija za raziskovalno dejavnost Republike Slovenije (ARRS)
Digitalizacija kot gonilo trajnostnega razvoja posameznika, organizacij in družbe
FCT - Fundação para a Ciência e a Tecnologia, I.P.
Similar works from RUL:
Similar works from other Slovenian collections:
You have to
to leave a comment.
0 - 0 / 0
There are no comments!