USAGE OF ARTIFICIAL NEURAL NETWORKS IN THE DIAGNOSIS OF KNEE JOINT DISORDERS

Konrad Witkowski

k.l.p.witkowski@gmail.com
SGH Warsaw School of Economics (Poland)
https://orcid.org/0009-0004-2916-8672

Mikołaj Wieczorek


Lublin University of Technology, Department of Electronics and Information Technology (Poland)
https://orcid.org/0000-0002-7879-9727

Abstract

Following article address the issue of automatic knee disorder diagnose with usage of neural networks. We proposed several hybrid neural net architectures which aim to successfully classify abnormality using MRI (magnetic resonance imaging) images acquired from publicly available dataset. To construct such combinations of models we used pretrained Alexnet, Resnet18 and Resnet34 downloaded from Torchvision. Experiments showed that for certain abnormalities our models can achieve up to 90% accuracy.


Keywords:

classification, MRI images, Resnet, Alexnet

Bien N. et al.: Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet. PLoS Med 15(11), 2018, e1002699 [http://doi.org/10.1371/journal.pmed.1002699].
DOI: https://doi.org/10.1371/journal.pmed.1002699   Google Scholar

He K., Zhang X., Ren S., Sun J.: Deep Residual Learning for Image Recognition. Computer Vision and Pattern Recognition 2015, arXiv:1512.03385.
DOI: https://doi.org/10.1109/CVPR.2016.90   Google Scholar

Krizhevsky A., Sutskever I., Hinton G. E.: ImageNet Classification with Deep Convolutional Neural Networks. F. Pereira, C. J. Burges, L. Bottou and K. Q. Weinberger: Advances in Neural Information Processing Systems 25 (NIPS 2012), 2012.
  Google Scholar

https://en.wikipedia.org/wiki/McNemar%27s_test
  Google Scholar

https://github.com/ahmedbesbes/mrnet
  Google Scholar

https://machinelearningmastery.com/mcnemars-test-for-machine-learning/
  Google Scholar

https://pytorch.org/vision/stable/models.html
  Google Scholar

https://stanfordmlgroup.github.io/competitions/mrnet/
  Google Scholar

https://www.mikulskibartosz.name/wilson-score-in-python-example/
  Google Scholar

Download


Published
2023-12-20

Cited by

Witkowski, K., & Wieczorek, M. (2023). USAGE OF ARTIFICIAL NEURAL NETWORKS IN THE DIAGNOSIS OF KNEE JOINT DISORDERS. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 13(4), 11–14. https://doi.org/10.35784/iapgos.5380

Authors

Konrad Witkowski 
k.l.p.witkowski@gmail.com
SGH Warsaw School of Economics Poland
https://orcid.org/0009-0004-2916-8672

Authors

Mikołaj Wieczorek 

Lublin University of Technology, Department of Electronics and Information Technology Poland
https://orcid.org/0000-0002-7879-9727

Statistics

Abstract views: 140
PDF downloads: 195