A3 Book section, Chapters in research books
Validation of Knee KL-classifying Deep Neural Network with Finnish Patient Data (2022)

Niinimäki, E., Paloneva, J., Pölönen, I., Heinonen, A., & Äyrämö, S. (2022). Validation of Knee KL-classifying Deep Neural Network with Finnish Patient Data. In T. T. Tuovinen, J. Periaux, & P. Neittaanmäki (Eds.), Computational Sciences and Artificial Intelligence in Industry : New Digital Technologies for Solving Future Societal and Economical Challenges (pp. 177-188). Springer. Intelligent Systems, Control and Automation: Science and Engineering, 76. https://doi.org/10.1007/978-3-030-70787-3_12

JYU authors or editors

Publication details

All authors or editors: Niinimäki, Esko; Paloneva, Juha; Pölönen, Ilkka; Heinonen, Ari; Äyrämö, Sami

Parent publication: Computational Sciences and Artificial Intelligence in Industry : New Digital Technologies for Solving Future Societal and Economical Challenges

Parent publication editors: Tuovinen, Tero T.; Periaux, Jacques; Neittaanmäki, Pekka

ISBN: 978-3-030-70786-6

eISBN: 978-3-030-70787-3

Journal or series: Intelligent Systems, Control and Automation: Science and Engineering

ISSN: 2213-8986

eISSN: 2213-8994

Publication year: 2022

Number in series: 76

Pages range: 177-188

Number of pages in the book: 275

Publisher: Springer

Place of Publication: Cham

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.1007/978-3-030-70787-3_12

Publication open access: Not open

Publication channel open access: 

Additional information: The CSAI 2019 Conference (Computational Science and AI in Industry: New Digital Technologies for Solving Future Societal and Economical Challenges) took place at Jyväskylä, Finland, on June 12–14, 2019.

Abstract

Osteoarthritis (OA) is the most common form of joint disease in the world. The diagnosis of OA is currently made by human experts and suffers from subjectivity, but recently new promising detection algorithms have been developed. We validated the current state-of-the-art KL-classifying neural network model for knee OA using knee X-rays taken from postmenopausal women suffering from knee pain attributable to OA. The performance of the model on the clinical data was considerably lower compared to the previous results on population-based test data. This suggests that the performance of the current grading methods is not yet adequate to be applied in clinical settings. The present results also emphasize the importance of using clinical data for performance evaluation before deploying medical machine learning models.

Keywords: arthrosis; knees; diagnostics; x-ray examination; machine learning; neural networks (information technology); validation

Free keywords: deep learning; neural network; convolution; osteoarthritis; validation

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2022

JUFO rating: 2