Knee osteoarthritis severity grading using soft labelling and ordinal classification
Francisco Bérchez-Moreno 
Víctor Manuel Vargas-Yun 
Antonio Manuel Gómez-Orellana 
David Guijo-Rubio 
Luca Romeo 
Pedro Antonio Gutiérrez 
César Hervás-Martínez Proceedings of the 18th international work-conference on artificial neural networks, IWANN 2025
Abstract
Knee Osteoarthritis (KOA) is a progressive joint disease characterised by stiffness and pain, among others. It is generally diagnosed by evaluating physical symptoms, medical history, and screening techniques. However, conventional methods are often subjective, posing a significant challenge to the early grading of disease progression. To address this issue and support clinical decision-making, we propose an ordinal deep learning framework to study the optimal combination of loss functions, and output methodologies with soft labelling approaches, for automatic KOA severity grading based on Kellgren and Lawrence scores from X-ray images. A total of 20 combinations (2 loss functions x 2 output methodologies x 5 soft labelling approaches) are compared in this study, using a public dataset. The optimal configuration uses the categorical cross entropy loss, a cumulative link model as output, and a beta distribution for soft labelling. The results achieved demonstrate the efficacy of these ordinal classification approaches.
BibTex Citation
@inproceedings{Berchez2025Knee,
author = {B{\' e}rchez-Moreno, Francisco and Vargas-Yun, V{\' i}ctor Manuel and G{\' o}mez-Orellana, Antonio Manuel and Guijo-Rubio, David and Romeo, Luca and Conti, Edoardo and Guti{\' e}rrez, Pedro Antonio and Herv{\' a}s-Mart{\' i}nez, C{\' e}sar},
booktitle = {Proceedings of the 18th international work-conference on artificial neural networks, {IWANN} 2025},
doi = {10.1007/978-3-032-02725-2_41},
year = {2025},
pages = {522--533},
organization = {Springer},
title = {Knee osteoarthritis severity grading using soft labelling and ordinal classification},
url = {https://doi.org/10.1007/978-3-032-02725-2_41},
volume = {16008},
}
BibTex Unicode Citation
@inproceedings{Berchez2025Knee,
author = {Bérchez-Moreno, Francisco and Vargas-Yun, Víctor Manuel and Gómez-Orellana, Antonio Manuel and Guijo-Rubio, David and Romeo, Luca and Conti, Edoardo and Gutiérrez, Pedro Antonio and Hervás-Martínez, César},
booktitle = {Proceedings of the 18th international work-conference on artificial neural networks, {IWANN} 2025},
doi = {10.1007/978-3-032-02725-2_41},
year = {2025},
pages = {522--533},
organization = {Springer},
title = {Knee osteoarthritis severity grading using soft labelling and ordinal classification},
url = {https://doi.org/10.1007/978-3-032-02725-2_41},
volume = {16008},
}
APA Citation
Bérchez-Moreno, F., Vargas-Yun, V. M., Gómez-Orellana, A. M., Guijo-Rubio, D., Romeo, L., Conti, E., Gutiérrez, P. A., & Hervás-Martínez, C. (2025). Knee osteoarthritis severity grading using soft labelling and ordinal classification. Proceedings of the 18th International Work-Conference on Artificial Neural Networks, IWANN 2025, 16008, 522–533. https://doi.org/10.1007/978-3-032-02725-2_41
RIS Citation
TY - CONF
AU - Bérchez-Moreno, Francisco
AU - Vargas-Yun, Víctor Manuel
AU - Gómez-Orellana, Antonio Manuel
AU - Guijo-Rubio, David
AU - Romeo, Luca
AU - Conti, Edoardo
AU - Gutiérrez, Pedro Antonio
AU - Hervás-Martínez, César
C3 - Proceedings of the 18th international work-conference on artificial ne
ural networks, IWANN 2025
DA - 2025///
C2 - 2025
DO - 10.1007/978-3-032-02725-2_41
ID - temp_id_385964353611
PB - Springer
SP - 522-533
TI - Knee osteoarthritis severity grading using soft labelling and ordinal
classification
UR - https://doi.org/10.1007/978-3-032-02725-2_41
VL - 16008
ER -
CV Citation
F. Bérchez-Moreno (CA), V.M. Vargas-Yun, A.M. Gómez-Orellana, D. Guijo-Rubio, L. Romeo, E. Conti, P.A. Gutiérrez, C. Hervás-Martínez (2/8). "Knee osteoarthritis severity grading using soft labelling and ordinal classification". Proceedings of the 18th international work-conference on artificial neural networks, IWANN 2025, pp. 522-533, 2025.