OMERACT validation of a deep learning algorithm for automated absolute quantification of knee joint effusion versus manual semi-quantitative assessment.

To begin evaluating deep learning (DL)-automated quantification of knee joint effusion-synovitis via the OMERACT filter. A DL algorithm previously trained on Osteoarthritis Initiative (OAI) knee MRI automatically quantified effusion volume in MRI of 53 OAI subjects, which were also scored semi-quantitatively via KIMRISS and MOAKS by 2-6 readers. DL-measured knee effusion correlated significantly with experts' assessments (Kendall's tau 0.34-0.43) CONCLUSION: The close correlation of automated DL knee joint effusion quantification to KIMRISS manual semi-quantitative scoring demonstrated its criterion validity. Further assessments of discrimination and truth vs. clinical outcomes are still needed to fully satisfy OMERACT filter requirements.

Informations de copyright

Copyright © 2024. Published by Elsevier Inc.

Déclaration de conflit d'intérêts

Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Jacob Jaremko reports financial support was provided by Medical Imaging Consultants (MIC), Edmonton, Canada. Banafshe Felfeliyan reports on a relationship with Alberta Innovates that includes funding grants. Walter P. Maksymowych is Chief Medical Officer CARE Arthritis Limited. Robert G. Lambart has received consulting fees from CARE Arthritis, Image Analysis Group and Calyx. We thank the members of the OMERACT MRI in Arthritis Working Group for their participation and support in this project.