基于深度学习算法的膝关节积液自动绝对定量与手动半定量评估的 OMERACT 验证。
OMERACT validation of a deep learning algorithm for automated absolute quantification of knee joint effusion versus manual semi-quantitative assessment.
机构信息
Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Canada.
Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Canada.
出版信息
Semin Arthritis Rheum. 2024 Jun;66:152420. doi: 10.1016/j.semarthrit.2024.152420. Epub 2024 Feb 17.
OBJECTIVE
To begin evaluating deep learning (DL)-automated quantification of knee joint effusion-synovitis via the OMERACT filter.
METHODS
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.
RESULTS
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.
目的
通过 OMERACT 筛选器，开始评估深度学习（DL）自动定量膝关节积液-滑膜炎。
方法
一种先前在 Osteoarthritis Initiative（OAI）膝关节 MRI 上训练的 DL 算法自动定量了 53 名 OAI 受试者 MRI 中的积液量，这些受试者还通过 2-6 位读者的 KIMRISS 和 MOAKS 进行了半定量评分。
结果
DL 测量的膝关节积液与专家评估具有显著相关性（Kendall's tau 0.34-0.43）。
结论
自动 DL 膝关节积液定量与 KIMRISS 手动半定量评分的密切相关性表明其具有标准效度。为了完全满足 OMERACT 筛选器的要求，仍需要进一步评估其区分度和与真实临床结果的关系。
Zotero 插件