Objectives To develop and validate an automatic, scalable framework for assessing the femoro-tibial osteoarthritic cartilage severity using high-resolution cartilage thickness maps (CTh-Maps) and a CTh-Score. Materials and methods The osteoarthritis initiative (OAI) cohort of 4796 subjects was analysed. A 3D-UNet was trained to segment femoro-tibial bones and cartilages using MRI from baseline, 1-, 2-, 3-, 4-, 6-, and 8-year follow-ups. CTh-Maps were created for each knee. A ResNet model trained on CTh-Maps assigned a CTh-Score ranging from 0 (healthy cartilage) to 100 (end-stage OA). The reproducibility of the CTh-Score was evaluated in a test/retest setup. Its validity was assessed by examining the correlation with expert evaluations of cartilage loss (MOAKS grading) and association with OA severity (KL grade) in both OAI and an external dataset. The CTh-Score sensitivity to OA structural progression was examined. Results The framework generated CTh-Maps for the entire OAI, forming the “OAI CTh-Maps” dataset. Both CTh-Maps and CTh-Score showed excellent reproducibility (ICC > 0.98). The CTh-Score demonstrated strong correlations (r = 0.81) with expert assessments of cartilage loss and strong associations to OA severity, including in the external dataset. The CTh-Score either increased or remained stable for almost all subjects at 8-year follow-up. The CTh-Score showed great sensitivity to change, significantly increasing between each timepoint, up to 6 years prior to KL progression. Conclusions CTh-Maps and CTh-Score represent a novel approach to analysing cartilage at imaging. Their scalability, reproducibility and sensitivity to osteoarthritic cartilage severity provide significant opportunities for earlier OA detection, better disease monitoring, and therapeutic window identification. Project page: <a href="https://lausannekneestudy.org/cthscore/">https://lausannekneestudy.org/cthscore/</a> Dataset link: <a href="https://doi.org/10.5281/zenodo.18745638">https://doi.org/10.5281/zenodo.18745638</a>. Key Points <Emphasis Type="BoldItalic">Question</Emphasis> Enhanced imaging biomarkers are needed in osteoarthritis research, but current methods present limitations in assessing variable cartilage degeneration and lack scalability. Findings This study introduces an automatic framework for the evaluation of osteoarthritic cartilage severity through the generation of CTh-Maps and the CTh-Score. <Emphasis Type="BoldItalic">Clinical relevance</Emphasis> The scalability and sensitivity of CTh-Maps and CTh-Score in assessing osteoarthritic cartilage severity create new opportunities for clinical trials, both in the screening phase (identifying progressors) and in treatment evaluation (serving as biomarkers for disease structural progression). Graphical Abstract

Automatic framework for evaluating osteoarthritic cartilage severity: high-resolution cartilage thickness mapping and scoring

期刊论文
发表日期：

2026年3月24日

查看全文

Paul Margain,
Patrick Omoumi,
Julien Favre

摘要

Objectives

To develop and validate an automatic, scalable framework for assessing the femoro-tibial osteoarthritic cartilage severity using high-resolution cartilage thickness maps (CTh-Maps) and a CTh-Score.

Materials and methods

The osteoarthritis initiative (OAI) cohort of 4796 subjects was analysed. A 3D-UNet was trained to segment femoro-tibial bones and cartilages using MRI from baseline, 1-, 2-, 3-, 4-, 6-, and 8-year follow-ups. CTh-Maps were created for each knee. A ResNet model trained on CTh-Maps assigned a CTh-Score ranging from 0 (healthy cartilage) to 100 (end-stage OA). The reproducibility of the CTh-Score was evaluated in a test/retest setup. Its validity was assessed by examining the correlation with expert evaluations of cartilage loss (MOAKS grading) and association with OA severity (KL grade) in both OAI and an external dataset. The CTh-Score sensitivity to OA structural progression was examined.

Results

The framework generated CTh-Maps for the entire OAI, forming the “OAI CTh-Maps” dataset. Both CTh-Maps and CTh-Score showed excellent reproducibility (ICC > 0.98). The CTh-Score demonstrated strong correlations (r = 0.81) with expert assessments of cartilage loss and strong associations to OA severity, including in the external dataset. The CTh-Score either increased or remained stable for almost all subjects at 8-year follow-up. The CTh-Score showed great sensitivity to change, significantly increasing between each timepoint, up to 6 years prior to KL progression.

Conclusions

CTh-Maps and CTh-Score represent a novel approach to analysing cartilage at imaging. Their scalability, reproducibility and sensitivity to osteoarthritic cartilage severity provide significant opportunities for earlier OA detection, better disease monitoring, and therapeutic window identification. Project page: https://lausannekneestudy.org/cthscore/ Dataset link: https://doi.org/10.5281/zenodo.18745638.

Key Points

Question Enhanced imaging biomarkers are needed in osteoarthritis research, but current methods present limitations in assessing variable cartilage degeneration and lack scalability.

Findings This study introduces an automatic framework for the evaluation of osteoarthritic cartilage severity through the generation of CTh-Maps and the CTh-Score.

Clinical relevance The scalability and sensitivity of CTh-Maps and CTh-Score in assessing osteoarthritic cartilage severity create new opportunities for clinical trials, both in the screening phase (identifying progressors) and in treatment evaluation (serving as biomarkers for disease structural progression).

Graphical Abstract