Construction of a radiomics-based diagnostic nomogram for patellofemoral osteoarthritis-using lateral knee X-ray images from a South China population.

Authors

Xiangshu Guo, Zhongli Xiao, Juanxiang Zhu, Baoxin Qian, Song Tan, Shaolin Li, Wei Li

Published in

Quantitative imaging in medicine and surgery. Volume 16. Issue 9. Pages 711. Sep 01, 2026. Epub Aug 10, 2026.

Abstract

Patellofemoral osteoarthritis (PFOA) is a common cause of anterior knee pain but is frequently overlooked on routine radiographic assessment. This study aimed to develop and internally validate a radiomics-based nomogram for diagnosing PFOA using lateral knee radiographs combined with clinical features.
This retrospective multicenter study included 1,742 patients with 2,197 knees who underwent knee radiography between July 2017 and July 2020. During screening, 13 patients (15 knees) were excluded because of poor positioning or unqualified image quality, leaving 1,729 patients (2,182 knees) for analysis. PFOA was identified on lateral radiographs according to the Framingham criteria. Radiomic features were extracted from manually delineated rectangular regions of interest (ROIs) on lateral knee radiographs. The dataset was randomly divided into training and internal test sets at a ratio of 7:3. After feature selection, logistic regression (LR), k-nearest neighbors (KNN), and random forest (RF) models were developed and compared. A radiomics-clinical nomogram was subsequently constructed and internally validated.
Twenty-five radiomic features were ultimately selected for model construction. In the internal test set, the LR model achieved the best performance, with an area under the curve (AUC) of 0.773. Age was identified as an independent risk factor for PFOA. The nomogram integrating radiomic features, age, and sex showed improved diagnostic performance, with an AUC of 0.842, and demonstrated good calibration and clinical utility. External test set further demonstrated acceptable diagnostic performance of the LR model, with an AUC of 0.751.
A radiomics-based nomogram integrating lateral knee radiographs with clinical factors showed good diagnostic performance for PFOA and may serve as a practical tool for radiographic assessment.

PMID:
42701610
Bibliographic data and abstract were imported from PubMed on 06 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.