Related Experiment Video
Updated: Jan 8, 2026
The Use of Thermal Infra-Red Imaging to Detect Delayed Onset Muscle Soreness
Published on: January 22, 2012
Diagnostic accuracy of infrared thermography and textural features in patellar tendinopathy: optimizing ROI selection
F J Molina-Payá1, S Montero-Navarro1, C Orts-Ruiz1
1Physical Therapy Department, Health Sciences Faculty, CEU-Cardenal Herrera University, CEU Universities, Plaza Reyes Católicos, 19, Elche, 03204, Spain.
Objectives:
To evaluate the diagnostic accuracy of infrared thermography (IT) using temperature difference (ΔT) and gray-level co-occurrence matrix (GLCM)-based textural parameters for detecting patellar tendinopathy (PT) in athletes, and to determine the optimal region of interest (ROI) size for analysis.
Design:
Cross-sectional study following STARD criteria.
Setting:
Physical therapy center with controlled environmental conditions.
Participants:
54 athletes (27 with unilateral PT; 27 healthy controls).
Main Outcome Measures:
Temperature differences (ΔT) and GLCM features (energy, homogeneity, contrast, correlation, entropy) from thermal images of tendon and knee ROIs.
Results:
Athletes with PT showed higher ΔT in the tendon ROI (0.5 ± 0.36 °C vs. 0.2 ± 0.20 °C; d = 0.77; p = 0.013). Among GLCM parameters, tendon ROI correlation (TCOR) differed significantly between groups (p = 0.042). Diagnostic performance analysis identified ΔT as the best single variable (AUC 0.83; sensitivity 78 %; specificity 78 %). The ΔT + GLCM combination achieved highest accuracy for tendon ROI (AUC 0.93). The patellar tendon-specific ROI provided better discrimination than the knee ROI.
Conclusions:
IRT combined with GLCM enhances PT diagnostic precision, with the tendon ROI optimal for detecting local physiological differences. This accessible multimodal approach could complement clinical diagnosis in athletes.
