Computer-assisted bone age assessment: image preprocessing and epiphyseal/metaphyseal ROI extraction

Area of Science:

• Radiology
• Medical Imaging
• Biometrics

Background:

• Skeletal maturity assessment traditionally relies on visual comparison of hand radiographs with atlas standards.
• This subjective method can lead to variability in bone age estimation.
• Objective and accurate skeletal maturity assessment is crucial for clinical decision-making.

Purpose of the Study:

• To develop and evaluate a novel digital image analysis methodology for objective bone age estimation.
• To enhance the accuracy and consistency of skeletal maturity assessment in clinical practice.
• To assist radiologists by providing quantitative features from hand radiographs.

Main Methods:

• A digital hand atlas was utilized for developing an image analysis methodology.
• The methodology involves preprocessing to identify epiphyseal/metaphyseal regions of interest (EMROIs).
• Feature extraction techniques were applied to quantify skeletal development characteristics.

Main Results:

• Accuracy was independently measured at key stages: phalangeal tip detection, EMROI extraction, and EMROI boundary localization.
• Extracted features objectively describe skeletal development stages.
• The developed method demonstrated potential for more objective skeletal maturity assessment compared to visual atlas comparison.

Conclusions:

• The developed image analysis methodology offers a more objective approach to bone age estimation.
• This digital tool has the potential to improve the accuracy and reliability of skeletal maturity assessment.
• Further integration into clinical workflows could enhance radiological practice in pediatric assessment.