A fuzzy-based growth model with principle component analysis selection for carpal bone-age assessment

Area of Science:

• Radiology
• Biomedical Engineering
• Pediatric Endocrinology

Background:

• Accurate bone age assessment is crucial for evaluating pediatric growth and development.
• Current methods like Greulich-Pyle and Tanner-Whitehouse rely on hand radiograms but can be subjective.
• Quantitative analysis of bone morphology offers a potential for more objective assessment.

Purpose of the Study:

• To develop and validate a novel bone age assessment system using fuzzy theory and principal component analysis.
• To quantitatively evaluate carpal bone morphology for skeletal maturity estimation.
• To improve the accuracy and objectivity of bone age determination in children.

Main Methods:

• Extraction of five geometric features from carpal bones (e.g., bone area, contour).
• Application of fuzzy theory combined with principal component analysis for feature analysis.
• Construction of a skeletal growth model using statistical correlation and three procedural types.

Main Results:

• The proposed fuzzy rule-based model demonstrated high accuracy in bone age assessment.
• Accuracy rates exceeded 89% for Type-I and II assessments and 87% for Type-III.
• The system achieved this accuracy within a 1.5-year tolerance.

Conclusions:

• The developed fuzzy rule-based system provides an accurate and objective method for bone age assessment.
• This quantitative approach using carpal bone morphology shows promise for clinical application in pediatric growth monitoring.
• The findings suggest a viable alternative to traditional subjective methods for bone age evaluation.