Deep learning models reveal sex-specific trochlear development and physeal migration on knee MRI

In 261 nondysplastic knee MRIs from ages 8–22, deep learning-based 3D modeling showed proximal physis migration and trochlear deepening between 13–19 years, with males having greater lateral trochlear depth after age 16. Findings may guide trochleoplasty timing.

• Sex-specific statistical shape models demonstrated proximal migration of the distal femoral physis and deepening of the trochlea between ages 13 and 19 years.
• After age 16, males exhibited significantly greater size-standardized lateral trochlear depth than females.
• A deep learning model enabled automated segmentation of femoral structures for 3D shape analysis.

Evidence grade: Level of evidence 3

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.