Dual-input deep learning bone age assessment in late adolescence using hand and knee radiographs. | ScholarDeck

Paper

Dual-input deep learning bone age assessment in late adolescence using hand and knee radiographs.

New research · Radiology

Skeletal radiology · 2w

AI / informaticsSkeletal radiology· Jul 2026

Dual-input deep learning bone age assessment in late adolescence using hand and knee radiographs.

Zishuai Peng, Nanxin Li, Yajia Wu … Junran Zhang

Read paper

Pediatric RadiologyAI / informaticsQ2IF 2.6

Dual-input hand-knee deep learning model estimated bone age within 3.77 months on average

Dual-input deep learning bone age assessment in late adolescence using hand and knee radiographs.

Zishuai Peng … Junran Zhang

Skeletal radiology · Jul 2026 · Q2 in Radiology

Purpose

To develop and internally evaluate an age-assisted dual-input model for bone age assessment in late adolescence using paired hand-wrist and knee radiographs.

Methods

This single-center retrospective study included 547 adolescents aged 13-19 years with paired left hand-wrist and left knee radiographs (1094 images) acquired during routine clinical care.

n = 1094 images

3.77

Results

3.77

months

predicted bone age typically lands within about 4 months of true age

n = 1094 images

More results

Internal ablation comparisons showed lower errors with paired hand-knee inputs and demographic variables than with single-site inputs.

“

Conclusion · 1 of 3

In this single-center retrospective cohort, the age-assisted dual-input framework showed promising internal performance for late-adolescent bone age assessment.

Conclusion · 2 of 3

Independent multicenter external validation is required before clinical deployment, forensic/disputed-age use, or legal decision-making.

Conclusion · 3 of 3

Knee radiographs should be used only when already available or medically justified, not as routine additional imaging.

Read paper