An interpretable deep concatenated architecture for osteoporosis detection using enhanced knee radiographs - Summary - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

A Transparent Deep Learning Framework for Osteoporosis Identification Utilizing Enhanced Knee X-rays

  • By

  • Narinder Kaur

  • Prabhdeep Singh

  • Jawad Khan

  • Dildar Hussain

  • Yeong Hyeon Gu

  • June 5, 2026

Share

Objective:

To develop a precise and automatic osteoporosis detection system using traditional X-ray images.

Key Findings:
  • The proposed model achieved an accuracy of 96.5%, an AUC of 0.97, and an F1-score of 89.5 for osteoporosis classification.
  • Comparative studies indicated that RGF and feature concatenation significantly improved classification accuracy over single models.
Interpretation:

Limitations:
Conclusion:

The method presents a robust automated detection system for osteoporosis through knee X-rays.

Original Source(s)

An interpretable deep concatenated architecture for osteoporosis detection using enhanced knee radiographs

  • by Narinder Kaur, Prabhdeep Singh, Jawad Khan, Dildar Hussain, Yeong Hyeon Gu

  • June 5, 2026

Related Content

Enhancing vertebral fracture prediction using multitask deep learning computed tomography imaging of bone and muscle

How Language Shapes Care 

ACP examines ethical implications of calling all physicians “providers”

Is atypical parathyroid tumor a different clinical entity than parathyroid adenoma and carcinoma? A retrospective review of a large single-center case series