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

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

  • 0 min

Share

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

At a Glance

CategoryDetail
Condition
Key Mechanisms
Target Population
Care SettingResource-restricted locations.

Key Highlights

  • Proposed model achieves 96.5% accuracy in osteoporosis classification.
  • Utilizes Rolling Guidance Filtering (RGF) for image enhancement.
  • Combines MobileNetV2 and NASNetLarge for feature extraction.

Guideline-Based Recommendations

Diagnosis

  • Utilize enhanced knee X-ray images for early detection of osteoporosis.

Management

    Monitoring & Follow-up

      Risks

        Patient & Prescribing Data

        Individuals over 50.

        Clinical Best Practices

          Related Resources & Content

          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

          Diagnostic accuracy of deep learning vs. human raters for detecting osteoporotic vertebral compression fractures in routine CT scans

          Ultrasound Models Estimate Whole-Body Muscle Mass

          New equations incorporating cross-sectional area improve estimation accuracy.

          Body Composition by DXA in Patients with Klinefelter and Kallmann Syndrome: The Kama Study