Development and validation of a deep learning model for liver shear stiffness regression using abdominal multiparametric MRI across multiple sites and vendors - Takeaways - MDSpire

Development and validation of a deep learning model for liver shear stiffness regression using abdominal multiparametric MRI across multiple sites and vendors

  • By

  • Redha Ali

  • Hailong Li

  • Scott B. Reeder

  • David Harris

  • William Masch

  • Anum Aslam

  • Krishna P. Shanbhogue

  • Nehal A. Parikh

  • Lili He

  • Jonathan R. Dillman

  • May 13, 2026

  • 0 min

Share

  • 1

    Chronic liver disease (CLD) significantly contributes to global morbidity and mortality, necessitating accurate assessment of liver fibrosis severity.

  • 2

    Current gold standard liver biopsy has limitations, prompting the need for reliable, non-invasive methods to assess liver fibrosis.

  • 3

    Magnetic resonance elastography (MRE) and ultrasound shear-wave elastography (SWE) are promising non-invasive tools but have accessibility and variability issues.

  • 4

    This study developed a transformer-based deep learning model using multiparametric MRI sequences to estimate liver shear stiffness across diverse patient profiles.

  • 5

    The model integrates T1-weighted, T2-weighted, and diffusion-weighted imaging data, aiming for improved accuracy in liver stiffness assessment.

Original Source(s)

Development and validation of a deep learning model for liver shear stiffness regression using abdominal multiparametric MRI across multiple sites and vendors

  • by Redha Ali, Hailong Li, Scott B. Reeder, David Harris, William Masch, Anum Aslam, Krishna P. Shanbhogue, Nehal A. Parikh, Lili He, Jonathan R. Dillman

  • May 13, 2026

Related Content

Single-cell CyTOF analysis uncovers changes in B, T, and macrophage populations in aging mouse liver

Strategies to promote liver fibrosis amelioration with involvement of restorative macrophages

Cirrhosis Patients Experiencing ARDS Encounter Significant Challenges