Correlation of histologic, imaging, and artificial intelligence features in NAFLD patients, derived from Gd-EOB-DTPA-enhanced MRI: a proof-of-concept study - Summary - MDSpire

Correlation of histologic, imaging, and artificial intelligence features in NAFLD patients, derived from Gd-EOB-DTPA-enhanced MRI: a proof-of-concept study

  • By

  • Nina Bastati

  • Matthias Perkonigg

  • Daniel Sobotka

  • Sarah Poetter-Lang

  • Romana Fragner

  • Andrea Beer

  • Alina Messner

  • Martin Watzenboeck

  • Svitlana Pochepnia

  • Jakob Kittinger

  • Alexander Herold

  • Antonia Kristic

  • Jacqueline C. Hodge

  • Stefan Traussnig

  • Michael Trauner

  • Ahmed Ba-Ssalamah

  • Georg Langs

  • June 26, 2023

  • 0 min

Share

Objective:

To investigate whether a hybrid unsupervised and supervised deep learning approach can differentiate simple steatosis from NASH using MRI techniques.

Key Findings:
  • Gd-EOB-DTPA-MRI can distinguish between simple steatosis and NASH based on relative liver enhancement (RLE) and fat fraction (FF).
  • The hybrid machine learning approach identified predictive patterns that effectively differentiate between the two conditions.
  • Histopathology confirmed the diagnosis of simple steatosis or NASH in all patients.
Interpretation:

The study suggests that advanced MRI techniques combined with AI can provide a non-invasive alternative to liver biopsy for diagnosing NASH in NAFLD patients.

Limitations:
  • Single-center study may limit generalizability.
  • Retrospective validation cohort may introduce bias.
  • Small sample size in both derivation and validation groups.
Conclusion:

The findings support the potential of Gd-EOB-DTPA-MRI and AI in improving the diagnosis and monitoring of NASH, reducing reliance on invasive liver biopsies.

Original Source(s)

Correlation of histologic, imaging, and artificial intelligence features in NAFLD patients, derived from Gd-EOB-DTPA-enhanced MRI: a proof-of-concept study

  • by Nina Bastati, Matthias Perkonigg, Daniel Sobotka, Sarah Poetter-Lang, Romana Fragner, Andrea Beer, Alina Messner, Martin Watzenboeck, Svitlana Pochepnia, Jakob Kittinger, Alexander Herold, Antonia Kristic, Jacqueline C. Hodge, Stefan Traussnig, Michael Trauner, Ahmed Ba-Ssalamah, Georg Langs

  • June 26, 2023

Related Content

AI Scribes: Efficiency for Whom?

Unresolved safety, privacy, and regulatory concerns may limit benefits of AI scribes for physicians and patients.

Factors Related to Textbook Outcome in Laparoscopic Liver Resections: a Single Western Centre Analysis

A new method to estimate the histological stage of primary biliary cholangitis