Gut decisions based on the liver: prediction of colorectal neoplasia using AI-based liver analysis of routine CT scans - Summary - MDSpire

Gut decisions based on the liver: prediction of colorectal neoplasia using AI-based liver analysis of routine CT scans

  • By

  • Anna Hinterberger

  • Jonas Bohn

  • Darya Trofimova

  • Nicolas Knabe

  • Julia Dettling

  • Tobias Norajitra

  • Fabian Isensee

  • Johannes Betge

  • Stefan O. Schönberg

  • Dominik Nörenberg

  • Sergio Grosu

  • Sonja Loges

  • Ralf Floca

  • Jakob Nikolas Kather

  • Klaus Maier-Hein

  • Freba Grawe

  • June 3, 2026

  • 0 min

Share

Objective:

To evaluate the potential of the gut–liver axis in predicting colorectal neoplasia through AI-based liver analysis in routine CT images, highlighting its role in risk assessment.

Key Findings:
  • The best-performing radiomics-based XGBoost model achieved a test AUROC of 0.810, indicating strong predictive capability.
  • Sensitivity reached 74.1% and specificity 72.3% for detecting colorectal neoplasia, demonstrating the model's effectiveness.
  • Subclassification between CRC and adenoma had an AUROC of 0.674, indicating room for improvement in distinguishing these conditions.
Interpretation:

AI-based liver analysis from routine CT scans can predict colorectal neoplasia, supporting its potential as an adjunct to CRC screening and enhancing early detection strategies.

Limitations:
  • The study is retrospective and conducted at a single center, which may limit the generalizability of the findings.
  • Subclassification accuracy between CRC and adenoma was lower, indicating a need for further refinement in predictive models.
Conclusion:

This study suggests that liver imaging features may serve as non-invasive biomarkers for colorectal neoplasia, potentially enhancing screening strategies and improving patient outcomes.

Original Source(s)

Gut decisions based on the liver: prediction of colorectal neoplasia using AI-based liver analysis of routine CT scans

  • by Anna Hinterberger, Jonas Bohn, Darya Trofimova, Nicolas Knabe, Julia Dettling, Tobias Norajitra, Fabian Isensee, Johannes Betge, Stefan O. Schönberg, Dominik Nörenberg, Sergio Grosu, Sonja Loges, Ralf Floca, Jakob Nikolas Kather, Klaus Maier-Hein, Freba Grawe

  • June 3, 2026

Related Content

Signals of inequity in the care pathway: rural lab diagnosis, systemic therapy delays, and RAS mutation differences in metastatic colorectal cancer

Case Report: Cytokeratin-positive interstitial reticulum cell tumor with HLA loss of heterozygosity

Bibliometric analysis of exercise and cancer prognosis research: trends, thematic evolution, and global collaborations (2015–2024)