Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
April 5, 2026Cancer Research

Abstract 2782: Automated segmentation of hepatocellular carcinoma lesions on contrast-enhanced MRI using an AI model in patients with cirrhosis.

View Full Paper
Ask AI
Bookmark
Share

Authors

ESEmma J. StevensonNLNathan LaySHStephanie A. Harmon

Discussion

Loading...

Member takes

Overview

Models detect hepatocellular carcinoma in cirrhosis patients, suggesting AI can enhance diagnosis accuracy.

Key Points

  • This research aims to develop an AI model for detecting hepatocellular carcinoma (HCC) in patients with cirrhosis using contrast-enhanced MRI.
  • Developed a model using multi-phasic contrast-enhanced T1 MRIs from two institutions.
  • Manually contoured 1794 liver lesions and assigned LI-RADS scores to assess lesion significance.
  • Trained six nnU-Net models using various imaging phases and assessed performance using sensitivity, specificity, and accuracy metrics.
  • The arterial phase model showed the best overall performance with 93% sensitivity and 81% accuracy at the scan level.
  • For lesion-level performance, sensitivity was 65.9% and positive predictive value was 68.1%.
  • 45.2% of true-positive lesions had a LI-RADS score ≥ 4, indicating their high severity.

Cite This Study

Stevenson et al. (2026) studied this question.

synapsesocial.com/papers/69d1fc8ea79560c99a0a233bhttps://doi.org/10.1158/1538-7445.am2026-2782
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A287 LEVERAGING MACHINE LEARNING TO IMPROVE THE DIAGNOSTIC ACCURACY OF ULTRASOUND SCREENING FOR HEPATOCELLULAR CARCINOMA2024 · 2 citations
  2. 2Deep Learning Combined with Radiologist’s Intervention Achieves Accurate Segmentation of Hepatocellular Carcinoma in Dual-Phase Magnetic Resonance Images2024 · 3 citations
  3. 3MRI radiomics based on deep learning automated segmentation to predict early recurrence of hepatocellular carcinoma2024 · 10 citations
  4. 4Automatic segmentation of hepatocellular carcinoma on dynamic contrast-enhanced MRI based on deep learning2024 · 2 citations
  5. 5Hepatocellular Carcinoma Segmentation on MRI: Five-Fold ATLAS Benchmarking, Phase-Wise External Stress Testing, and Multiphasic OpenSwissHCC Ablation2026