Multimodal deep learning model predicts time-specific survival after HCC resection

TEMPO-HCC, a multimodal deep model using MRI and histology, predicted time-specific survival after HCC resection (C-index 0.751, 1-yr AUC 0.836), outperforming staging systems.

• In external validation, time-dependent AUCs were 0.836, 0.781, 0.812, and 0.680 at 12, 24, 36, and 60 months.
• Augmenting guideline-based staging with TEMPO-HCC improved discrimination, supporting personalized follow-up.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.