AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Latent Imaging Biomarkers for Interpretable Microvascular Invasion Prediction in Hepatocellular Carcinoma

Ji Rao, Xinyu Liu, Yong Yi, Ying Xiao, Ye Luo

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add mixup augmentation (ablation)IRCL · HCC-ZSH multi-modalityACC (%): 79.81 -> 92.78Improved
add mixup augmentation (ablation)IRCL · HCC-ZSH multi-modalityF1 (%): 73.16 -> 90.39Improved
add intra-patient positive samples (ablation)IRCL contrastive learning · HCC-ZSH multi-modalityACC (%): 90.37 -> 92.78Improved
add inter-patient positive samples (ablation)IRCL contrastive learning · HCC-ZSH multi-modalityACC (%): 90.55 -> 92.78Improved
add contrastive loss Lc (ablation)IRCL Stage I · HCC-ZSH multi-modalityACC (%): 90.09 -> 92.78Improved
add reconstruction loss Lr (ablation)IRCL Stage I · HCC-ZSH multi-modalityACC (%): 89.35 -> 92.78Improved
add biomarker prototype attention (ablation)IRCL Stage II · HCC-ZSH multi-modalityACC (%): 92.17 -> 92.78Improved
vary number of biomarkers K and inter-patient positives s (ablation)IRCL · HCC-ZSHperformanceNo clear effect
use multi-modality (T1, T1D, T1V) input instead of single modalityIRCL · HCC-ZSHACC (%): 88.06 -> 92.78Improved
use IRCL instead of competing methods on T1D and T1V single modalitiesMVI classification · HCC-ZSH (T1D)AUC (%): 90.55 -> 84.44Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy