BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinoma
Quick Take
BioFact-MoE is a novel biologically factorized Mixture of Experts framework that enhances survival prediction in hepatocellular carcinoma (HCC) by achieving AUCs of 75.33%, 75.85%, and 73.96% at 12, 18, and 24 months, respectively. This model effectively separates liver and tumor factors, improving both accuracy and biological interpretability in prognostic modeling.
Key Points
- BioFact-MoE uses biologically supervised experts for improved prognostic modeling in HCC.
- The model was validated on a cohort of 588 patients with 3D MRI image-report pairs.
- It outperforms existing models across multiple time horizons for survival prediction.
- Gated expert weights allow for phenotype-aware risk stratification in patients.
- Hepatic and tumor embeddings show significant associations with liver function and tumor burden.
Article Content
From source RSS / original summaryarXiv:2605. 26376v1 Announce Type: new Abstract: Hepatocellular carcinoma (HCC) is biologically heterogeneous, shaped by the interplay between hepatic functional reserve and tumor-related oncologic factors; thus, similar survival outcomes may reflect fundamentally different underlying biological processes. Prognostic modeling in HCC is informed by rich multimodal information from multiparametric MRI and radiology reports from routine clinical practice.
Existing prognostic vision-language models (VLMs) learn a single entangled latent representation that blends hepatic and tumor-related factors, limiting both accuracy and biological interpretability. We present BioFact-MoE, a biologically factorized Mixture of Experts (MoE) framework that explicitly decomposes liver and tumor factors via biologically supervised experts within a residual MoE survival architecture.
On a HCC cohort of N=588 patients (pretrained on 4,582 3D MRI image-report pairs), BioFact-MoE consistently improves survival prediction over all baselines across time horizons, achieving 12-, 18-, and 24-month AUCs of 75. 33%, 75. 85%, and 73. 96%. Beyond scalar risk prediction, gated expert weights enable phenotype-aware risk stratification. Pathway-informed gating uncovers clinically meaningful treatment-associated survival heterogeneity.
In held-out validation, hepatic and tumor embeddings show selective associations with liver function and tumor burden markers, respectively (p<0. 05), without supervision. The code is available at https://github. com/jy-639/BioFact-MoE.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, achieving 0.11% parameter updates while enhancing uncertainty-aware fine-tuning. It outperforms state-of-the-art methods across 15 biomedical imaging datasets, proving effective in few-shot learning and domain shifts for clinical applications.