The paper introduces a modular framework for multimodal AI fusion that combines slide-level embeddings from histology images with per-visit clinical embeddings using 15 interchangeable fusion methods. Applied to a prospective cohort of newly diagnosed inflammatory bowel disease patients, the best fusion method achieved macro‑F1 scores between 0.57 and 0.75, outperforming single‑modality models in most scenarios and showing varying reliance on image data depending on the remission outcome. The study highlights how different fusion strategies can influence predictive performance across distinct clinical endpoints.
arXiv:2610.07913v1 Announce Type: cross Abstract: Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whol...
MIST is a multimodal survival prediction framework that fuses whole-slide images and genomic profiles by representing genomic features as tokens that query histology context tokens derived from a foundation model. The architecture enriches molecular information with histology context before survival prediction, avoiding late-stage merging of separately encoded modalities. Training incorporates discrete-time survival prediction, genomic feature masking, WSI dropout, and contrastive alignment, and demonstrates improved external C-index across colon, renal, lung, and glioblastoma cohorts compared to standard fusion baselines.
The study introduces a computationally efficient multi‑section whole slide image analysis framework that captures the entire prostate tumor landscape to predict biochemical recurrence (BCR) after radical prostatectomy. Using a large dataset of 23,451 slides from 789 patients, the authors optimized patch and slide subsampling to reduce computational demands while achieving strong predictive performance for 1‑ and 2‑year BCR, comparable to or better than existing clinical benchmarks. The AI‑derived risk score was an independent prognostic factor, improved prognostic performance when combined with clinical variables, and showed preliminary transferability in an external cohort, with attention‑dispersion analysis confirming that the model leveraged information from multiple sections consistent with prostate cancer’s multifocal nature.
arXiv:2606. 17115v1 Announce Type: cross Abstract: Foundation models (FMs) have emerged as powerful representation extractors for medical data, yet their generalizability to datasets under distribution shift remains underexplored.
Multimodal fusion learning (MFL) has shown great potential in the medical domain, where we are faced with disparate data modalities such as imaging, clinical records, and omics. However, existing MFL strategies face several major challenges.
The paper introduces GPF‑Net, a Gated Progressive Fusion Network designed for colonoscopic polyp re‑identification. It fuses multimodal features from multiple levels using fully connected gating mechanisms, allowing layer‑wise refinement of semantic information. Experiments on standard benchmarks show that this multimodal, progressive fusion approach outperforms state‑of‑the‑art unimodal ReID models, especially for small polyps where fine‑grained details are crucial.
arXiv:2510. 00053v2 Announce Type: replace-cross Abstract: Pathology whole-slide images (WSIs) are widely used for cancer survival analysis because of their comprehensive histopathological information at both cellular and tissue levels, enabling quantitative, large-scale, and prognostically rich tumor feature analysis.
arXiv:2609.00396v1 Announce Type: new Abstract: Histopathological whole slide images (WSIs) are central to cancer diagnosis, but their gigapixel scale, tissue heterogeneity, weak slide-level supervis...
SCOUT is a concept‑grounded multimodal transformer that generates whole‑slide pathology reports by integrating local histological patterns, whole‑slide context, and expert‑curated diagnostic concepts. It uses evolving visual representations and recursively updated slide‑ and concept‑conditioned representations, with separate attention pathways during decoding that are fused adaptively for each token. Evaluated on TCGA‑BRCA, HistAI, and REG‑2025, SCOUT outperformed existing methods, improving BLEU, METEOR, and ROUGE‑L scores and raising the Clinical Report Quality Score on REG‑2025.
arXiv:2610.07694v1 Announce Type: new Abstract: The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival predi...
arXiv:2606. 15038v1 Announce Type: new Abstract: Accurate time-to-event (TTE) prediction from multimodal clinical data remains challenging due to modality imbalance and distribution shift.
The paper introduces a dual cross‑attention deep learning framework for automated grading of Cervical Intraepithelial Neoplasia (CIN) and prediction of Swede scores, using a newly released BUET Multi‑Center Colposcopy Dataset. The architecture fuses paired multimodal cervigrams and employs a custom composite loss to handle class imbalance, achieving 71.85% accuracy and 86.23% AUC‑ROC for three‑class CIN grading, and AUC‑ROC values between 75.7% and 88.4% for individual Swede score components. The total predicted Swede Score has a mean absolute error of 1.489, indicating potential for AI‑assisted colposcopy screening in resource‑limited settings.