Pith. sign in

REVIEW 7 cited by

Multimodal Prototyping for cancer survival prediction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.00224 v1 pith:YVOGNGIY submitted 2024-06-28 cs.CV stat.AP

classification cs.CVstat.AP
keywords tokensmultimodalanalysescancerinterpretabilitymethodsmorphologicalpatches
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal survival methods combining gigapixel histology whole-slide images (WSIs) and transcriptomic profiles are particularly promising for patient prognostication and stratification. Current approaches involve tokenizing the WSIs into smaller patches (>10,000 patches) and transcriptomics into gene groups, which are then integrated using a Transformer for predicting outcomes. However, this process generates many tokens, which leads to high memory requirements for computing attention and complicates post-hoc interpretability analyses. Instead, we hypothesize that we can: (1) effectively summarize the morphological content of a WSI by condensing its constituting tokens using morphological prototypes, achieving more than 300x compression; and (2) accurately characterize cellular functions by encoding the transcriptomic profile with biological pathway prototypes, all in an unsupervised fashion. The resulting multimodal tokens are then processed by a fusion network, either with a Transformer or an optimal transport cross-alignment, which now operates with a small and fixed number of tokens without approximations. Extensive evaluation on six cancer types shows that our framework outperforms state-of-the-art methods with much less computation while unlocking new interpretability analyses.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis

    cs.LG 2026-06 conditional novelty 6.0 of 10

    An adaptive Mamba architecture with dynamic cross-modal weighting and semantic reordering of WSI patches reports ~2% C-Index gains over baselines on five TCGA datasets.

  2. Pathway-Structured Privileged Distillation for Deployable Computational Pathology

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MoPE is a privileged distillation framework that transfers RNA-derived pathway supervision to histology experts via memory-usage alignment, improving whole-slide image only inference on cancer benchmarks.

  3. Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining

    q-bio.QM 2026-05 unverdicted novelty 6.0 of 10

    MIST augments MIL projection layers with cross-modal gene-expression prototypes derived from spatial transcriptomics, yielding consistent gains on survival, subtyping, and biomarker tasks across 23 endpoints and 8 agg...

  4. Structural Prognostic Event Modeling for Multimodal Cancer Survival Analysis

    cs.CV 2025-11 unverdicted novelty 5.0 of 10

    SlotSPE is a slot-attention framework that decomposes multimodal cancer data into structural prognostic event slots to improve survival prediction and interpretability.

  5. Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis

    eess.IV 2025-07 conditional novelty 5.0 of 10

    The paper introduces a shuffling-equivalence regularizer for MIL-based WSI analysis, claiming consistent gains over state-of-the-art methods.

  6. HeLo: Heterogeneous Multi-Modal Fusion with Label Correlation for Emotion Distribution Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    HeLo fuses physiological and behavioral features with optimal transport and label-correlation-driven attention, reporting the best average rank on DMER and WESAD emotion distribution benchmarks.

  7. CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment

    cs.CV 2026-08 conditional novelty 4.0 of 10

    CIGTSurv uses clinical text embeddings to guide cross-attention and distribution alignment between pathology and genomics, reaching an average C-index of 0.788 across five TCGA cohorts.

Pith tools