Disentangled and Interpretable Multimodal Attention Fusion for Cancer Survival Prediction

• URL: http://arxiv.org/abs/2503.16069v1
• Date: Thu, 20 Mar 2025 12:02:10 GMT
• Title: Disentangled and Interpretable Multimodal Attention Fusion for Cancer Survival Prediction
• Authors: Aniek Eijpe, Soufyan Lakbir, Melis Erdal Cesur, Sara P. Oliveira, Sanne Abeln, Wilson Silva,
• Abstract summary: We propose Disentangled and Interpretable Multimodal Attention Fusion (DIMAF) to improve cancer survival prediction.<n>DIMAF separates intra- and inter-modal interactions within an attention-based fusion mechanism to learn distinct modality-specific and modality-shared representations.<n>We evaluate DIMAF on four public cancer survival datasets, achieving a relative average improvement of 1.85% in performance and 23.7% in disentanglement.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To improve the prediction of cancer survival using whole-slide images and transcriptomics data, it is crucial to capture both modality-shared and modality-specific information. However, multimodal frameworks often entangle these representations, limiting interpretability and potentially suppressing discriminative features. To address this, we propose Disentangled and Interpretable Multimodal Attention Fusion (DIMAF), a multimodal framework that separates the intra- and inter-modal interactions within an attention-based fusion mechanism to learn distinct modality-specific and modality-shared representations. We introduce a loss based on Distance Correlation to promote disentanglement between these representations and integrate Shapley additive explanations to assess their relative contributions to survival prediction. We evaluate DIMAF on four public cancer survival datasets, achieving a relative average improvement of 1.85% in performance and 23.7% in disentanglement compared to current state-of-the-art multimodal models. Beyond improved performance, our interpretable framework enables a deeper exploration of the underlying interactions between and within modalities in cancer biology.

Related papers

• Continually Evolved Multimodal Foundation Models for Cancer Prognosis [50.43145292874533]
  Cancer prognosis is a critical task that involves predicting patient outcomes and survival rates.<n>Previous studies have integrated diverse data modalities, such as clinical notes, medical images, and genomic data, leveraging their complementary information.<n>Existing approaches face two major limitations. First, they struggle to incorporate newly arrived data with varying distributions into training, such as patient records from different hospitals.<n>Second, most multimodal integration methods rely on simplistic concatenation or task-specific pipelines, which fail to capture the complex interdependencies across modalities.
  arXiv  Detail & Related papers  (2025-01-30T06:49:57Z)
• M2EF-NNs: Multimodal Multi-instance Evidence Fusion Neural Networks for Cancer Survival Prediction [24.323961146023358]
  We propose a neural network model called M2EF-NNs for accurate cancer survival prediction. To capture global information in the images, we use a pre-trained Vision Transformer (ViT) model. We are the first to apply the Dempster-Shafer evidence theory (DST) to cancer survival prediction.
  arXiv  Detail & Related papers  (2024-08-08T02:31:04Z)
• Confidence-aware multi-modality learning for eye disease screening [58.861421804458395]
  We propose a novel multi-modality evidential fusion pipeline for eye disease screening. It provides a measure of confidence for each modality and elegantly integrates the multi-modality information. Experimental results on both public and internal datasets demonstrate that our model excels in robustness.
  arXiv  Detail & Related papers  (2024-05-28T13:27:30Z)
• FORESEE: Multimodal and Multi-view Representation Learning for Robust Prediction of Cancer Survival [3.4686401890974197]
  We propose a new end-to-end framework, FORESEE, for robustly predicting patient survival by mining multimodal information. Cross-fusion transformer effectively utilizes features at the cellular level, tissue level, and tumor heterogeneity level to correlate prognosis. The hybrid attention encoder (HAE) uses the denoising contextual attention module to obtain the contextual relationship features. We also propose an asymmetrically masked triplet masked autoencoder to reconstruct lost information within modalities.
  arXiv  Detail & Related papers  (2024-05-13T12:39:08Z)
• Joint Multimodal Transformer for Emotion Recognition in the Wild [49.735299182004404]
  Multimodal emotion recognition (MMER) systems typically outperform unimodal systems. This paper proposes an MMER method that relies on a joint multimodal transformer (JMT) for fusion with key-based cross-attention.
  arXiv  Detail & Related papers  (2024-03-15T17:23:38Z)
• TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction [7.646155781863875]
  We propose a novel framework named Two-stream Transformer-based Multimodal Fusion Network for survival prediction (TTMFN) In TTMFN, we present a two-stream multimodal co-attention transformer module to take full advantage of the complex relationships between different modalities. The experiment results on four datasets from The Cancer Genome Atlas demonstrate that TTMFN can achieve the best performance or competitive results.
  arXiv  Detail & Related papers  (2023-11-13T02:31:20Z)
• Cross-modality Attention-based Multimodal Fusion for Non-small Cell Lung Cancer (NSCLC) Patient Survival Prediction [0.6476298550949928]
  We propose a cross-modality attention-based multimodal fusion pipeline designed to integrate modality-specific knowledge for patient survival prediction in non-small cell lung cancer (NSCLC) Compared with single modality, which achieved c-index of 0.5772 and 0.5885 using solely tissue image data or RNA-seq data, respectively, the proposed fusion approach achieved c-index 0.6587 in our experiment.
  arXiv  Detail & Related papers  (2023-08-18T21:42:52Z)
• Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognition [69.32305810128994]
  Incongruity between modalities poses a challenge for multimodal fusion, especially in affect recognition. We propose the Hierarchical Crossmodal Transformer with Dynamic Modality Gating (HCT-DMG), a lightweight incongruity-aware model. HCT-DMG: 1) outperforms previous multimodal models with a reduced size of approximately 0.8M parameters; 2) recognizes hard samples where incongruity makes affect recognition difficult; 3) mitigates the incongruity at the latent level in crossmodal attention.
  arXiv  Detail & Related papers  (2023-05-23T01:24:15Z)
• Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
  We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH) We learn informative representations that can preserve both intra- and inter-modal similarities. The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
  arXiv  Detail & Related papers  (2021-12-13T08:58:03Z)
• Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis [96.46952672172021]
  Bi-Bimodal Fusion Network (BBFN) is a novel end-to-end network that performs fusion on pairwise modality representations. Model takes two bimodal pairs as input due to known information imbalance among modalities.
  arXiv  Detail & Related papers  (2021-07-28T23:33:42Z)
• Learning Multimodal VAEs through Mutual Supervision [72.77685889312889]
  MEME combines information between modalities implicitly through mutual supervision. We demonstrate that MEME outperforms baselines on standard metrics across both partial and complete observation schemes.
  arXiv  Detail & Related papers  (2021-06-23T17:54:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.