Single-Domain Generalization for Multimodal Cross-Cancer Prognosis via Dirac Rebalancer and Distribution Entanglement

• URL: http://arxiv.org/abs/2507.08340v1
• Date: Fri, 11 Jul 2025 06:37:48 GMT
• Title: Single-Domain Generalization for Multimodal Cross-Cancer Prognosis via Dirac Rebalancer and Distribution Entanglement
• Authors: Jia-Xuan Jiang, Jiashuai Liu, Hongtao Wu, Yifeng Wu, Zhong Wang, Qi Bi, Yefeng Zheng,
• Abstract summary: We show that multimodal prognosis models often generalize worse than unimodal ones in cross-cancer scenarios.<n>We introduce two plug-and-play modules: Sparse Dirac Information Rebalancer (SDIR) and Cancer-aware Distribution Entanglement (CADE)
• Score: 21.69257115232317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has shown remarkable performance in integrating multimodal data for survival prediction. However, existing multimodal methods mainly focus on single cancer types and overlook the challenge of generalization across cancers. In this work, we are the first to reveal that multimodal prognosis models often generalize worse than unimodal ones in cross-cancer scenarios, despite the critical need for such robustness in clinical practice. To address this, we propose a new task: Cross-Cancer Single Domain Generalization for Multimodal Prognosis, which evaluates whether models trained on a single cancer type can generalize to unseen cancers. We identify two key challenges: degraded features from weaker modalities and ineffective multimodal integration. To tackle these, we introduce two plug-and-play modules: Sparse Dirac Information Rebalancer (SDIR) and Cancer-aware Distribution Entanglement (CADE). SDIR mitigates the dominance of strong features by applying Bernoulli-based sparsification and Dirac-inspired stabilization to enhance weaker modality signals. CADE, designed to synthesize the target domain distribution, fuses local morphological cues and global gene expression in latent space. Experiments on a four-cancer-type benchmark demonstrate superior generalization, laying the foundation for practical, robust cross-cancer multimodal prognosis. Code is available at https://github.com/HopkinsKwong/MCCSDG

Related papers

• MoXGATE: Modality-aware cross-attention for multi-omic gastrointestinal cancer sub-type classification [7.7134821078470965]
  MoXGATE is a novel deep-learning framework that captures inter-modality dependencies, ensuring robust and interpretable integration.<n>We demonstrate that MoXGATE outperforms existing methods, achieving 95% classification accuracy.<n>Key contributions include (1) a cross-attention-based multi-omic integration framework, (2) modality-weighted fusion for enhanced interpretability, and (3) application of focal loss to mitigate data imbalance.
  arXiv  Detail & Related papers  (2025-06-08T03:42:23Z)
• 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)
• 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)
• MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer [13.74067035373274]
  We introduce a multi-modal heterogeneous graph-based conditional feature-guided diffusion model for lymph node metastasis diagnosis based on CT images. We propose a masked relational representation learning strategy, aiming to uncover the latent prognostic correlations and priorities of primary tumor and lymph node image representations.
  arXiv  Detail & Related papers  (2024-05-15T17:52:00Z)
• UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification [36.94690613164942]
  UniChest is a Conquer-and-Divide pre-training framework, aiming to make full use of the collaboration benefit of multiple sources of CXRs. We conduct thorough experiments on many benchmarks, e.g., ChestX-ray14, CheXpert, Vindr-CXR, Shenzhen, Open-I and SIIM-ACR Pneumothorax.
  arXiv  Detail & Related papers  (2023-12-18T09:16:48Z)
• Cancer-Net PCa-Gen: Synthesis of Realistic Prostate Diffusion Weighted Imaging Data via Anatomic-Conditional Controlled Latent Diffusion [68.45407109385306]
  In Canada, prostate cancer is the most common form of cancer in men and accounted for 20% of new cancer cases for this demographic in 2022. There has been significant interest in the development of deep neural networks for prostate cancer diagnosis, prognosis, and treatment planning using diffusion weighted imaging (DWI) data. In this study, we explore the efficacy of latent diffusion for generating realistic prostate DWI data through the introduction of an anatomic-conditional controlled latent diffusion strategy.
  arXiv  Detail & Related papers  (2023-11-30T15:11:03Z)
• A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion [54.512440195060584]
  We propose the Unified Multi-Modal Conditional Score-based Generative Model (UMM-CSGM) to take advantage of Score-based Generative Model (SGM) UMM-CSGM employs a novel multi-in multi-out Conditional Score Network (mm-CSN) to learn a comprehensive set of cross-modal conditional distributions. Experiments on BraTS19 dataset show that the UMM-CSGM can more reliably synthesize the heterogeneous enhancement and irregular area in tumor-induced lesions.
  arXiv  Detail & Related papers  (2022-07-07T16:57:21Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• AMINN: Autoencoder-based Multiple Instance Neural Network for Outcome Prediction of Multifocal Liver Metastases [1.7294318054149134]
  Multifocality occurs frequently in colorectal cancer liver metastases. Most existing biomarkers do not take the imaging features of all multifocal lesions into account. We present an end-to-end autoencoder-based multiple instance neural network (AMINN) for the prediction of survival outcomes.
  arXiv  Detail & Related papers  (2020-12-12T17:52:14Z)
• M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients [151.4352001822956]
  Early and accurate prediction of overall survival (OS) time can help to obtain better treatment planning for brain tumor patients. Existing prediction methods rely on radiomic features at the local lesion area of a magnetic resonance (MR) volume. We propose an end-to-end OS time prediction model; namely, Multi-modal Multi-channel Network (M2Net)
  arXiv  Detail & Related papers  (2020-06-01T05:21:37Z)

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.