Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis

• URL: http://arxiv.org/abs/2603.10526v1
• Date: Wed, 11 Mar 2026 08:30:15 GMT
• Title: Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis
• Abstract summary: Current studies generally follow a cancer-specific learning paradigm.<n>The available training samples for one cancer type are usually scarce in pathology.<n>This paper proposes a new scheme, Sparse Task Vector Mixup with Hypernetworks.
• Score: 17.53610180337971
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Whole-Slide Images (WSIs) are widely used for estimating the prognosis of cancer patients. Current studies generally follow a cancer-specific learning paradigm. However, the available training samples for one cancer type are usually scarce in pathology. Consequently, the model often struggles to learn generalizable knowledge, thus performing worse on the tumor samples with inherent high heterogeneity. Although multi-cancer joint learning and knowledge transfer approaches have been explored recently to address it, they either rely on large-scale joint training or extensive inference across multiple models, posing new challenges in computational efficiency. To this end, this paper proposes a new scheme, Sparse Task Vector Mixup with Hypernetworks (STEPH). Unlike previous ones, it efficiently absorbs generalizable knowledge from other cancers for the target via model merging: i) applying task vector mixup to each source-target pair and then ii) sparsely aggregating task vector mixtures to obtain an improved target model, driven by hypernetworks. Extensive experiments on 13 cancer datasets show that STEPH improves over cancer-specific learning and an existing knowledge transfer baseline by 5.14% and 2.01%, respectively. Moreover, it is a more efficient solution for learning prognostic knowledge from other cancers, without requiring large-scale joint training or extensive multi-model inference. Code is publicly available at https://github.com/liupei101/STEPH.

Related papers

• Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction [26.98955103296043]
  Whole-Slide Image (WSI) is an important tool for estimating cancer prognosis.<n>This paper makes a paradigm shift to knowledge transfer and presents the first preliminary yet systematic study on cross-cancer prognosis knowledge transfer in WSIs.
  arXiv  Detail & Related papers  (2025-08-19T03:24:19Z)
• Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification [50.899861205016265]
  We propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification.<n>Our framework introduces two key components into the common MIL model architecture.<n>We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets.
  arXiv  Detail & Related papers  (2025-03-08T04:51:58Z)
• CrossFusion: A Multi-Scale Cross-Attention Convolutional Fusion Model for Cancer Survival Prediction [1.8720735308601646]
  Cancer survival prediction from whole slide images (WSIs) is a challenging task in computational pathology.<n>We propose CrossFusion, a novel multi-scale feature integration framework.<n>By effectively modeling both scale-specific patterns and their interactions, CrossFusion generates a rich feature set that enhances survival prediction accuracy.
  arXiv  Detail & Related papers  (2025-03-03T21:34:52Z)
• Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression Values [3.1298840947078372]
  We train a classifier to categorize tumors into a high- or low-risk group of recurrence. Our CL-based classifiers achieved an area under the receiver operating characteristic curve (AUC) greater than 0.8 for 14 types of cancer. Our CLCox models trained with the TCGA data outperformed existing methods significantly in predicting the prognosis of 19 types of cancer.
  arXiv  Detail & Related papers  (2023-06-09T22:03:18Z)
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection [98.5549882883963]
  We present findings from the largest Federated ML study to-date, involving data from 71 healthcare institutions across 6 continents. We generate an automatic tumor boundary detector for the rare disease of glioblastoma. We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent.
  arXiv  Detail & Related papers  (2022-04-22T17:27:00Z)
• Multi-View Hypercomplex Learning for Breast Cancer Screening [15.961240921898586]
  We introduce multi-view hypercomplex learning, a novel learning paradigm for multi-view breast cancer classification.<n>Thanks to hypercomplex algebra, our models intrinsically capture both intra- and inter-view relations.<n>Our approach consistently outperforms state-of-the-art multi-view models.
  arXiv  Detail & Related papers  (2022-04-12T13:32:31Z)
• A Multi-modal Fusion Framework Based on Multi-task Correlation Learning for Cancer Prognosis Prediction [8.476394437053477]
  We present a multi-modal fusion framework based on multi-task correlation learning (MultiCoFusion) for survival analysis and cancer grade classification. We systematically evaluate our framework using glioma datasets from The Cancer Genome Atlas (TCGA)
  arXiv  Detail & Related papers  (2022-01-22T15:16:24Z)
• Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets [63.62764375279861]
  We propose an end-to-end MB tumor classification and explore transfer learning with various input sizes and matching network dimensions. Using a data set with 161 cases, we demonstrate that pre-trained EfficientNets with larger input resolutions lead to significant performance improvements.
  arXiv  Detail & Related papers  (2021-09-10T13:07:11Z)
• 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)
• A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis [49.3704402041314]
  We propose a multi-stage attentive transfer learning framework for improving COVID-19 diagnosis. Our proposed framework consists of three stages to train accurate diagnosis models through learning knowledge from multiple source tasks and data of different domains. Importantly, we propose a novel self-supervised learning method to learn multi-scale representations for lung CT images.
  arXiv  Detail & Related papers  (2021-01-14T01:39:19Z)
• A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning [49.86828302591469]
  We train >35,000 neural network models, sweeping over common featurization techniques. We found the RNA-seq to be highly redundant and informative even with subsets larger than 128 features.
  arXiv  Detail & Related papers  (2020-04-30T20:42:17Z)
• A Novel and Efficient Tumor Detection Framework for Pancreatic Cancer via CT Images [21.627818410241552]
  A novel and efficient pancreatic tumor detection framework is proposed in this paper. The contribution of the proposed method mainly consists of three components: Augmented Feature Pyramid networks, Self-adaptive Feature Fusion and a Dependencies Computation Module. Experimental results achieve competitive performance in detection with the AUC of 0.9455, which outperforms other state-of-the-art methods to our best of knowledge.
  arXiv  Detail & Related papers  (2020-02-11T15:48:22Z)

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.