From Linear Probing to Joint-Weighted Token Hierarchy: A Foundation Model Bridging Global and Cellular Representations in Biomarker Detection

• URL: http://arxiv.org/abs/2511.05150v1
• Date: Fri, 07 Nov 2025 11:05:36 GMT
• Title: From Linear Probing to Joint-Weighted Token Hierarchy: A Foundation Model Bridging Global and Cellular Representations in Biomarker Detection
• Authors: Jingsong Liu, Han Li, Nassir Navab, Peter J. Schüffler,
• Abstract summary: AI-based biomarkers can infer molecular features directly from hematoxylin & eosin (H&E) slides.<n>Most pathology foundation models (PFMs) rely on global patch-level embeddings and overlook cell-level morphology.<n>We present a PFM model, JWTH, which integrates large-scale self-supervised pretraining with cell-centric post-tuning and attention pooling to fuse local and global tokens.
• Score: 44.3895875409365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI-based biomarkers can infer molecular features directly from hematoxylin & eosin (H&E) slides, yet most pathology foundation models (PFMs) rely on global patch-level embeddings and overlook cell-level morphology. We present a PFM model, JWTH (Joint-Weighted Token Hierarchy), which integrates large-scale self-supervised pretraining with cell-centric post-tuning and attention pooling to fuse local and global tokens. Across four tasks involving four biomarkers and eight cohorts, JWTH achieves up to 8.3% higher balanced accuracy and 1.2% average improvement over prior PFMs, advancing interpretable and robust AI-based biomarker detection in digital pathology.

Related papers

• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• EXAONE Path 2.5: Pathology Foundation Model with Multi-Omics Alignment [7.030162358506499]
  We present EXAONE Path 2.5, a pathology foundation model that jointly models histologic, genomic, epigenetic and transcriptomic modalities.<n>We evaluate EXAONE Path 2.5 against six leading pathology foundation models across two complementary benchmarks.
  arXiv  Detail & Related papers  (2025-12-16T02:31:53Z)
• PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer [54.958921946378304]
  We introduce PanFoMa, a lightweight hybrid neural network that combines the strengths of Transformers and state-space models.<n>PanFoMa consists of a front-end local-context encoder with shared self-attention layers to capture complex, order-independent gene interactions.<n>We also construct a large-scale pan-cancer single-cell benchmark, PanFoMaBench, containing over 3.5 million high-quality cells.
  arXiv  Detail & Related papers  (2025-12-02T08:31:31Z)
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling [74.25438319700929]
  We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that models local-global dependencies between molecules and cellular responses.<n> evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines.<n>Results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations.
  arXiv  Detail & Related papers  (2025-11-26T07:15:00Z)
• A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches [35.18016233072556]
  We present a machine learning pipeline for biomarker discovery in Multiple Sclerosis (MS)<n>After robust preprocessing we trained an XGBoost classifier optimized via Bayesian search.<n>Our comparison revealed both overlapping and unique biomarkers between SHAP and DEA, suggesting complementary strengths.<n>This study highlights the value of combining explainable AI (xAI) with traditional statistical methods to gain deeper insights into disease mechanism.
  arXiv  Detail & Related papers  (2025-09-26T15:31:34Z)
• The Next Layer: Augmenting Foundation Models with Structure-Preserving and Attention-Guided Learning for Local Patches to Global Context Awareness in Computational Pathology [23.32822092398391]
  We present EAGLE-Net, a structure-preserving, attention-guided MIL architecture designed to augment prediction and interpretability.<n>We benchmarked it on large pan-cancer datasets, including 3 cancer types for classification (10,260 slides) and 7 cancer types for survival prediction (4,172 slides)
  arXiv  Detail & Related papers  (2025-08-27T14:19:38Z)
• FoundBioNet: A Foundation-Based Model for IDH Genotyping of Glioma from Multi-Parametric MRI [1.4249472316161877]
  We propose a Foundation-based Biomarker Network (FoundBioNet) to noninvasively predict IDH mutation status from multi-parametric MRI.<n>Our model was trained and validated on a diverse, multi-center cohort of 1705 glioma patients from six public datasets.<n>Our model achieved AUCs of 90.58%, 88.08%, 65.41%, and 80.31% on independent test sets from EGD, TCGA, Ivy GAP, RHUH, and UPenn.
  arXiv  Detail & Related papers  (2025-08-09T00:08:10Z)
• Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation [46.36100528165335]
  Photoplethysmography and electrocardiography can potentially enable continuous blood pressure (BP) monitoring.<n>Yet accurate and robust machine learning (ML) models remains challenging due to variability in data quality and patient-specific factors.<n>In this work, we investigate whether a model pre-trained on one modality can effectively be exploited to improve the accuracy of a different signal type.<n>Our approach achieves near state-of-the-art accuracy for diastolic BP and surpasses by 1.5x the accuracy of prior works for systolic BP.
  arXiv  Detail & Related papers  (2025-02-10T13:33:12Z)
• Augmenting Biomedical Named Entity Recognition with General-domain Resources [47.24727904076347]
  Training a neural network-based biomedical named entity recognition (BioNER) model usually requires extensive and costly human annotations.<n>We propose GERBERA, a simple-yet-effective method that utilized general-domain NER datasets for training.<n>We systematically evaluated GERBERA on five datasets of eight entity types, collectively consisting of 81,410 instances.
  arXiv  Detail & Related papers  (2024-06-15T15:28:02Z)
• Deep Learning Predicts Biomarker Status and Discovers Related Histomorphology Characteristics for Low-Grade Glioma [21.281553456323998]
  Biomarker detection is an indispensable part in the diagnosis and treatment of low-grade glioma (LGG) We propose an interpretable deep learning pipeline to predict the status of five biomarkers in LGG using only hematoxylin and eosin-stained whole slide images and slide-level biomarker status labels. Our pipeline not only provides a novel approach for biomarker prediction, enhancing the applicability of molecular treatments for LGG patients but also facilitates the discovery of new mechanisms in molecular functionality and LGG progression.
  arXiv  Detail & Related papers  (2023-10-11T13:05:33Z)
• Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations [68.32093648671496]
  We introduce GODE, which accounts for the dual-level structure inherent in molecules.<n> Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph.<n>By pre-training two GNNs on different graph structures, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures.
  arXiv  Detail & Related papers  (2023-06-02T15:49:45Z)
• BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks [68.39821375903591]
  Generalist AI holds the potential to address limitations due to its versatility in interpreting different data types. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model.
  arXiv  Detail & Related papers  (2023-05-26T17:14:43Z)

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.