EXAONE Path 2.5: Pathology Foundation Model with Multi-Omics Alignment

• URL: http://arxiv.org/abs/2512.14019v1
• Date: Tue, 16 Dec 2025 02:31:53 GMT
• Title: EXAONE Path 2.5: Pathology Foundation Model with Multi-Omics Alignment
• Authors: Juseung Yun, Sunwoo Yu, Sumin Ha, Jonghyun Kim, Janghyeon Lee, Jongseong Jang, Soonyoung Lee,
• Abstract summary: 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.
• Score: 7.030162358506499
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Cancer progression arises from interactions across multiple biological layers, especially beyond morphological and across molecular layers that remain invisible to image-only models. To capture this broader biological landscape, we present EXAONE Path 2.5, a pathology foundation model that jointly models histologic, genomic, epigenetic and transcriptomic modalities, producing an integrated patient representation that reflects tumor biology more comprehensively. Our approach incorporates three key components: (1) multimodal SigLIP loss enabling all-pairwise contrastive learning across heterogeneous modalities, (2) a fragment-aware rotary positional encoding (F-RoPE) module that preserves spatial structure and tissue-fragment topology in WSI, and (3) domain-specialized internal foundation models for both WSI and RNA-seq to provide biologically grounded embeddings for robust multimodal alignment. We evaluate EXAONE Path 2.5 against six leading pathology foundation models across two complementary benchmarks: an internal real-world clinical dataset and the Patho-Bench benchmark covering 80 tasks. Our framework demonstrates high data and parameter efficiency, achieving on-par performance with state-of-the-art foundation models on Patho-Bench while exhibiting the highest adaptability in the internal clinical setting. These results highlight the value of biologically informed multimodal design and underscore the potential of integrated genotype-to-phenotype modeling for next-generation precision oncology.

Related papers

• CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis [23.45449218534003]
  We present Cross-modal Adaptive Region (CARE), a foundation model for pathology that automatically partitions whole-slide images into morphologically relevant regions.<n>Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks.
  arXiv  Detail & Related papers  (2026-02-25T07:01:54Z)
• Benchmarking Computational Pathology Foundation Models For Semantic Segmentation [0.0]
  Concatenating features from CONCH, PathDino and CellViT outperformed individual models across all the datasets by 7.95%.<n>We show that the vision language foundation model, CONCH performed the best across datasets when compared to vision-only foundation models.
  arXiv  Detail & Related papers  (2026-02-21T08:00:46Z)
• Atlas 2 - Foundation models for clinical deployment [58.17064730809252]
  We present Atlas 2, Atlas 2-B, and Atlas 2-S, three pathology vision foundation models which bridge these shortcomings.<n>Our models were trained on the largest pathology foundation model dataset to date comprising 5.5 million histopathology whole slide images.
  arXiv  Detail & Related papers  (2026-01-08T17:37:00Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• 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)
• HiFusion: Hierarchical Intra-Spot Alignment and Regional Context Fusion for Spatial Gene Expression Prediction from Histopathology [7.982889842329205]
  HiFusion is a novel deep learning framework that integrates two complementary components.<n>We show that HiFusion achieves state-of-the-art performance across both 2D slide-wise cross-validation and more challenging 3D sample-specific scenarios.<n>These results underscore HiFusion's potential as a robust, accurate, and scalable solution for ST inference from routine histopathology.
  arXiv  Detail & Related papers  (2025-11-17T04:47:39Z)
• Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification [0.0]
  We leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets.<n>We incorporated ConvNeXt V2, a state-of-the-art convolutional neural network architecture, to complement PFMs.<n>We ensembled multiple PFMs to integrate complementary morphological insights, achieving balanced accuracy on the Preliminary Evaluation Phase dataset.
  arXiv  Detail & Related papers  (2025-08-29T03:24:57Z)
• AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models [49.550545038402184]
  We propose AdaFusion, a novel prompt-guided inference framework.<n>Our method compresses and aligns tile-level features from diverse models.<n>AdaFusion consistently surpasses individual PFMs across both classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-07T07:09:31Z)
• GRASPing Anatomy to Improve Pathology Segmentation [67.98147643529309]
  We introduce GRASP, a modular plug-and-play framework that enhances pathology segmentation models.<n>We evaluate GRASP on two PET/CT datasets, conduct systematic ablation studies, and investigate the framework's inner workings.
  arXiv  Detail & Related papers  (2025-08-05T12:26:36Z)
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention [57.044719143401664]
  Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease.<n>We present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention.<n>Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance.
  arXiv  Detail & Related papers  (2025-03-01T07:02:30Z)
• UNICORN: A Deep Learning Model for Integrating Multi-Stain Data in Histopathology [2.9389205138207277]
  UNICORN is a multi-modal transformer capable of processing multi-stain histopathology for atherosclerosis severity class prediction. The architecture comprises a two-stage, end-to-end trainable model with specialized modules utilizing transformer self-attention blocks. UNICORN achieved a classification accuracy of 0.67, outperforming other state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-26T12:13:52Z)
• HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis [19.04633470168871]
  Panoramic image segmentation in computational pathology presents a remarkable challenge due to the morphologically complex and variably scaled anatomy. In this paper, we propose a novel Hierarchical Adaptive Taxonomy (HATs) method, which is designed to thoroughly segment panoramic views of kidney structures by leveraging detailed anatomical insights. Our approach entails (1) the innovative HATs technique which translates spatial relationships among 15 distinct object classes into a versatile "plug-and-play" loss function that spans across regions, functional units, and cells, (2) the incorporation of anatomical hierarchies and scale considerations into a unified simple matrix representation for all panoramic entities, and (3) the
  arXiv  Detail & Related papers  (2024-06-30T05:35:26Z)

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.