TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning

• URL: http://arxiv.org/abs/2512.21331v2
• Date: Thu, 25 Dec 2025 17:05:10 GMT
• Title: TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning
• Abstract summary: TICON is a transformer-based tile representation contextualizer.<n>It produces rich, contextualized embeddings for ''any'' application in computational pathology.
• Score: 39.229282208556846
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The interpretation of small tiles in large whole slide images (WSI) often needs a larger image context. We introduce TICON, a transformer-based tile representation contextualizer that produces rich, contextualized embeddings for ''any'' application in computational pathology. Standard tile encoder-based pipelines, which extract embeddings of tiles stripped from their context, fail to model the rich slide-level information essential for both local and global tasks. Furthermore, different tile-encoders excel at different downstream tasks. Therefore, a unified model is needed to contextualize embeddings derived from ''any'' tile-level foundation model. TICON addresses this need with a single, shared encoder, pretrained using a masked modeling objective to simultaneously unify and contextualize representations from diverse tile-level pathology foundation models. Our experiments demonstrate that TICON-contextualized embeddings significantly improve performance across many different tasks, establishing new state-of-the-art results on tile-level benchmarks (i.e., HEST-Bench, THUNDER, CATCH) and slide-level benchmarks (i.e., Patho-Bench). Finally, we pretrain an aggregator on TICON to form a slide-level foundation model, using only 11K WSIs, outperforming SoTA slide-level foundation models pretrained with up to 350K WSIs.

Related papers

• From Patches to Patients: A study of the tile-to-slide performance transferability in Digital Pathology [5.356949046416353]
  We investigate whether efficient tile-level linear probing can serve as a reliable proxy for slide-level performance.<n>We benchmark 19 state-of-the-art FMs on 42 slide-level and 16 tile-level tasks.
  arXiv  Detail & Related papers  (2026-06-09T12:33:14Z)
• MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image [52.47434184153733]
  We introduce MulTaBench, a benchmark of 40 datasets split equally between image-tabular and text-tabular tasks.<n>We show that the gains from target-aware representation tuning generalize across both text and image modalities.
  arXiv  Detail & Related papers  (2026-05-11T14:12:05Z)
• LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models [19.89635786218384]
  Whole Slide Image (WSI) understanding is fundamentally challenging due to its gigapixel scale and the extreme sparsity of diagnostically relevant regions.<n>Existing slide-level multimodal large language models (MLLMs) for pathology rely on heavy slide-level encoders.<n>We introduce an efficient MLLM framework, called LoC-Path, that replaces the expensive slide-level encoder with redundancy-reducing modules.
  arXiv  Detail & Related papers  (2025-12-05T03:16:46Z)
• DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models [103.18486625853099]
  DEFT, Decompositional Efficient Fine-Tuning, adapts a pre-trained weight matrix by decomposing its update into two components.<n>We conduct experiments on the Dreambooth and Dreambench Plus datasets for personalization, the InsDet dataset for object and scene adaptation, and the VisualCloze dataset for a universal image generation framework.
  arXiv  Detail & Related papers  (2025-09-26T18:01:15Z)
• THUNDER: Tile-level Histopathology image UNDERstanding benchmark [33.01211128068007]
  THUNDER is a tile-level benchmark for digital pathology foundation models.<n>In this paper, we provide a comprehensive comparison of 23 foundation models on 16 different datasets.
  arXiv  Detail & Related papers  (2025-07-10T15:41:35Z)
• VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models [76.94378391979228]
  We introduce a new, more demanding task known as Interleaved Image-Text (IITC) This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA)
  arXiv  Detail & Related papers  (2024-06-14T17:59:40Z)
• Combining Graph Neural Network and Mamba to Capture Local and Global Tissue Spatial Relationships in Whole Slide Images [1.1813933389519358]
  In computational pathology, extracting spatial features from gigapixel whole slide images (WSIs) is a fundamental task. We introduce a model that combines a message-passing graph neural network (GNN) with a state space model (Mamba) to capture both local and global spatial relationships. The model's effectiveness was demonstrated in predicting progression-free survival among patients with early-stage lung adenocarcinomas.
  arXiv  Detail & Related papers  (2024-06-05T22:06:57Z)
• PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology [9.556246087301883]
  We present a slide-level foundation model for H&E-stained histopathology, PRISM, that builds on Virchow tile embeddings. PRISM produces slide-level embeddings with the ability to generate clinical reports, resulting in several modes of use. Using text prompts, PRISM achieves zero-shot cancer detection and sub-typing performance approaching that of a supervised aggregator model.
  arXiv  Detail & Related papers  (2024-05-16T16:59:12Z)
• Interfacing Foundation Models' Embeddings [131.0352288172788]
  We present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval.
  arXiv  Detail & Related papers  (2023-12-12T18:58:02Z)
• DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition [62.95223898214866]
  We explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field. With a pyramid architecture, we construct a Multi-Scale Dilated Transformer (DilateFormer) by stacking MSDA blocks at low-level stages and global multi-head self-attention blocks at high-level stages. Our experiment results show that our DilateFormer achieves state-of-the-art performance on various vision tasks.
  arXiv  Detail & Related papers  (2023-02-03T14:59:31Z)
• Modeling Image Composition for Complex Scene Generation [77.10533862854706]
  We present a method that achieves state-of-the-art results on layout-to-image generation tasks. After compressing RGB images into patch tokens, we propose the Transformer with Focal Attention (TwFA) for exploring dependencies of object-to-object, object-to-patch and patch-to-patch.
  arXiv  Detail & Related papers  (2022-06-02T08:34:25Z)

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.