Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Albastaki, Shahad, Sohail, Anabia, Ganapathi, Iyyakutti Iyappan, Alawode, Basit, Khan, Asim, Javed, Sajid, Werghi, Naoufel, Bennamoun, Mohammed, Mahmood, Arif
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913809971544064
author Albastaki, Shahad
Sohail, Anabia
Ganapathi, Iyyakutti Iyappan
Alawode, Basit
Khan, Asim
Javed, Sajid
Werghi, Naoufel
Bennamoun, Mohammed
Mahmood, Arif
author_facet Albastaki, Shahad
Sohail, Anabia
Ganapathi, Iyyakutti Iyappan
Alawode, Basit
Khan, Asim
Javed, Sajid
Werghi, Naoufel
Bennamoun, Mohammed
Mahmood, Arif
contents In Computational Pathology (CPath), the introduction of Vision-Language Models (VLMs) has opened new avenues for research, focusing primarily on aligning image-text pairs at a single magnification level. However, this approach might not be sufficient for tasks like cancer subtype classification, tissue phenotyping, and survival analysis due to the limited level of detail that a single-resolution image can provide. Addressing this, we propose a novel multi-resolution paradigm leveraging Whole Slide Images (WSIs) to extract histology patches at multiple resolutions and generate corresponding textual descriptions through advanced CPath VLM. We introduce visual-textual alignment at multiple resolutions as well as cross-resolution alignment to establish more effective text-guided visual representations. Cross-resolution alignment using a multimodal encoder enhances the model's ability to capture context from multiple resolutions in histology images. Our model aims to capture a broader range of information, supported by novel loss functions, enriches feature representation, improves discriminative ability, and enhances generalization across different resolutions. Pre-trained on a comprehensive TCGA dataset with 34 million image-language pairs at various resolutions, our fine-tuned model outperforms state-of-the-art (SOTA) counterparts across multiple datasets and tasks, demonstrating its effectiveness in CPath. The code is available on GitHub at: https://github.com/BasitAlawode/MR-PLIP
format Preprint
id arxiv_https___arxiv_org_abs_2504_18856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
Albastaki, Shahad
Sohail, Anabia
Ganapathi, Iyyakutti Iyappan
Alawode, Basit
Khan, Asim
Javed, Sajid
Werghi, Naoufel
Bennamoun, Mohammed
Mahmood, Arif
Computer Vision and Pattern Recognition
In Computational Pathology (CPath), the introduction of Vision-Language Models (VLMs) has opened new avenues for research, focusing primarily on aligning image-text pairs at a single magnification level. However, this approach might not be sufficient for tasks like cancer subtype classification, tissue phenotyping, and survival analysis due to the limited level of detail that a single-resolution image can provide. Addressing this, we propose a novel multi-resolution paradigm leveraging Whole Slide Images (WSIs) to extract histology patches at multiple resolutions and generate corresponding textual descriptions through advanced CPath VLM. We introduce visual-textual alignment at multiple resolutions as well as cross-resolution alignment to establish more effective text-guided visual representations. Cross-resolution alignment using a multimodal encoder enhances the model's ability to capture context from multiple resolutions in histology images. Our model aims to capture a broader range of information, supported by novel loss functions, enriches feature representation, improves discriminative ability, and enhances generalization across different resolutions. Pre-trained on a comprehensive TCGA dataset with 34 million image-language pairs at various resolutions, our fine-tuned model outperforms state-of-the-art (SOTA) counterparts across multiple datasets and tasks, demonstrating its effectiveness in CPath. The code is available on GitHub at: https://github.com/BasitAlawode/MR-PLIP
title Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.18856