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

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:this https URL

@article{albastaki2025_2504.18856,
  title={ Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation },
  author={ Shahad Albastaki and Anabia Sohail and Iyyakutti Iyappan Ganapathi and Basit Alawode and Asim Khan and Sajid Javed and Naoufel Werghi and Mohammed Bennamoun and Arif Mahmood },
  journal={arXiv preprint arXiv:2504.18856},
  year={ 2025 }
}