Enhancing Pathological VLMs with Cross-scale Reasoning

2026-06-15

AI Summary

Existing pathological vision-language models lack an explicit cross-scale reasoning mechanism, hindering their ability to integrate multi-scale evidence—from tissue to cellular levels—for precise diagnosis. This work introduces the first training and evaluation framework tailored for multi-magnification reasoning in histopathology. It proposes a leakage-aware data construction pipeline, designs adversarial text filtering and constraint-guided question generation strategies, and establishes Scale-VQA, a high-quality multi-scale visual question answering benchmark. Building upon this, the authors develop ScaleReasoner-R1, a model trained via reinforcement learning. ScaleReasoner-R1 achieves state-of-the-art performance on the newly curated cross-scale benchmark and outperforms existing methods on multiple single-scale pathological VQA tasks, demonstrating that even limited cross-scale supervision can substantially enhance pathological understanding.

Abstract

Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to cellular morphology at higher magnification for accurate diagnosis. While existing pathological datasets for vision-language model (VLM) include various scales, they often lack an explicit cross-scale reasoning objective. This limitation prevents VLMs from capturing essential cross-scale representations and learning evidence-based reasoning. To bridge this gap, we introduce the first cross-scale training and evaluation paradigm that formulates pathology interpretation as multi-magnification reasoning. However, creating such a task reveals a critical challenge: multi-image visual question answering (VQA) is prone to text-only shortcuts, which allow models to guess answers using magnification-dependent artifacts rather than visual evidence. To address this, we propose a leakage-aware curation pipeline that combines adversarial text-only screening with constraint-guided question design. Using this pipeline, we construct Scale-VQA, a high-quality benchmark with 4,685 multiple-choice questions grounded in 2,537 pathology images across multiple magnification levels. Finally, we present ScaleReasoner-R1, a model trained via reinforcement learning to optimize performance on the cross-scale VQA task. ScaleReasoner-R1 achieves state-of-the-art performance on our cross-scale reasoning benchmark and generalizes to SOTA performance on established single-scale benchmarks. Findings suggest that even the limited cross-scale supervision can significantly improve pathological understanding. The code and demos will be open-sourced.

Problem

• cross-scale reasoning
• pathological VLMs
• multi-magnification
• visual question answering
• text-only shortcuts

Innovation

• cross-scale reasoning
• pathological VLM
• multi-magnification VQA
• leakage-aware curation
• reinforcement learning