Search papers, labs, and topics across Lattice.
This paper introduces PathScale-R1, a novel framework for cross-scale reasoning in pathological image analysis that integrates both global tissue architecture and cellular morphology. By developing a benchmark and training strategies that mitigate shortcut learning, the authors create a robust visual question answering (VQA) system, PathScale-VQA, with over 10,000 questions designed to assess multi-magnification reasoning. The results show that PathScale-R1 achieves state-of-the-art performance on cross-scale tasks while also transferring effectively to traditional single-scale pathology VQA, highlighting its clinical relevance.
PathScale-R1 outperforms existing models in multi-scale reasoning, revealing that integrating diverse magnification levels can significantly enhance diagnostic accuracy.
Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification. However, existing pathology benchmarks and vision-language models (VLMs) are still largely developed under single-scale settings, limiting their ability to learn clinically meaningful multi-magnification reasoning. Moreover, naively constructed visual question answering (VQA) tasks may be susceptible to text-only or superficial visual shortcuts, leading to unreliable assessments of visual understanding. To address these limitations, we introduce a benchmark and training framework for shortcut-resistant cross-scale pathology reasoning. We design an Adversarial Text-only Screening strategy for semantic reasoning questions and a Structure-controlled Distractor Sampling strategy for visual grounding questions, encouraging models to rely on cross-scale visual evidence. Based on this pipeline, we construct PathScale-VQA, a high-quality cross-scale pathology VQA benchmark with 10,373 multiple-choice questions grounded in 1,368 diagnostic paths across multiple magnification levels. Building on the semantic reasoning set, PathScale-R1 is optimized through Difficulty-driven Reasoning Distillation supervised fine-tuning followed by reinforcement learning with a Scale-aware Reasoning Structure reward, which encourages the use of evidence across magnifications. Extensive experiments demonstrate state-of-the-art performance of PathScale-R1 on cross-scale reasoning tasks and effective transfer to conventional single-scale pathology VQA. Our code is available at https://github.com/iMVR-PL/PathScale-R1.
