PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs
This addresses the challenge of consistent diagnostic reasoning in computational pathology by enabling better knowledge integration, though it is incremental as it builds on existing MLLM frameworks.
The paper tackles the problem of integrating structured pathology knowledge into multimodal large language models (MLLMs) for computational pathology, proposing PathMem, which achieves state-of-the-art performance with improvements such as 12.8% in WSI-Precision and 9.7% in open-ended diagnosis over prior models.
Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading criteria, and clinical evidence. In practice, diagnostic reasoning requires linking morphological evidence with formal diagnostic and grading criteria. Although multimodal large language models (MLLMs) demonstrate strong vision language reasoning capabilities, they lack explicit mechanisms for structured knowledge integration and interpretable memory control. As a result, existing models struggle to consistently incorporate pathology-specific diagnostic standards during reasoning. Inspired by the hierarchical memory process of human pathologists, we propose PathMem, a memory-centric multimodal framework for pathology MLLMs. PathMem organizes structured pathology knowledge as a long-term memory (LTM) and introduces a Memory Transformer that models the dynamic transition from LTM to working memory (WM) through multimodal memory activation and context-aware knowledge grounding, enabling context-aware memory refinement for downstream reasoning. PathMem achieves SOTA performance across benchmarks, improving WSI-Bench report generation (12.8% WSI-Precision, 10.1% WSI-Relevance) and open-ended diagnosis by 9.7% and 8.9% over prior WSI-based models.