Toward Auditable Neuro-Symbolic Reasoning in Pathology: SQL as an Explicit Trace of Evidence
This work addresses the need for verifiable evidence in clinical diagnosis by pathologists, though it is incremental as it builds on existing vision-language models with a novel SQL-based approach.
The paper tackles the problem of making automated pathology image analysis more interpretable and auditable by introducing an SQL-centered agentic framework that links cellular feature measurements to diagnostic conclusions through executable SQL queries, improving interpretability and decision traceability on two pathology visual question answering datasets.
Automated pathology image analysis is central to clinical diagnosis, but clinicians still ask which slide features drive a model's decision and why. Vision-language models can produce natural language explanations, but these are often correlational and lack verifiable evidence. In this paper, we introduce an SQL-centered agentic framework that enables both feature measurement and reasoning to be auditable. Specifically, after extracting human-interpretable cellular features, Feature Reasoning Agents compose and execute SQL queries over feature tables to aggregate visual evidence into quantitative findings. A Knowledge Comparison Agent then evaluates these findings against established pathological knowledge, mirroring how pathologists justify diagnoses from measurable observations. Extensive experiments evaluated on two pathology visual question answering datasets demonstrate our method improves interpretability and decision traceability while producing executable SQL traces that link cellular measurements to diagnostic conclusions.