NOVA: An Agentic Framework for Automated Histopathology Analysis and Discovery
This addresses the problem of limited accessibility to histopathology analysis for researchers and clinicians by automating workflows, though it is incremental as it builds on existing tools and agentic methods.
The paper tackles the complexity and inaccessibility of digitized histopathology analysis by introducing NOVA, an agentic framework that translates scientific queries into executable analysis pipelines, outperforming coding-agent baselines on a new 90-question benchmark and demonstrating potential for scalable discovery in a pathologist-verified case study.
Digitized histopathology analysis involves complex, time-intensive workflows and specialized expertise, limiting its accessibility. We introduce NOVA, an agentic framework that translates scientific queries into executable analysis pipelines by iteratively generating and running Python code. NOVA integrates 49 domain-specific tools (e.g., nuclei segmentation, whole-slide encoding) built on open-source software, and can also create new tools ad hoc. To evaluate such systems, we present SlideQuest, a 90-question benchmark -- verified by pathologists and biomedical scientists -- spanning data processing, quantitative analysis, and hypothesis testing. Unlike prior biomedical benchmarks focused on knowledge recall or diagnostic QA, SlideQuest demands multi-step reasoning, iterative coding, and computational problem solving. Quantitative evaluation shows NOVA outperforms coding-agent baselines, and a pathologist-verified case study links morphology to prognostically relevant PAM50 subtypes, demonstrating its scalable discovery potential.