NOVA: An Agentic Framework for Automated Histopathology Analysis and Discovery

TL;DR

NOVA is an innovative agentic framework that automates histopathology analysis by translating scientific queries into executable pipelines, integrating numerous tools, and enabling scalable discovery through iterative code generation and testing.

Contribution

The paper introduces NOVA, a novel framework that automates complex histopathology workflows and creates new tools on demand, advancing automated biomedical analysis.

Findings

NOVA outperforms baseline coding agents in quantitative evaluations.

SlideQuest benchmark effectively assesses multi-step reasoning in biomedical analysis.

Case study demonstrates NOVA's potential in linking morphology to prognostic subtypes.

Abstract

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.