Exploring General-Purpose Autonomous Multimodal Agents for Pathology Report Generation

TL;DR

This study evaluates the capabilities of agentic multimodal AI systems in autonomously analyzing histopathologic images for pathology report generation, highlighting their potential and current limitations compared to human experts.

Contribution

It introduces a novel application of agentic multimodal AI systems for autonomous pathology image analysis and compares their diagnostic accuracy to human pathologists.

Findings

AI systems achieved up to 28.6% accuracy with minimal info

Accuracy increased to 68.6% with morphological descriptions

Human experts achieved over 85% accuracy with similar data

Abstract

Recent advances in agentic artificial intelligence, i.e. systems capable of autonomous perception, reasoning, and tool use, offer new opportunities for digital pathology. In this pilot study, we evaluate whether two agentic multimodal AI systems (OpenAI's ChatGPT 5.0 in agentic mode, and H Company's Surfer) can autonomously navigate, describe, and interpret histopathologic features in digitized tissue slides on a slide viewing platform. A set of 35 veterinary pathology cases, curated for training purposes, was used as the test dataset. The agent was tasked with autonomously exploring whole-slide images using a web-based slide viewer, identifying salient tissue structures, generating descriptive summaries, and proposing provisional diagnoses. We fed different prompts to explore three scenarios: 1) analysis without knowledge of the signalment, 2) analysis with organ and species provided, and 3) diagnosis based on a morphological description provided. All outputs were reviewed and validated by a board-certified pathologist for accuracy and diagnostic consistency. We further tasked another board-certified pathologist with the same task to establish a baseline. We found the systems to yield accurate diagnoses in up to 28.6% of cases with only images, signalment and organ provided, and up to 68.6% when a morphological description was provided. With only the WSI provided, the models were only correct in up to 5.7% of cases. The human expert, on the other hand, achieved 85.7% diagnostic accuracy with only a single WSI, and 88.6% when also signalment and organ was provided. The study demonstrates that while the agentic AI system can meaningfully engage with web-based slide viewing software to assess complex visual pathology data and produce contextually aligned feature descriptions, diagnostic precision remains limited compared with a human expert.