CellDX AI Autopilot: Agent-Guided Training and Deployment of Pathology Classifiers

TL;DR

CellDX AI Autopilot is a platform enabling pathology image classifier training and deployment via natural language, reducing technical barriers and hyperparameter tuning costs significantly.

Contribution

It introduces a novel agent-guided platform with pathology-specific skills for end-to-end model training and deployment, supporting non-experts and automating complex ML tasks.

Findings

Reduces hyperparameter tuning cost by over 30x.

Supports training on a large dataset of over 32,000 cases.

First system to expose pathology-specific agent skills for AI model training.

Abstract

Training AI models for computational pathology currently requires access to expensive whole-slide-image datasets, GPU infrastructure, deep expertise in machine learning, and substantial engineering effort. We present CellDX AI Autopilot, a platform that lets users -- from pathologists with no ML background to ML practitioners running many parallel experiments -- train, evaluate, and deploy whole-slide image classifiers through natural language interaction with an AI agent. The platform provides a structured set of agent skills that guide the user through dataset curation, automated hyperparameter tuning, multi-strategy model comparison, and human-in-the-loop deployment, all on a pre-built dataset of over 32,000 cases and 66,000 H&E-stained whole-slide images with pre-extracted features. We describe the agent skill architecture, the underlying Multiple Instance Learning (MIL) training framework supporting four classification strategies, and an iterative pairwise hyperparameter search (grid or seeded random) that reduces tuning cost by over 30x compared to exhaustive search. CellDX AI Autopilot is, to our knowledge, the first system to expose pathology-specialized agent skills and a pathology-specialized training platform to general-purpose AI agents (e.g. any LLM-based agent runtime), delivering end-to-end automated model training without requiring the agent itself to be domain-specific. The platform addresses both the ML-expertise bottleneck that limits adoption in diagnostic pathology and the engineering bottleneck that limits how many experiments a researcher can run cost-effectively.