TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
For medical imaging researchers, TopoAgent automates the selection of topological descriptors, a process that previously required expert knowledge and manual tuning, potentially improving downstream task performance.
TopoAgent is an LLM-based agentic framework that automatically selects and configures the optimal topological descriptor for a given medical image dataset, eliminating the need for manual selection and task-specific training. It achieves this through a Perception-Reasoning-Action-Reflection loop with 21 tools and dual memory, distilled from evaluations on 15 descriptors across 26 datasets.
Topological data analysis (TDA), particularly persistent homology (PH), captures geometric structural properties in medical images (e.g., connected components, loops, shape characteristics), which conventional pixel-level deep learning approaches often neglect. While many topological descriptors are known for converting persistence diagrams (PDs) or raw images into topological feature vectors, existing methods mostly default to a single fixed descriptor (e.g., persistence images), leaving the diversity of topological representations largely unexplored. To the best of our knowledge, there is no known large language model (LLM)-based agentic framework that can automatically determine the most suitable topological descriptors for a given image dataset and produce the corresponding topological feature vectors for downstream tasks. To fill this gap, we propose \textbf{TopoAgent}, an LLM-based agentic framework that automates topology learning for medical image analysis.TopoAgent operates through a Perception--Reasoning--Action--Reflection loop supported by 21 domain-specific tools and dual memory that accumulates experience across runs. Its skill set is distilled from systematic evaluation of 15 topological descriptors across 26 datasets with six classifiers. TopoAgent analyzes input images and their topological characteristics, reasons about which topological descriptors best suit the input, and determines the optimal descriptor and its configuration, all without task-specific training.