TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created TopoAgent, a system that uses a large language model to pick the best topological features for analyzing medical images. Unlike past methods that use just one way to describe image shapes, their system tries many different approaches and learns which works best without extra training on specific tasks. TopoAgent works by observing images, reasoning about the best features, acting to extract those features, and improving over time using memory. This helps capture complex shape information often missed by usual deep learning methods.
Topological Data AnalysisPersistent HomologyPersistence DiagramsLarge Language ModelsMedical Image AnalysisFeature ExtractionTopological DescriptorsMachine LearningAgentic Framework
Authors
Guangyu Meng, Pengfei Gu, Xueyang Li, Yiyu Shi, Erin Wolf Chambers, Danny Z. Chen
Abstract
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.