Bridging Perception and Reasoning: An Evidence-Based Agentic System for Diagnosis and Treatment Recommendations of Vascular Anomalies

TL;DR

HevaDx is an AI system that improves diagnosis and treatment of vascular anomalies by combining visual analysis with evidence-based reasoning.

Contribution

HevaDx introduces a cooperative AI system that decouples visual perception from clinical reasoning using a new dataset and RAG-based therapeutic planning.

Findings

HevaDx achieves 94.8% top-3 diagnostic accuracy for vascular anomalies.

The system provides treatment recommendations with 83.3% accuracy.

The system bridges the 'reasoning gap' by using up-to-date clinical guidelines.

Abstract

Background: Vascular anomalies (VAs), including hemangiomas and vascular malformations, present a significant diagnostic challenge due to their high prevalence, complex classification (nearly 100 subtypes), and visual mimicry. Current Multimodal Large Language Models (MLLMs) struggle in this specialized domain, often failing to capture fine-grained visual features or lacking evidence-based reasoning. To address these limitations, we introduce HevaDx, an agentic diagnostic system that explicitly decouples visual perception from clinical reasoning. Methods: Leveraging a newly constructed large-scale dataset of VA patients, HevaDx employs a lightweight visual specialist for precise feature extraction and a reasoning specialist equipped with Retrieval-Augmented Generation (RAG) for therapeutic planning. This cooperative architecture mitigates the “reasoning gap” observed in end-to-end models by grounding decisions in up-to-date clinical guidelines. Results: Experimental results demonstrate that HevaDx achieves high performance with a top-3 diagnostic accuracy of 94.8% and a treatment recommendation accuracy of 83.3%. Conclusions: By bridging visual precision with transparent, verifiable logic, HevaDx offers a reliable framework for AI-assisted management of vascular anomalies.

Figures