UltraHiT: A Hierarchical Transformer Architecture for Generalizable Internal Carotid Artery Robotic Ultrasonography

2025-09-17

AI Summary

Automated scanning of the internal carotid artery (ICA) in carotid ultrasound remains challenging due to its deep anatomical location, tortuous course, and high inter-subject morphological variability. To address this, we propose UltraHiT—a hierarchical Transformer architecture—and introduce the first large-scale robotic ultrasound dataset specifically curated for ICA scanning. UltraHiT features a morphology-aware hierarchical decision mechanism that jointly performs high-level vascular variation assessment and low-level robotic action planning, enabling adaptive responses to both normal and pathological vessel structures. Furthermore, we incorporate a causal Transformer to support higher-order variation recognition, real-time adaptive correction, and history-conditional dynamic prediction. Evaluated on unseen subjects, UltraHiT achieves a 95% ICA localization success rate—substantially outperforming existing baselines—and demonstrates strong generalization capability and clinical deployment potential.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Carotid ultrasound is crucial for the assessment of cerebrovascular health, particularly the internal carotid artery (ICA). While previous research has explored automating carotid ultrasound, none has tackled the challenging ICA. This is primarily due to its deep location, tortuous course, and significant individual variations, which greatly increase scanning complexity. To address this, we propose a Hierarchical Transformer-based decision architecture, namely UltraHiT, that integrates high-level variation assessment with low-level action decision. Our motivation stems from conceptualizing individual vascular structures as morphological variations derived from a standard vascular model. The high-level module identifies variation and switches between two low-level modules: an adaptive corrector for variations, or a standard executor for normal cases. Specifically, both the high-level module and the adaptive corrector are implemented as causal transformers that generate predictions based on the historical scanning sequence. To ensure generalizability, we collected the first large-scale ICA scanning dataset comprising 164 trajectories and 72K samples from 28 subjects of both genders. Based on the above innovations, our approach achieves a 95% success rate in locating the ICA on unseen individuals, outperforming baselines and demonstrating its effectiveness. Our code will be released after acceptance.

Problem

• Automating internal carotid artery robotic ultrasound scanning
• Addressing deep location and individual anatomical variations
• Ensuring generalizability across diverse patient populations

Innovation

• Hierarchical Transformer architecture for ICA scanning
• Causal transformers for historical sequence predictions
• Large-scale dataset for generalizable robotic ultrasonography