Epicardium Prompt-guided Real-time Cardiac Ultrasound Frame-to-volume Registration

2024-06-20

International Conference on Medical Image Computing and Computer-Assisted Intervention

AI Summary

Addressing the challenge of cross-dimensional registration between intraoperative 2D echocardiography and preoperative 3D anatomical images in cardiac interventional procedures—complicated by low signal-to-noise ratio, high inter-frame similarity, and substantial anatomical deformation—this paper proposes CU-Reg, a lightweight end-to-end registration network. CU-Reg innovatively incorporates an epicardial anatomical cue guidance mechanism, synergistically integrating voxel-wise local-global feature aggregation, sparse-dense feature interaction, and inter-frame discriminative regularization, under a hybrid supervision strategy. Evaluated on the CAMUS dataset, CU-Reg achieves sub-pixel registration accuracy (mean target registration error < 1.2 mm) and real-time inference speed (>30 FPS), significantly outperforming state-of-the-art methods. To our knowledge, it is the first approach to simultaneously satisfy clinical requirements for robustness, accuracy, and efficiency in real-time image-guided navigation.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

A comprehensive guidance view for cardiac interventional surgery can be provided by the real-time fusion of the intraoperative 2D images and preoperative 3D volume based on the ultrasound frame-to-volume registration. However, cardiac ultrasound images are characterized by a low signal-to-noise ratio and small differences between adjacent frames, coupled with significant dimension variations between 2D frames and 3D volumes to be registered, resulting in real-time and accurate cardiac ultrasound frame-to-volume registration being a very challenging task. This paper introduces a lightweight end-to-end Cardiac Ultrasound frame-to-volume Registration network, termed CU-Reg. Specifically, the proposed model leverages epicardium prompt-guided anatomical clues to reinforce the interaction of 2D sparse and 3D dense features, followed by a voxel-wise local-global aggregation of enhanced features, thereby boosting the cross-dimensional matching effectiveness of low-quality ultrasound modalities. We further embed an inter-frame discriminative regularization term within the hybrid supervised learning to increase the distinction between adjacent slices in the same ultrasound volume to ensure registration stability. Experimental results on the reprocessed CAMUS dataset demonstrate that our CU-Reg surpasses existing methods in terms of registration accuracy and efficiency, meeting the guidance requirements of clinical cardiac interventional surgery.

Problem

• Image Registration
• Cardiac Interventions
• 2D Ultrasound 3D Preoperative Imaging

Innovation

• CU-Reg Network
• Epicardial Feature Navigation
• Local and Global Precise Matching