BCRNet: Enhancing Landmark Detection in Laparoscopic Liver Surgery via Bezier Curve Refinement

2025-06-18

AI Summary

In laparoscopic liver resection, curved anatomical landmarks—such as the hepatic hilum—are difficult to localize precisely in 2D laparoscopic images, limiting the accuracy of AR-guided 2D–3D registration. To address this, we propose the first end-to-end Bézier curve detection framework tailored for curved anatomical structures. Our method introduces two key innovations: (1) adaptive Bézier curve initialization, generating geometrically plausible initial curve proposals; and (2) a hierarchical iterative refinement mechanism that fuses multimodal features and multi-scale contextual information to achieve pixel-accurate curve regression. Evaluated on the L3D and P2ILF datasets, our approach reduces curve localization error by 12.7% over state-of-the-art methods. Clinical validation confirms its robustness and generalizability under intraoperative conditions, meeting real-time navigation requirements.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Laparoscopic liver surgery, while minimally invasive, poses significant challenges in accurately identifying critical anatomical structures. Augmented reality (AR) systems, integrating MRI/CT with laparoscopic images based on 2D-3D registration, offer a promising solution for enhancing surgical navigation. A vital aspect of the registration progress is the precise detection of curvilinear anatomical landmarks in laparoscopic images. In this paper, we propose BCRNet (Bezier Curve Refinement Net), a novel framework that significantly enhances landmark detection in laparoscopic liver surgery primarily via the Bezier curve refinement strategy. The framework starts with a Multi-modal Feature Extraction (MFE) module designed to robustly capture semantic features. Then we propose Adaptive Curve Proposal Initialization (ACPI) to generate pixel-aligned Bezier curves and confidence scores for reliable initial proposals. Additionally, we design the Hierarchical Curve Refinement (HCR) mechanism to enhance these proposals iteratively through a multi-stage process, capturing fine-grained contextual details from multi-scale pixel-level features for precise Bezier curve adjustment. Extensive evaluations on the L3D and P2ILF datasets demonstrate that BCRNet outperforms state-of-the-art methods, achieving significant performance improvements. Code will be available.

Problem

• Accurate detection of curvilinear landmarks in laparoscopic liver surgery
• Enhancing 2D-3D registration for augmented reality surgical navigation
• Improving Bezier curve refinement for precise anatomical structure identification

Innovation

• Bezier curve refinement for landmark detection
• Multi-modal feature extraction module
• Hierarchical curve refinement mechanism