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

2025/06/18 by Qian Li, Li, Qian, Feng Liu +7
Medicine · Engineering · Physics and Astronomy · #Radiomics and Machine Learning in Medical Imaging #Medical Imaging and Analysis #Advanced Radiotherapy Techniques

paper · pdf · doi:10.48550/arxiv.2506.15279

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.

Citations

• Depth-Driven Geometric Prompt Learning for Laparoscopic Liver Landmark Detection
• An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion
• SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation
• How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images
• Ladder Fine-tuning approach for SAM integrating complementary network
• DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
• Customized Segment Anything Model for Medical Image Segmentation
• Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
• Micrograph segmentations for DDEVD
• Segment Anything
• Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
• Text Spotting Transformers
• ABLaneNet
• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
• Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation
• ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
• Deep High-Resolution Representation Learning for Visual Recognition
• Deep High-Resolution Representation Learning for Visual Recognition
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• U-Net: Convolutional Networks for Biomedical Image Segmentation

Related

• Depth-Driven Geometric Prompt Learning for Laparoscopic Liver Landmark Detection
• An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion
• PIVOTS: Aligning unseen Structures using Preoperative to Intraoperative Volume-To-Surface Registration for Liver Navigation
• Subsampled Randomized Fourier GaLore for Adapting Foundation Models in Depth-Driven Liver Landmark Segmentation
• Topology-Constrained Learning for Efficient Laparoscopic Liver Landmark Detection