Topology-Constrained Learning for Efficient Laparoscopic Liver Landmark Detection

2025-07-01

AI Summary

Automated detection of hepatic landmarks—such as tubular structures and intraoperative dynamic deformations—remains challenging in laparoscopic liver surgery. To address this, we propose TopoNet, a topology-constrained learning framework. Methodologically, TopoNet innovatively fuses RGB-D dual-modal input, employs a snake-shaped CNN dual-path encoder, and introduces a boundary-aware topological fusion (BTF) module. It further incorporates centerline guidance and a topological persistence loss to jointly enforce geometric and topological constraints for end-to-end landmark localization. Evaluated on the L3D and P2ILF datasets, TopoNet achieves significantly improved detection accuracy with low computational overhead, demonstrating strong efficacy and robustness for real-time anatomical guidance in clinical laparoscopic liver procedures.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Liver landmarks provide crucial anatomical guidance to the surgeon during laparoscopic liver surgery to minimize surgical risk. However, the tubular structural properties of landmarks and dynamic intraoperative deformations pose significant challenges for automatic landmark detection. In this study, we introduce TopoNet, a novel topology-constrained learning framework for laparoscopic liver landmark detection. Our framework adopts a snake-CNN dual-path encoder to simultaneously capture detailed RGB texture information and depth-informed topological structures. Meanwhile, we propose a boundary-aware topology fusion (BTF) module, which adaptively merges RGB-D features to enhance edge perception while preserving global topology. Additionally, a topological constraint loss function is embedded, which contains a center-line constraint loss and a topological persistence loss to ensure homotopy equivalence between predictions and labels. Extensive experiments on L3D and P2ILF datasets demonstrate that TopoNet achieves outstanding accuracy and computational complexity, highlighting the potential for clinical applications in laparoscopic liver surgery. Our code will be available at https://github.com/cuiruize/TopoNet.

Problem

• Detect liver landmarks in laparoscopic surgery accurately
• Address challenges from tubular structures and deformations
• Enhance edge perception while preserving global topology

Innovation

• Snake-CNN dual-path encoder for RGB-D data
• Boundary-aware topology fusion module
• Topological constraint loss for homotopy equivalence