Top-K Maximum Intensity Projection Priors for 3D Liver Vessel Segmentation

2025-03-05

AI Summary

In preoperative planning for hepatic resection, conventional 3D liver vessel segmentation often fails to preserve global topological structure. To address this, we propose a physics-driven, topology-preserving segmentation method. Our core innovation lies in discretizing the integral physical properties of CT imaging into a differentiable, geometrically interpretable Top-K Maximum Intensity Projection (Top-K MIP), which encodes vessel connectivity as a structural prior. This prior is then integrated as a topology-guided signal into a conditional diffusion model to generate anatomically plausible and topologically consistent 3D vascular trees—without requiring post-processing. Evaluated on the 3D-ircadb-01 dataset, our method achieves statistically significant improvements in Dice score, IoU, and sensitivity over state-of-the-art 2D and 3D convolutional models. Results demonstrate that synergistically combining physics-informed priors with generative modeling effectively enhances topological accuracy in medical image segmentation.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Liver-vessel segmentation is an essential task in the pre-operative planning of liver resection. State-of-the-art 2D or 3D convolution-based methods focusing on liver vessel segmentation on 2D CT cross-sectional views, which do not take into account the global liver-vessel topology. To maintain this global vessel topology, we rely on the underlying physics used in the CT reconstruction process, and apply this to liver-vessel segmentation. Concretely, we introduce the concept of top-k maximum intensity projections, which mimics the CT reconstruction by replacing the integral along each projection direction, with keeping the top-k maxima along each projection direction. We use these top-k maximum projections to condition a diffusion model and generate 3D liver-vessel trees. We evaluate our 3D liver-vessel segmentation on the 3D-ircadb-01 dataset, and achieve the highest Dice coefficient, intersection-over-union (IoU), and Sensitivity scores compared to prior work.

Problem

• Enhance 3D liver vessel segmentation accuracy
• Maintain global liver-vessel topology in segmentation
• Improve pre-operative planning for liver resection

Innovation

• Top-k maximum intensity projections for 3D segmentation
• Diffusion model conditioned on top-k projections
• Improved Dice, IoU, and Sensitivity scores