PrIntMesh: Precise Intersection Surfaces for 3D Organ Mesh Reconstruction

TL;DR

PrIntMesh is a topology-preserving, template-based framework that accurately reconstructs interconnected 3D organ meshes, maintaining internal boundaries and structural integrity even with limited data.

Contribution

It introduces a novel joint deformation approach that preserves internal boundaries and topology, improving anatomical plausibility over existing independent-part methods.

Findings

Achieves high geometric accuracy in organ reconstruction

Maintains correct topology and shared interfaces

Performs robustly with limited or noisy data

Abstract

Human organs are composed of interconnected substructures whose geometry and spatial relationships constrain one another. Yet, most deep-learning approaches treat these parts independently, producing anatomically implausible reconstructions. We introduce PrIntMesh, a template-based, topology-preserving framework that reconstructs organs as unified systems. Starting from a connected template, PrIntMesh jointly deforms all substructures to match patient-specific anatomy, while explicitly preserving internal boundaries and enforcing smooth, artifact-free surfaces. We demonstrate its effectiveness on the heart, hippocampus, and lungs, achieving high geometric accuracy, correct topology, and robust performance even with limited or noisy training data. Compared to voxel- and surface-based methods, PrIntMesh better reconstructs shared interfaces, maintains structural consistency, and provides a data-efficient solution suitable for clinical use.