Reconsider the Template Mesh in Deep Learning-based Mesh Reconstruction

TL;DR

This paper introduces an adaptive-template-based mesh reconstruction network that generates subject-specific templates from images, improving the fidelity of mesh reconstructions in medical imaging applications.

Contribution

The proposed ATMRN method moves beyond fixed templates by creating adaptive templates from images, enhancing accuracy in mesh reconstruction across different modalities and structures.

Findings

Achieved an average symmetric surface distance of 0.267mm on cortical MR images.

Set a new benchmark in voxel-to-cortex mesh reconstruction.

Method is adaptable to various image modalities and anatomical structures.

Abstract

Mesh reconstruction is a cornerstone process across various applications, including in-silico trials, digital twins, surgical planning, and navigation. Recent advancements in deep learning have notably enhanced mesh reconstruction speeds. Yet, traditional methods predominantly rely on deforming a standardised template mesh for individual subjects, which overlooks the unique anatomical variations between them, and may compromise the fidelity of the reconstructions. In this paper, we propose an adaptive-template-based mesh reconstruction network (ATMRN), which generates adaptive templates from the given images for the subsequent deformation, moving beyond the constraints of a singular, fixed template. Our approach, validated on cortical magnetic resonance (MR) images from the OASIS dataset, sets a new benchmark in voxel-to-cortex mesh reconstruction, achieving an average symmetric surface distance of 0.267mm across four cortical structures. Our proposed method is generic and can be easily transferred to other image modalities and anatomical structures.