Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks

• URL: http://arxiv.org/abs/2203.09446v2
• Date: Fri, 18 Mar 2022 11:10:19 GMT
• Title: Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks
• Authors: Fabian Bongratz, Anne-Marie Rickmann, Sebastian P\"olsterl, Christian Wachinger
• Abstract summary: We propose Vox2Cortex, a deep learning-based algorithm that directly yields topologically correct, three-dimensional meshes of the boundaries of the cortex. We show in extensive experiments on three brain MRI datasets that our meshes are as accurate as the ones reconstructed by state-of-the-art methods in the field.
• Score: 3.364554138758565
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The reconstruction of cortical surfaces from brain magnetic resonance imaging (MRI) scans is essential for quantitative analyses of cortical thickness and sulcal morphology. Although traditional and deep learning-based algorithmic pipelines exist for this purpose, they have two major drawbacks: lengthy runtimes of multiple hours (traditional) or intricate post-processing, such as mesh extraction and topology correction (deep learning-based). In this work, we address both of these issues and propose Vox2Cortex, a deep learning-based algorithm that directly yields topologically correct, three-dimensional meshes of the boundaries of the cortex. Vox2Cortex leverages convolutional and graph convolutional neural networks to deform an initial template to the densely folded geometry of the cortex represented by an input MRI scan. We show in extensive experiments on three brain MRI datasets that our meshes are as accurate as the ones reconstructed by state-of-the-art methods in the field, without the need for time- and resource-intensive post-processing. To accurately reconstruct the tightly folded cortex, we work with meshes containing about 168,000 vertices at test time, scaling deep explicit reconstruction methods to a new level.

Related papers

• R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
  3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction. This paper introduces R2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
  arXiv  Detail & Related papers  (2024-05-31T08:39:02Z)
• Neural deformation fields for template-based reconstruction of cortical surfaces from MRI [5.4173776411667935]
  We introduce Vox2Cortex-Flow, a deep mesh-deformation technique that learns a deformation field from a brain template to the cortical surfaces of an MRI scan. V2C-Flow is not only very fast, requiring less than two seconds to infer all four cortical surfaces. We show that V2C-Flow results in cortical surfaces that are state-of-the-art in terms of accuracy.
  arXiv  Detail & Related papers  (2024-01-23T17:50:58Z)
• Reconstruction of Cortical Surfaces with Spherical Topology from Infant Brain MRI via Recurrent Deformation Learning [16.9042503785353]
  Cortical surface reconstruction (CSR) from MRI is key to investigating brain structure and function. Here, we present a method for simultaneous and spherical mapping efficiently within seconds. We demonstrate the efficacy of our approach on infant brain MRI, which poses significant challenges to CSR.
  arXiv  Detail & Related papers  (2023-12-10T20:20:16Z)
• Tissue Segmentation of Thick-Slice Fetal Brain MR Scans with Guidance from High-Quality Isotropic Volumes [52.242103848335354]
  We propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficiently transfer the knowledge learned from high-quality isotropic volumes for accurate tissue segmentation of thick-slice scans. Our C2DA-Net can fully utilize a small set of annotated isotropic volumes to guide tissue segmentation on unannotated thick-slice scans.
  arXiv  Detail & Related papers  (2023-08-13T12:51:15Z)
• Deep learning network to correct axial and coronal eye motion in 3D OCT retinal imaging [65.47834983591957]
  We propose deep learning based neural networks to correct axial and coronal motion artifacts in OCT based on a single scan. The experimental result shows that the proposed method can effectively correct motion artifacts and achieve smaller error than other methods.
  arXiv  Detail & Related papers  (2023-05-27T03:55:19Z)
• Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction [53.93674177236367]
  Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. We introduce a novel geometry-aware encoder-decoder framework to solve this problem.
  arXiv  Detail & Related papers  (2023-03-26T14:38:42Z)
• GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs [49.55919802779889]
  We propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. In this work, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. Our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps.
  arXiv  Detail & Related papers  (2022-10-19T17:56:03Z)
• Joint Reconstruction and Parcellation of Cortical Surfaces [3.9198548406564604]
  Reconstruction of cerebral cortex surfaces from brain MRI scans is instrumental for the analysis of brain morphology and the detection of cortical thinning in neurodegenerative diseases like Alzheimer's disease (AD) In this work, we propose two options, one based on a graph classification branch and another based on a novel generic 3D reconstruction loss, to augment template-deformation algorithms. We attain highly accurate parcellations with a Dice score of 90.2 (graph classification branch) and 90.4 (novel reconstruction loss) together with state-of-the-art surfaces.
  arXiv  Detail & Related papers  (2022-09-19T11:45:39Z)
• A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction [1.8047694351309207]
  We propose a novel deep-learning-based approach that directly predicts whole heart surface meshes from volumetric CT and MR image data. Our method demonstrated promising performance of generating high-resolution and high-quality whole heart reconstructions.
  arXiv  Detail & Related papers  (2021-02-16T00:39:43Z)
• DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction [20.977071784183256]
  DeepCSR is a 3D deep learning framework for cortical surface reconstruction from MRI. It efficiently reconstructs cortical surfaces at high resolution capturing fine details in the cortical folding. DeepCSR is as accurate, more precise, and faster than the widely used FreeSurfer toolbox and its deep learning powered variant FastSurfer.
  arXiv  Detail & Related papers  (2020-10-22T03:57:44Z)
• Cephalometric Landmark Regression with Convolutional Neural Networks on 3D Computed Tomography Data [68.8204255655161]
  Cephalometric analysis performed on lateral radiographs doesn't fully exploit the structure of 3D objects due to projection onto the lateral plane. We present a series of experiments with state of the art 3D convolutional neural network (CNN) based methods for keypoint regression. For the first time, we extensively evaluate the described methods and demonstrate their effectiveness in the estimation of Frankfort Horizontal and cephalometric points locations.
  arXiv  Detail & Related papers  (2020-07-20T12:45:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.