Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI

• URL: http://arxiv.org/abs/2006.04725v3
• Date: Wed, 8 Jul 2020 09:42:11 GMT
• Title: Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI
• Authors: Chen Qin, Shuo Wang, Chen Chen, Huaqi Qiu, Wenjia Bai and Daniel Rueckert
• Abstract summary: We propose a novel method that can implicitly learn biomechanics-informed regularisation. The proposed method is validated in the context of myocardial motion tracking on 2D stacks of cardiac MRI data.
• Score: 15.686391154738006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image registration is an ill-posed inverse problem which often requires regularisation on the solution space. In contrast to most of the current approaches which impose explicit regularisation terms such as smoothness, in this paper we propose a novel method that can implicitly learn biomechanics-informed regularisation. Such an approach can incorporate application-specific prior knowledge into deep learning based registration. Particularly, the proposed biomechanics-informed regularisation leverages a variational autoencoder (VAE) to learn a manifold for biomechanically plausible deformations and to implicitly capture their underlying properties via reconstructing biomechanical simulations. The learnt VAE regulariser then can be coupled with any deep learning based registration network to regularise the solution space to be biomechanically plausible. The proposed method is validated in the context of myocardial motion tracking on 2D stacks of cardiac MRI data from two different datasets. The results show that it can achieve better performance against other competing methods in terms of motion tracking accuracy and has the ability to learn biomechanical properties such as incompressibility and strains. The method has also been shown to have better generalisability to unseen domains compared with commonly used L2 regularisation schemes.

Related papers

• MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints [50.61346764110482]
  We integrate a musculoskeletal system with a learnable parametric hand model, MANO, to create MS-MANO. This model emulates the dynamics of muscles and tendons to drive the skeletal system, imposing physiologically realistic constraints on the resulting torque trajectories. We also propose a simulation-in-the-loop pose refinement framework, BioPR, that refines the initial estimated pose through a multi-layer perceptron network.
  arXiv  Detail & Related papers  (2024-04-16T02:18:18Z)
• LIBR+: Improving Intraoperative Liver Registration by Learning the Residual of Biomechanics-Based Deformable Registration [6.0499389232972565]
  We propose a novel textithybrid registration approach that leverage a linearized iterative boundary reconstruction (LIBR) method based on linear elastic biomechanics. We also formulate a dual-branch spline-residual graph convolutional neural network (SR-GCN) to assimilate information from sparse and variable intraoperative measurements.
  arXiv  Detail & Related papers  (2024-03-11T16:54:44Z)
• GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration [62.41725951450803]
  Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and smoothness of the field. We construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyper parameter-free balance on multiple losses. Our method is model-agnostic and can be merged into any deep registration network without introducing extra parameters or slowing down inference.
  arXiv  Detail & Related papers  (2023-06-26T13:32:09Z)
• Non-rigid Medical Image Registration using Physics-informed Neural Networks [8.7196937169933]
  Biomechanical modelling of soft tissue provides a non-data-driven method for constraining medical image registration. This work instantiates the recently-proposed physics-informed neural networks (PINNs) to a 3D linear elastic model for modelling prostate motion.
  arXiv  Detail & Related papers  (2023-02-20T22:17:29Z)
• Learning correspondences of cardiac motion from images using biomechanics-informed modeling [7.193217430660012]
  We propose an explicit biomechanics-informed prior as regularization on the predicted displacement vector field (DVF) Our proposed methods better preserve biomechanical properties by visual assessment and show advantages in segmentation performance using quantitative evaluation metrics.
  arXiv  Detail & Related papers  (2022-09-01T20:59:26Z)
• Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior [16.129107206314043]
  Myocardial motion and deformation are rich descriptors that characterize cardiac function. Image registration, as the most commonly used technique for myocardial motion tracking, is an ill-posed inverse problem. We propose a novel method that can implicitly learn an application-specific biomechanics-informed prior.
  arXiv  Detail & Related papers  (2022-06-08T12:02:00Z)
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network [51.44506007844284]
  We propose a shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection surgery. We first devise an algorithm to automatically generate relation keypoint heatmaps, which intuitively represent the prior knowledge of spatial relations among landmarks. We then develop two complementary regularization schemes to progressively incorporate the prior knowledge into the training process.
  arXiv  Detail & Related papers  (2021-11-08T07:57:30Z)
• One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video [71.43912903508765]
  MDAL is a dynamic online adaptive learning scheme for instrument segmentation in robot-assisted surgery. It learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. It outperforms other state-of-the-art methods on two datasets.
  arXiv  Detail & Related papers  (2021-03-24T05:02:18Z)
• Domain Adaptive Robotic Gesture Recognition with Unsupervised Kinematic-Visual Data Alignment [60.31418655784291]
  We propose a novel unsupervised domain adaptation framework which can simultaneously transfer multi-modality knowledge, i.e., both kinematic and visual data, from simulator to real robot. It remedies the domain gap with enhanced transferable features by using temporal cues in videos, and inherent correlations in multi-modal towards recognizing gesture. Results show that our approach recovers the performance with great improvement gains, up to 12.91% in ACC and 20.16% in F1score without using any annotations in real robot.
  arXiv  Detail & Related papers  (2021-03-06T09:10:03Z)
• A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans [63.28835187934139]
  We propose a novel method for removing motion artefacts using a deep neural network with two input branches. The proposed method can be applied to artefacts generated by multiple movements of the patient.
  arXiv  Detail & Related papers  (2020-06-24T15:25:11Z)
• Registration by tracking for sequential 2D MRI [0.0]
  We present an image registration method that exploits the sequential nature of 2D MR images to estimate the displacement field. The method is evaluated on a segmented cardiac dataset and when compared to two conventional methods we observe an improved performance.
  arXiv  Detail & Related papers  (2020-03-24T13:12:42Z)

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.