Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness

• URL: http://arxiv.org/abs/2202.01208v2
• Date: Mon, 8 May 2023 22:53:48 GMT
• Title: Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness
• Authors: Farnaz Khun Jush, Markus Biele, Peter M. Dueppenbecker, Andreas Maier
• Abstract summary: We propose a new simulation setup for training data generation based on Tomosynthesis images. We studied the sensitivity of the trained network to different simulation parameters. We showed that the network trained with the joint set of data is more stable on out-of-domain simulated data as well as measured phantom data.
• Score: 7.909848251752742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ultrasound b-mode imaging is a qualitative approach and diagnostic quality strongly depends on operators' training and experience. Quantitative approaches can provide information about tissue properties; therefore, can be used for identifying various tissue types, e.g., speed-of-sound in the tissue can be used as a biomarker for tissue malignancy, especially in breast imaging. Recent studies showed the possibility of speed-of-sound reconstruction using deep neural networks that are fully trained on simulated data. However, because of the ever-present domain shift between simulated and measured data, the stability and performance of these models in real setups are still under debate. In prior works, for training data generation, tissue structures were modeled as simplified geometrical structures which does not reflect the complexity of the real tissues. In this study, we proposed a new simulation setup for training data generation based on Tomosynthesis images. We combined our approach with the simplified geometrical model and investigated the impacts of training data diversity on the stability and robustness of an existing network architecture. We studied the sensitivity of the trained network to different simulation parameters, e.g., echogenicity, number of scatterers, noise, and geometry. We showed that the network trained with the joint set of data is more stable on out-of-domain simulated data as well as measured phantom data.

Related papers

• Graph Neural Networks for modelling breast biomechanical compression [0.08192907805418582]
  Breast compression simulation is essential for accurate image registration from 3D modalities to X-ray procedures like mammography. It accounts for tissue shape and position changes due to compression, ensuring precise alignment and improved analysis. Finite Element Analysis (FEA) is reliable for approximating soft tissue deformation, it struggles with balancing accuracy and computational efficiency. Recent studies have used data-driven models trained on FEA results to speed up tissue deformation predictions. We propose to explore Physics-based Graph Neural Networks (PhysGNN) for breast compression simulation.
  arXiv  Detail & Related papers  (2024-11-10T20:59:23Z)
• Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation [73.81105275628751]
  Finding all structures compatible with reflectometry data is computationally prohibitive for standard algorithms. We address this lack of reliability with a probabilistic deep learning method that identifies all realistic structures in seconds. Our method, Prior-Amortized Neural Posterior Estimation (PANPE), combines simulation-based inference with novel adaptive priors.
  arXiv  Detail & Related papers  (2024-07-26T10:29:16Z)
• Advancing fNIRS Neuroimaging through Synthetic Data Generation and Machine Learning Applications [0.0]
  This study presents an integrated approach for advancing functional Near-Infrared Spectroscopy (fNIRS) neuroimaging. By addressing the scarcity of high-quality neuroimaging datasets, this work harnesses Monte Carlo simulations and parametric head models to generate a comprehensive synthetic dataset. A cloud-based infrastructure is established for scalable data generation and processing, enhancing the accessibility and quality of neuroimaging data.
  arXiv  Detail & Related papers  (2024-05-18T09:50:19Z)
• Physics-informed Neural Network Estimation of Material Properties in Soft Tissue Nonlinear Biomechanical Models [2.8763745263714005]
  We propose a new approach which relies on the combination of physics-informed neural networks (PINNs) with three-dimensional soft tissue nonlinear biomechanical models. The proposed learning algorithm encodes information from a limited amount of displacement and, in some cases, strain data, that can be routinely acquired in the clinical setting. Several benchmarks are presented to show the accuracy and robustness of the proposed method.
  arXiv  Detail & Related papers  (2023-12-15T13:41:20Z)
• Persistence-based operators in machine learning [62.997667081978825]
  We introduce a class of persistence-based neural network layers. Persistence-based layers allow the users to easily inject knowledge about symmetries respected by the data, are equipped with learnable weights, and can be composed with state-of-the-art neural architectures.
  arXiv  Detail & Related papers  (2022-12-28T18:03:41Z)
• An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design [55.62660894625669]
  Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. Recent developments in machine learning have provided alternative solutions in replacing the time-consuming lithography simulations with deep neural networks. We propose a litho-aware data augmentation framework to resolve the dilemma of limited data and improve the machine learning model performance.
  arXiv  Detail & Related papers  (2022-10-27T20:53:39Z)
• Ultrasound Signal Processing: From Models to Deep Learning [64.56774869055826]
  Medical ultrasound imaging relies heavily on high-quality signal processing to provide reliable and interpretable image reconstructions. Deep learning based methods, which are optimized in a data-driven fashion, have gained popularity. A relatively new paradigm combines the power of the two: leveraging data-driven deep learning, as well as exploiting domain knowledge.
  arXiv  Detail & Related papers  (2022-04-09T13:04:36Z)
• Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples [1.112751058850223]
  We develop a new model-based data normalization pre-processing procedure for homogenizing the sample contrast. We demonstrate this framework's capabilities on experimental measurements of epithelial buccal cells and Caenorhabditis elegans worms.
  arXiv  Detail & Related papers  (2021-03-29T17:43:56Z)
• Data-driven generation of plausible tissue geometries for realistic photoacoustic image synthesis [53.65837038435433]
  Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties. We propose a novel approach to PAT data simulation, which we refer to as "learning to simulate" We leverage the concept of Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data to generate plausible tissue geometries.
  arXiv  Detail & Related papers  (2021-03-29T11:30:18Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)

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.