Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy

Authors:
Publisher website
Google Scholar
Abstract
Ultrasound Localization Microscopy (ULM) is a non-invasive technique that allows for the imaging of micro-vessels in vivo, at depth and with a resolution on the order of ten microns. ULM is based on the sub-resolution localization of individual microbubbles injected in the bloodstream. Mapping the whole angioarchitecture requires the accumulation of microbubbles trajectories from thousands of frames, typically acquired over a few minutes. ULM acquisition times can be reduced by increasing the microbubble concentration, but requires more advanced algorithms to detect them individually. Several deep learning approaches have been proposed for this task, but they remain limited to 2D imaging, in part due to the associated large memory requirements. Herein, we propose the use of sparse tensor neural networks to enable deep learning-based 3D ULM by improving memory scalability with increased dimensionality. We study several approaches to efficiently convert ultrasound data into a sparse format and study the impact of the associated loss of information. When applied in 2D, the sparse formulation reduces the memory requirements by a factor 2 at the cost of a small reduction of performance when compared against dense networks. In 3D, the proposed approach reduces memory requirements by two order of magnitude while largely outperforming conventional ULM in high concentration settings. We show that Sparse Tensor Neural Networks in 3D ULM allow for the same benefits as dense deep learning based method in 2D ULM i.e. the use of higher concentration in silico and reduced acquisition time.
Funding Information
  • Institute for Data Valorization
  • Canada Foundation for Innovation (38095)
  • Canadian Institutes of Health Research (452530)
  • Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery (RGPIN-2020-06786)
  • Calcul Québec
  • Digital Research Alliance of Canada
  • Institut de Valorisation des Données
  • Institut TransMedTech
  • Fonds de Recherche du Québec—Nature et Technologies
  • Institut de Valorisation des Données
  • Institut TransMedTech
  • Institut de Valorisation des Données
  • Institut TransMedTech
  • Canada First Research Excellence Fund

This publication has 49 references indexed in Scilit: