Enhanced Localization in Ultrafast Ultrasound Imaging through Spatio-Temporal Deep Learning - Computational Imaging and Vision
Conference Papers Year : 2024

Enhanced Localization in Ultrafast Ultrasound Imaging through Spatio-Temporal Deep Learning

Vassili Pustovalov
  • Function : Author
  • PersonId : 1111426
Duong-Hung Pham
Denis Kouamé

Abstract

The integration of ultrasound localization microscopy (ULM) in ultrasound imaging has enabled an unprecedented enhancement in resolution, offering insights into blood flow direction and velocity measurement. Despite its potential, ULM remains a complex and time-intensive procedure, continually improved through advancements in deep learning (DL) methods. Current DL techniques for micro-bubble (MB) super-localization encounter complexity stemming from the use of high-resolution images within their networks. Consequently, these convolutional neural networks (CNNs) incur longer execution times compared to traditional ULM, necessitating arbitrary filtering of their outcomes prior to integration with a subsequent tracking algorithm. To address these challenges, our study introduces a novel DL approach inspired by the success of single-molecule localization microscopy DL techniques. Our proposed 3D CNN, named 3DML-ResNet, enables fast and scalable super-localization while providing explicit estimations of the number of MBs in each frame.
Fichier principal
Vignette du fichier
EUSIPCO_2024.pdf (3.85 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04596871 , version 1 (04-06-2024)

Identifiers

  • HAL Id : hal-04596871 , version 1

Cite

Vassili Pustovalov, Duong-Hung Pham, Denis Kouamé. Enhanced Localization in Ultrafast Ultrasound Imaging through Spatio-Temporal Deep Learning. 32nd European Signal Processing Conference (EUSIPCO 2024), Aug 2024, Lyon, France. pp.TU1.SC1.6. ⟨hal-04596871⟩
518 View
134 Download

Share

More