See a list of publications below or visit the Photonics academic staff page and click on a particular  member of staff to access their personal web page, which includes a list of their own publications.

Citation

BibTex format

@phdthesis{Lerendegui:2025,
author = {Lerendegui, M},
title = {Simulation Framework of Contrast Enhanced Ultrasound (CEUS) and Microvascular Flow for Ultrasound Localization Microscopy (ULM) and Deep Learning},
year = {2025}
}
Download

RIS format (EndNote, RefMan)

TY  - THES
AB  - Standard ultrasound imaging is a widely adopted noninvasive and safe modality, known for its affordability, real-time imaging capabilities, and ease of use. Despite its advantages, it faces limitations such as low resolution due to the diffraction limit, and the need for high frequencies to increase resolution and visualize blood flow, that leads to a trade-off between frequency and depth.Recent decades have witnessed notable advancements in ultrasound vascular imaging, including the use of Microbubble (MB) contrast agents that highlight the vasculature --known as Contrast Enhanced Ultrasound (CEUS)--, and unfocused transmission techniques that significantly increase framerate. But more importantly, inspired by optical imaging techniques like STochastic Optical Reconstruction Microscopy (STORM) and Fluorescence Photo-Activated Localization Microscopy (FPALM), Ultrasound Localization Microscopy (ULM) emerged as a novel approach capable of overcoming the diffraction limit. ULM provides unprecedented in-vivo resolution for microvascular flow, producing super-resolved maps with detailed flow information.While the field of ULM has rapidly expanded, significant challenges for clinical translation exist, such as its low acquisition rate, and the need for algorithms capable of isolating, localizing and tracking MBs accurately.Many algorithms addressing these challenges were developed, but their performance has not been consistently evaluated and benchmarked. Some attempts of evaluation have been performed, but they all present some limitations such as using datasets without considering MB oscillation physics or focusing only on localization and not tracking.Additionally, the generation of datasets with known ground truth information is crucial for training deep learning models, as it provides a reliable reference for the network to learn from.For supervised learning in ULM, relying only on real world data is not an option due to the impossibility of obtaining ground truth l
AU  - Lerendegui,M
PY  - 2025///
TI  - Simulation Framework of Contrast Enhanced Ultrasound (CEUS) and Microvascular Flow for Ultrasound Localization Microscopy (ULM) and Deep Learning
ER  -
Download