Short Courses

This short course is sponsored by IEEE UFFC-S as an outreach activity by the IEEE UFFC-S outreach ambassador Dr. Koen W.A. van Dongen

Please note that this course will be held one day before the conference: May 7, 2024 at the Faculty of Science,  Universidad de la República (Udelar). 

Shuttle transportation will be provided:

Departure time: 8:30 AM 

Location: "Explanada de la Intendencia de Montevideo"

https://maps.app.goo.gl/2i7GMvAvATZjFMJk9
 

To optimize your ultrasound imaging device, to understand your data, or to improve your imaging algorithm; it is always important to have a good understanding of how acoustic wave field propagates in the medium, and why and how it scatters of the object of interest. To get this understanding, it is essential to have knowledge about the physical mechanisms and mathematical formulations that describe the wave propagation in the heterogenous medium. This course is about the fundamentals of acoustic wave theory and imaging and inversion. 

During this course, the acoustic field equations (equation of motion and equation of deformation) will be derived, and it will be shown how the acoustic wavefield is described via a pressure and a velocity wave field. Next, linearized versions of the field equations are used to derive the wave equation for linear acoustics. A similar approach is used to derive the Westerveld equation used for non-linear acoustics. Next, different solution methods for modelling acoustic wave fields in heterogeneous media will be explained, as well as the concepts behind Kirchhoff integrals, Rayleigh I and II integrals, and evanescent waves. Finally, the ideas behind imaging and (non-linear) inversion for quantitative imaging are explained. During the course, oral lectures will be interchanged with simple numerical exercises and a small practical assignment. 

This short course will take place May 8th at Montevideo City Hall (Intendencia de Montevideo). It will occur at the same time as “Quantitative Ultrasound Techniques: The Current State of the Art.”

This course will start with a brief introduction of deep learning, and its impact across many domains, including medical imaging in general. We will then shortly outline the strong opportunities for ultrasound imaging, moving from workflow enhancement and image analysis to image formation and acquisition. To that end, we will also discuss the basic principles of ultrasound image acquisition and image formation, along with the specific challenges that may well be addressed using deep learning in the coming years.

We will then briefly recall fundamentals of deep learning, ranging from understanding the relevance of sequential nonlinear transformations for representation learning to log-likelihood based optimization of neural network parameters. Optimization aspects such as the impact of local minima and saddle points in the solution space will also be discussed. We will then elaborate on the design of effective neural network architectures in the context of ultrasound imaging. In this last part, we place a particular emphasis on model-based deep learning methods, i.e. deep networks that leverage known signal structure by integrating models into deep networks (deep unfolding methods), and deep networks that are integrated into known model-based algorithms (data-driven hybrid algorithms).

The last part of this tutorial will focus on the wealth of opportunities that deep learning brings for ultrasound imaging. We will discuss neural networks for front-end receive processing, including beamforming, image compounding, clutter suppression, and advanced applications such as super-resolution imaging. We will also discuss the power of end-to-end optimization of entire signal processing chains in ultrasound imaging, from the upstream sensor to the final downstream analysis.

This short course will take place May 8th at Montevideo City Hall (Intendencia de Montevideo). It will occur at the same time as “ Deep learning for ultrasound imaging.”

Conventional medical imaging technologies, including ultrasound, have continued to improve over the years. Conventional ultrasound B-mode imaging is mainly qualitative in nature. However, quantitative ultrasound (QUS) imaging can provide specific numbers related to tissue features that can increase the specificity of image findings leading to improvements in diagnostic ultrasound. QUS imaging techniques can encompass a wide variety of techniques including spectral-based parameterization, elastography, shear wave imaging, flow estimation and envelope statistics. QUS techniques involving spectral-based parameterization and envelope statistics have demonstrated success in many applications, providing additional diagnostic capabilities and are now becoming available on clinical ultrasound machines. Spectral-based techniques include the estimation of the backscatter coefficient, estimation of attenuation, and estimation of scatterer properties such as the correlation length associated with an effective scatterer diameter and the effective acoustic concentration of scatterers. Envelope statistics include the estimation of the number density of scatterers and quantification of coherent to incoherent signals produced from the tissue.

In this short course, we will discuss the basic underlying principles behind QUS imaging, model the signals leading to QUS estimates, quantify the spatial resolution of QUS imaging versus estimate bias and variance, recent work involving deep learning and QUS, and describe the attempts to implement these techniques on modern clinical systems. Practical implementation issues will be addressed with highlights for specific applications and successes. Instruction on using a GUI estimator for Matlab to yield QUS estimates and images will be provided with specific examples.