YoVDO

Coupled Physics Imaging with Sound and Light - Deterministic and Stochastic Approaches

Offered By: Society for Industrial and Applied Mathematics via YouTube

Tags

Machine Learning Courses Monte Carlo Methods Courses Wave Propagation Courses Compressed Sensing Courses

Course Description

Overview

Explore coupled physics imaging techniques using sound and light in this comprehensive seminar talk. Delve into deterministic and stochastic approaches for PhotoAcoustic Tomography (PAT) and Ultrasound Modulated Acoustic Tomography (UMOT). Learn about various methods developed for tackling these problems, including Compressed Sensing, Machine Learning, and a fully stochastic inversion algorithm. Gain insights into modeling optical tomography, light propagation using Monte Carlo approaches, and mathematical models for photoacoustic reconstruction. Examine wave propagation examples, inversion techniques by time reversal, and the adjoint operator method. Discover the applications of spatio-temporal regularization and deterministic reconstruction based on the Radiative Transfer Equation (RTE). Investigate quantitative PhotoAcoustic Tomography and the principles of Fully Stochastic Reconstruction (FSR). Conclude with an outlook on future developments in coupled physics imaging.

Syllabus

Intro
Outline
Introduction : PhotoAcoustic Tomography
Modelling in Optical Tomography
Modelling of Light The Monte Carlo Approach
Mathematical Models
PhotoAcoustic Reconstruction Methods
Wave propagation: Example
Basic Principles: Inversion by time reversal
Basic Principles: Adjoint operator
Random Point Sub-Sampled Data, 16x
Spatio-Temporal Regularization
Deterministic Reconstruction based on RTE
Quantitative PhotoAcoustic Tomography
Fully Stochastic Reconstruction (FSR)
FSR : Introduction
Conclusions and Outlook


Taught by

Society for Industrial and Applied Mathematics

Related Courses

Introduction to Artificial Intelligence
Stanford University via Udacity
Natural Language Processing
Columbia University via Coursera
Probabilistic Graphical Models 1: Representation
Stanford University via Coursera
Computer Vision: The Fundamentals
University of California, Berkeley via Coursera
Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent