| RUS ENG |
| Full version |
|
|
|
| SEMINARS |
|
Seminar on Analysis, Differential Equations and Mathematical Physics
|
|||
|
|
|||
|
Wave tomography: theory, numerical methods and neural networks M. A. Shishlenin Sobolev Institute of Mathematics, Siberian Branch of the Russian Academy of Sciences, Novosibirsk |
|||
|
Abstract: Tomography has been developing intensively over the past two decades. The development of ultrasound methods for the early diagnosis of malignant neoplasms of soft tissues is one of the key problems in medicine, and the absence of exposure to ionizing radiation has become an urgent field in medicine, which makes ultrasound tomography very promising. Currently, various research groups around the world are developing ultrasound scanners. One of the serious problems of ultrasound tomography is the development of effective and stable methods for solving nonlinear coefficient inverse problems. The most adequate model is a 3D inverse problem in which the wave propagation velocity, medium density, and acoustic attenuation must be reconstructed from data recorded by detectors located at the boundary of the region. We consider the dynamic and kinematic inverse problem formulation and apply the direct and iterative methods to solve the inverse coefficient problem. The results of numerical calculations and a comparative analysis of numerical algorithms, including neural network approaches, are presented. Language: English Website: https://msrn.tilda.ws/sl |
|||