BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:EIT reconstruction using virtual X-rays and machine learning - Sii
 ri  Rautio (University of Helsinki)
DTSTART:20230328T101000Z
DTEND:20230328T104000Z
UID:TALK198217@talks.cam.ac.uk
DESCRIPTION:The mathematical model of electrical impedance tomography (EIT
 ) is the inverse conductivity problem introduced by Calder\\'on. The aim i
 s to recover the conductivity $\\sigma$ from the knowledge of\nthe Dirichl
 et-to-Neumann map $\\Lambda_\\sigma$. It is a nonlinear and ill-posed inve
 rse problem.\nWe introduce a new reconstruction algorithm for EIT\, which 
 provides a connection between EIT and traditional X-ray tomography. We div
 ide the exponentially ill-posed and nonlinear inverse problem of EIT into 
 separate steps. We start by mathematically calculating so-called virtual X
 -ray projection data from the DN map. Then\, we perform explicit algebraic
  operations and one-dimensional integration\, ending up with a blurry Rado
 n sinogram. We use neural networks to deconvolve the sinogram and finally\
 , we can compute a reconstruction of the conductivity using the inverse Ra
 don transform. We demonstrate the method with simulated data examples.\n&n
 bsp\;\nThis is a joint work with Samuli Siltanen\, Matti Lassas\, Rashmi M
 urthy\, Fernando Silva de Moura\, Juan Pablo Agnelli\, and Melody Alsaker.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR