English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Diffuse Optical Tomography (DOT) is an emerging technology in medical imagingwhich employs light in the NIR spectrum to estimate the distribution of opticalcoefficients in biological tissues for diagnostic and monitoring purposes. DOTreconstruction implies the solution of a severely ill-posed inverse problem,for which regularization techniques are mandatory in order to achievereasonable results. Traditionally, regularization techniques put a varianceprior on the desired solution/gradient via regularization parameters, whosechoice requires a fine tuning, specific for each case. In this work we exploredeep learning techniques in a fully data-driven approach, able ofreconstructing the generating signal (optical absorption coefficient) in anautomated way. We base our approach on the so-called Learned Singular ValueDecomposition, which has been proposed for general inverse problems, and wetailor it to the DOT application. We perform tests with increasing levels ofnoise on the measure, and compare it with standard variational approaches.

A Learned-SVD approach for Regularization in Diffuse Optical Tomography