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

Optical imaging modalities such as near-infrared spectroscopy (NIRS) andhyperspectral imaging (HSI) represent a promising alternative for low-cost,non-invasive, and fast monitoring of functional and structural properties ofliving tissue. Particularly, the possibility of extracting the molecularcomposition of the tissue from the optical spectra in real-time deems thespectroscopy techniques as a unique diagnostic tool. However, due to a lack ofpaired optical and molecular profiling studies, building a mapping between aspectral signature and a corresponding set of molecular concentrations is stillan unsolved problem. Furthermore, there are currently no established methods tostreamline inference of the biochemical composition from the optical spectrumfor real-time applications such as surgical monitoring. In this paper, wedevelop a technique for fast inference of changes in the molecular compositionof brain tissue. We base our method on the Beer-Lambert law to analyticallyconnect the spectra with concentrations and use a deep-learning approach tosignificantly speed up the concentration inference compared to traditionaloptimization methods. We test our approach on real data obtained from thebroadband NIRS study of piglets' brains and the HSI dataset of glioma patients.The results demonstrate that the proposed method enables real-time molecularcomposition inference while maintaining the accuracy of traditional linear andnon-linear optimization solvers.

Shallow learning enables real-time inference of molecular composition from spectroscopy of brain tissue