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

Inter-observer variability and cancer over-diagnosis are emerging clinicalproblems, and there is a strong necessity to support the standards histologicaland cytological evaluations by biochemical composition information. Over thepast decades, there has been a very active research in the development of Ramanspectroscopy techniques for oncological applications and large scale clinicaldiagnosis. A major issue that has received a lot of attention in the Ramanliterature is the fact that variations in instrumental responses and intrinsicspectral backgrounds over different days of measurements or devices createsstrong inconsistency of Raman intensity spectra over the various experimentalcondition, thus making the use of Raman spectroscopy on a large scale andreproductive basis difficult. We explore different methods to tackle thisinconsistency and show that regular preprocessing methods such as baselinecorrection, normalization or wavelet transformation are inefficient on ourdatasets. We find that subtracting the mean background spectrum estimated byidentifying non-cell regions in Raman images makes the data more consistent. Asa proof of concept, we employ our single-cell Raman Imaging protocol todiagnosis challenging follicular lesions, that is known to be particularlydifficult due to the lack of obvious morphological and cytological criteria formalignancy. We explore dimensionality reduction with both PCA and featureselection methods, and classification is then performed at the single celllevel with standard classifiers such as k Nearest Neighbors or Random Forest.We investigate Raman hyperspectral images from FTC133, RO82W-1 and NthyOri 3-1cell lines and show that the chemical information for the diagnosis is mostlycontained in the cytoplasm. We also reveal some important wavenumber formalignancy, that can be associated mainly to lipids, cytochrome andphenylalanine.

Intelligent Measurement Analysis on Single Cell Raman Images for the Diagnosis of Follicular Thyroid Carcinoma