Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer.

Parmar C, Leijenaar RT, Grossmann P, Rios Velazquez E, Bussink J, Rietveld D, Rietbergen MM, Haibe-Kains B, Lambin P, Aerts HJ. · 2015

Read Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer. by Parmar C, Leijenaar RT, Grossmann P, Rios Velazquez E, Bussink J, Rietveld D, Rietbergen MM, Haibe-Kains B, Lambin P, Aerts HJ. (2015) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc4937496.txt.

Description

Chintan Parmar and nine co-authors group radiomic features, numbers mined from tumor scans, into clusters for two cancers. Their study appeared in Scientific Reports. Radiomics extracts hundreds of measures from CT images to describe a tumor's shape and texture. Many measures repeat each other, which clutters prediction models. The team studied four patient groups with lung cancer or head and neck cancer, 878 patients in total, and clustered the features by similarity.

Lung tumors gave eleven stable clusters and head and neck tumors thirteen. The clusters held up in outside patient groups used for validation. Some clusters and clinical links were shared across the cancers, while others were specific to one. Outcome prediction reached a concordance of 0.60 for lung and 0.68 for head and neck disease. The authors say cluster level analysis can cut clutter and make scan based signatures easier to compare across centers.

Catalog record

CREATORParmar C, Leijenaar RT, Grossmann P, Rios Velazquez E, Bussink J, Rietveld D, Rietbergen MM, Haibe-Kains B, Lambin P, Aerts HJ.
YEAR2015
COLLECTIONPAPERS
FORMATTXT
FILE SIZE32 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC4937496

Browse the full library · About the Tower of Babel