Reproducibility of radiomics for deciphering tumor phenotype with imaging.
Zhao B, Tan Y, Tsai WY, Qi J, Xie C, Lu L, Schwartz LH. · 2016
Read Reproducibility of radiomics for deciphering tumor phenotype with imaging. by Zhao B, Tan Y, Tsai WY, Qi J, Xie C, Lu L, Schwartz LH. (2016) 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-pmc4806325.txt.
Description
Binsheng Zhao and six co-authors test the stability of radiomics in Scientific Reports in 2016. Radiomics mines routine tumor scans for hundreds of measured features, hoping the pattern betrays the tumor's type and likely course. A feature that shifts with scanner settings, though, is worthless as a medical marker, and little was known about that risk.
The team used a rare same-day repeat scan set from lung cancer patients. Each scan was rebuilt at six settings, mixing three slice thicknesses and two sharpening styles. Most features repeated well across settings, which supports the field's promise. One limit stood out: scans rebuilt with smooth versus sharp styling should not be mixed in one study. The paper urges scan settings be fixed and reported in radiomics work.
Catalog record
| CREATOR | Zhao B, Tan Y, Tsai WY, Qi J, Xie C, Lu L, Schwartz LH. |
|---|---|
| YEAR | 2016 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 28 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |