review Open AccessTop 1% cited
Repeatability and Reproducibility of Radiomic Features: A Systematic Review
International Journal of Radiation Oncology*Biology*Physics · 2018 · Vol. 102(4) · pp. 1143–1158
Alberto Traverso✉(Maastricht University)Leonard Wee(Maastricht University)André Dekker(Maastricht University)Robert J. Gillies(Moffitt Cancer Center)
Abstract
Investigations of feature repeatability and reproducibility are currently limited to a small number of cancer types. Reporting quality could be improved regarding details of feature extraction software, digital image manipulation (preprocessing), and the cutoff value used to distinguish stable features.
Radiomics and Machine Learning in Medical ImagingAdvanced X-ray and CT ImagingMRI in cancer diagnosisRepeatabilityReproducibilityPreprocessorRadiomicsMedicineData extractionComputer scienceArtificial intelligencePattern recognition (psychology)Medical physics
MeSH terms
HumansImage Processing, Computer-AssistedNeoplasmsReproducibility of ResultsPhantoms, Imaging
Citations
837
FWCI
61.40
field-weighted impact
References
83
Percentile
100%
vs. same field & year
Citations per year
Cited by
The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping
Radiology · 2020 · 3,655 citations
References
Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement
British Journal of Cancer · 2015 · 3,343 citations
New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)
European Journal of Cancer · 2008 · 28,935 citations
Dangers of Using "Optimal" Cutpoints in the Evaluation of Prognostic Factors
JNCI Journal of the National Cancer Institute · 1994 · 1,124 citations
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
Nature Communications · 2014 · 5,021 citations
Radiomics: Extracting more information from medical images using advanced feature analysis
European Journal of Cancer · 2012 · 5,765 citations
New Guidelines to Evaluate the Response to Treatment in Solid Tumors
JNCI Journal of the National Cancer Institute · 2000 · 15,689 citations
Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement
BMJ · 2009 · 82,871 citations
A Concordance Correlation Coefficient to Evaluate Reproducibility
Biometrics · 1989 · 8,535 citations
Citation Network
How this paper connects to the literature. Drag to explore, click any node to open that paper.