2019
DOI: 10.1148/radiol.2018181197
|View full text |Cite|
|
Sign up to set email alerts
|

Radiomics Analysis of Gadoxetic Acid–enhanced MRI for Staging Liver Fibrosis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
92
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 107 publications
(94 citation statements)
references
References 34 publications
0
92
0
Order By: Relevance
“…Given that not all features would be useful for the classification task, we followed a two‐step methodology to dimensionality reduction, feature selection, and recognition of the optimal set of features for the final radiomics signature construction. Particularly, to overcome the selection bias and overfitting in the traditional logistic regression algorithm, the Kendall correlation coefficient was calculated between each feature and the pathologic outcome as previously described . The feature would be eliminated if the corresponding coefficient was less than 0.2.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Given that not all features would be useful for the classification task, we followed a two‐step methodology to dimensionality reduction, feature selection, and recognition of the optimal set of features for the final radiomics signature construction. Particularly, to overcome the selection bias and overfitting in the traditional logistic regression algorithm, the Kendall correlation coefficient was calculated between each feature and the pathologic outcome as previously described . The feature would be eliminated if the corresponding coefficient was less than 0.2.…”
Section: Methodsmentioning
confidence: 99%
“…Particularly, to overcome the selection bias and overfitting in the traditional logistic regression algorithm, the Kendall correlation coefficient was calculated between each feature and the pathologic outcome as previously described. 25 The feature would be eliminated if the corresponding coefficient was less than 0.2. Second, a least absolute shrinkage and selection operator (LASSO) regression algorithm was used to evaluate the remaining radiomics features.…”
Section: Radiomics Analysismentioning
confidence: 99%
“…https://doi.org/10.3348/kjr.2019.0752 kjronline.org (mean), dispersion (standard deviation), asymmetry (skewness), peakedness or flatness (kurtosis), randomness (entropy), uniformity (energy and uniformity), and dispersion relative to the magnitude (coefficient of variation) of gray-level pixel values. These histogram features describe the distribution pattern of gray-level pixel values within a VOI as a whole, but cannot address the spatial relationship among pixels or the textural pattern (4)(5)(6) (Fig. 2).…”
Section: Radiomicsmentioning
confidence: 99%
“…Radiomics features can be extracted in 2D or 3D using inhouse software (6,(9)(10)(11)(12)(13) or commercial software (14,15 (16), the analysis of high-dimensional features may lead to problems of multicollinearity and overfitting. A recent phantom study revealed that the information provided by multiple radiomics features could be summarized using only 10 features because of redundancy (16).…”
Section: Process Of Radiomics Analysismentioning
confidence: 99%
See 1 more Smart Citation