2018
DOI: 10.1002/mp.13202
|View full text |Cite
|
Sign up to set email alerts
|

Identification of optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition‐based radiomic features

Abstract: This study has revealed the potential of Symlet and Biorthogonal mother wavelets in  the survival prediction of lung cancer patients by using WDB radiomic features in CT images.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
47
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 60 publications
(48 citation statements)
references
References 53 publications
1
47
0
Order By: Relevance
“…This was achieved with a LASSO Cox regression model applied to the training dataset for the signature construction . This model has often been used for radiomics analysis …”
Section: Methodsmentioning
confidence: 99%
“…This was achieved with a LASSO Cox regression model applied to the training dataset for the signature construction . This model has often been used for radiomics analysis …”
Section: Methodsmentioning
confidence: 99%
“…Reproducible features in terms of segmentation difference are usually identified with the criterion of ICC > 0.75-0.80 for each feature in most radiomics studies [12,28,[34][35][36]. One of the reasons for defining the ICC criterion > 0.75-0.80 may be that it is necessary for constructing a prognostic or classification model to significantly reduce the feature's dimensions.…”
Section: Discussionmentioning
confidence: 99%
“…The number of texture features that showed a significant difference between datasets NE and CE was greater with a wider bin width. Soufi et al constructed a prognostic model of overall survival for lung cancer patients using wavelet-based radiomic features with changing requantization levels [28]. In their results, the number of constructed prognostic models increased by decreasing the requantization levels (equal to enlarging the bin width).…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…The matrices were constructed by analyzing eight neighborhoods. Decomposition was performed by applying either a low-pass filter (scaling function, L) or high-pass filter (wavelet function, H) [29] to eight-bit CT images in each direction. Therefore, the four wavelet decomposition filters consisted of a combination of two filters using either a low-pass filter (L) or high-pass filter (H) in each direction (the x or y direction in the two-dimensional images).…”
Section: Clinical Casesmentioning
confidence: 99%