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

Soufi, Mazen; Arimura, Hidetaka; Nagami, Noriyuki

doi:10.1002/mp.13202

Cited by 60 publications

(48 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

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%

Homology‐based radiomic features for prediction of the prognosis of lung cancer based on CT‐based radiomics

et al. 2020

View full text Add to dashboard Cite

Purpose: Radiomics is a new technique that enables noninvasive prognostic prediction by extracting features from medical images. Homology is a concept used in many branches of algebra and topology that can quantify the contact degree. In the present study, we developed homology-based radiomic features to predict the prognosis of non-small-cell lung cancer (NSCLC) patients and then evaluated the accuracy of this prediction method. Methods: Four datasets were used: two to provide training and test data and two for the selection of robust radiomic features. All the datasets were downloaded from The Cancer Imaging Archive (TCIA). In two-dimensional cases, the Betti numbers consist of two values: b 0 (zero-dimensional Betti number), which is the number of isolated components, and b 1 (one-dimensional Betti number), which is the number of one-dimensional or "circular" holes. For homology-based evaluation, computed tomography (CT) images must be converted to binarized images in which each pixel has two possible values: 0 or 1. All CT slices of the gross tumor volume were used for calculating the homology histogram. First, by changing the threshold of the CT value (range: À150 to 300 HU) for all its slices, we developed homology-based histograms for b 0 , b 1 , and b 1 /b 0 using binarized images. All histograms were then summed, and the summed histogram was normalized by the number of slices. 144 homology-based radiomic features were defined from the histogram. To compare the standard radiomic features, 107 radiomic features were calculated using the standard radiomics technique.To clarify the prognostic power, the relationship between the values of the homology-based radiomic features and overall survival was evaluated using LASSO Cox regression model and the Kaplan-Meier method. The retained features with nonzero coefficients calculated by the LASSO Cox regression model were used for fitting the regression model. Moreover, these features were then integrated into a radiomics signature. An individualized rad score was calculated from a linear combination of the selected features, which were weighted by their respective coefficients. Results: When the patients in the training and test datasets were stratified into high-risk and low-risk groups according to the rad scores, the overall survival of the groups was significantly different. The C-index values for the homology-based features (rad score), standard features (rad score), and tumor size were 0.625, 0.603, and 0.607, respectively, for the training datasets and 0.689, 0.668, and 0.667 for the test datasets. This result showed that homology-based radiomic features had slightly higher prediction power than the standard radiomic features. Conclusions: Prediction performance using homology-based radiomic features had a comparable or slightly higher prediction power than standard radiomic features. These findings suggest that homology-based radiomic features may have great potential for improving the prognostic prediction accuracy of CT-based radiomics. In this result, i...

show abstract

“…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%

Homology‐based radiomic features for prediction of the prognosis of lung cancer based on CT‐based radiomics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…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%

“…Matrices of the texture categories were constructed by assessing in three dimensions with a 26voxel connectivity. To reduce the variability of radiomic feature values due to different voxel sizes, the voxel size was resampled into a 1 × 1 × 1 mm 3 cubic interpolation prior to feature extraction, in an identical manner to a previous radiomics study of lung cancer [28]. To increase the sensitivity of all texture features and two first-order features, a CT value histogram was resampled into a bin width of 25 Hounsfield units (HU) [6,29,30].…”

Section: Radiomic Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of radiomic features in diagnostic CT images with and without contrast enhancement in the delayed phase for NSCLC patients

et al. 2020

View full text Add to dashboard Cite

“…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%

Homological radiomics analysis for prognostic prediction in lung cancer patients

Ninomiya

Arimura

2020

Physica Medica

Self Cite

View full text Add to dashboard Cite

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.

Cited by 60 publications

References 53 publications

Homology‐based radiomic features for prediction of the prognosis of lung cancer based on CT‐based radiomics

Homology‐based radiomic features for prediction of the prognosis of lung cancer based on CT‐based radiomics

Comparison of radiomic features in diagnostic CT images with and without contrast enhancement in the delayed phase for NSCLC patients

Homological radiomics analysis for prognostic prediction in lung cancer patients

Contact Info

Product

Resources

About