Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules
Here, we report on the added value of principal component analysis applied to a dataset of texture features derived from 39 solitary pulmonary lung nodule (SPN) lesions for the purpose of differentiating benign from malignant lesions, as compared to the use of SUVmax alone. Texture features were der...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/24/7731 |
| _version_ | 1797380549311987712 |
|---|---|
| author | Birte Bomhals Lara Cossement Alex Maes Mike Sathekge Kgomotso M. G. Mokoala Chabi Sathekge Katrien Ghysen Christophe Van de Wiele |
| author_facet | Birte Bomhals Lara Cossement Alex Maes Mike Sathekge Kgomotso M. G. Mokoala Chabi Sathekge Katrien Ghysen Christophe Van de Wiele |
| author_sort | Birte Bomhals |
| collection | DOAJ |
| description | Here, we report on the added value of principal component analysis applied to a dataset of texture features derived from 39 solitary pulmonary lung nodule (SPN) lesions for the purpose of differentiating benign from malignant lesions, as compared to the use of SUVmax alone. Texture features were derived using the LIFEx software. The eight best-performing first-, second-, and higher-order features for separating benign from malignant nodules, in addition to SUVmax (MaximumGreyLevelSUVbwIBSI184IY), were included for PCA. Two principal components (PCs) were retained, of which the contributions to the total variance were, respectively, 87.6% and 10.8%. When included in a logistic binomial regression analysis, including age and gender as covariates, both PCs proved to be significant predictors for the underlying benign or malignant character of the lesions under study (<i>p</i> = 0.009 for the first PC and 0.020 for the second PC). As opposed to SUVmax alone, which allowed for the accurate classification of 69% of the lesions, the regression model including both PCs allowed for the accurate classification of 77% of the lesions. PCs derived from PCA applied on selected texture features may allow for more accurate characterization of SPN when compared to SUVmax alone. |
| first_indexed | 2024-03-08T20:38:53Z |
| format | Article |
| id | doaj.art-6fe73085b3f746db9899eac030404d60 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-08T20:38:53Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-6fe73085b3f746db9899eac030404d602023-12-22T14:17:35ZengMDPI AGJournal of Clinical Medicine2077-03832023-12-011224773110.3390/jcm12247731Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary NodulesBirte Bomhals0Lara Cossement1Alex Maes2Mike Sathekge3Kgomotso M. G. Mokoala4Chabi Sathekge5Katrien Ghysen6Christophe Van de Wiele7Department of Diagnostic Sciences, University Ghent, 9000 Ghent, BelgiumDepartment of Diagnostic Sciences, University Ghent, 9000 Ghent, BelgiumDepartment of Morphology and Functional Imaging, University Hospital Leuven, 3000 Leuven, BelgiumDepartment of Nuclear Medicine, Steve Biko Academic Hospital and Nuclear Medicine Research Infrastructure (NuMeRi), University of Pretoria, Pretoria 0002, South AfricaDepartment of Nuclear Medicine, Steve Biko Academic Hospital and Nuclear Medicine Research Infrastructure (NuMeRi), University of Pretoria, Pretoria 0002, South AfricaDepartment of Nuclear Medicine, Steve Biko Academic Hospital and Nuclear Medicine Research Infrastructure (NuMeRi), University of Pretoria, Pretoria 0002, South AfricaDepartment of Pneumology, AZ Groeninge, 8500 Kortrijk, BelgiumDepartment of Diagnostic Sciences, University Ghent, 9000 Ghent, BelgiumHere, we report on the added value of principal component analysis applied to a dataset of texture features derived from 39 solitary pulmonary lung nodule (SPN) lesions for the purpose of differentiating benign from malignant lesions, as compared to the use of SUVmax alone. Texture features were derived using the LIFEx software. The eight best-performing first-, second-, and higher-order features for separating benign from malignant nodules, in addition to SUVmax (MaximumGreyLevelSUVbwIBSI184IY), were included for PCA. Two principal components (PCs) were retained, of which the contributions to the total variance were, respectively, 87.6% and 10.8%. When included in a logistic binomial regression analysis, including age and gender as covariates, both PCs proved to be significant predictors for the underlying benign or malignant character of the lesions under study (<i>p</i> = 0.009 for the first PC and 0.020 for the second PC). As opposed to SUVmax alone, which allowed for the accurate classification of 69% of the lesions, the regression model including both PCs allowed for the accurate classification of 77% of the lesions. PCs derived from PCA applied on selected texture features may allow for more accurate characterization of SPN when compared to SUVmax alone.https://www.mdpi.com/2077-0383/12/24/7731solitary pulmonary nodulestexture featuresprincipal component analysis |
| spellingShingle | Birte Bomhals Lara Cossement Alex Maes Mike Sathekge Kgomotso M. G. Mokoala Chabi Sathekge Katrien Ghysen Christophe Van de Wiele Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules Journal of Clinical Medicine solitary pulmonary nodules texture features principal component analysis |
| title | Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules |
| title_full | Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules |
| title_fullStr | Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules |
| title_full_unstemmed | Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules |
| title_short | Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules |
| title_sort | principal component analysis applied to radiomics data added value for separating benign from malignant solitary pulmonary nodules |
| topic | solitary pulmonary nodules texture features principal component analysis |
| url | https://www.mdpi.com/2077-0383/12/24/7731 |
| work_keys_str_mv | AT birtebomhals principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT laracossement principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT alexmaes principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT mikesathekge principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT kgomotsomgmokoala principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT chabisathekge principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT katrienghysen principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules AT christophevandewiele principalcomponentanalysisappliedtoradiomicsdataaddedvalueforseparatingbenignfrommalignantsolitarypulmonarynodules |