Principal component analysis of texture features derived from FDG PET images of melanoma lesions
Abstract Background The clinical utility of radiomics is hampered by a high correlation between the large number of features analysed which may result in the “bouncing beta” phenomenon which could in part explain why in a similar patient population texture features identified and/or cut-off values o...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-09-01
|
| Series: | EJNMMI Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40658-022-00491-x |
| _version_ | 1818020913540497408 |
|---|---|
| author | DeLeu Anne-Leen Sathekge Machaba Maes Alex De Spiegeleer Bart Beels Laurence Sathekge Mike Pottel Hans Christophe Van de Wiele |
| author_facet | DeLeu Anne-Leen Sathekge Machaba Maes Alex De Spiegeleer Bart Beels Laurence Sathekge Mike Pottel Hans Christophe Van de Wiele |
| author_sort | DeLeu Anne-Leen |
| collection | DOAJ |
| description | Abstract Background The clinical utility of radiomics is hampered by a high correlation between the large number of features analysed which may result in the “bouncing beta” phenomenon which could in part explain why in a similar patient population texture features identified and/or cut-off values of prognostic significance differ from one study to another. Principal component analysis (PCA) is a technique for reducing the dimensionality of large datasets containing highly correlated variables, such as texture feature datasets derived from FDG PET images, increasing data interpretability whilst at the same time minimizing information loss by creating new uncorrelated variables that successively maximize variance. Here, we report on PCA of a texture feature dataset derived from 123 malignant melanoma lesions with a significant range in lesion size using the freely available LIFEx software. Results Thirty-eight features were derived from all lesions. All features were standardized. The statistical assumptions for carrying out PCA analysis were met. Seven principal components with an eigenvalue > 1 were identified. Based on the “elbow sign” of the Scree plot, only the first five were retained. The contribution to the total variance of these components derived using Varimax rotation was, respectively, 30.6%, 23.6%, 16.1%, 7.4% and 4.1%. The components provided summarized information on the locoregional FDG distribution with an emphasis on high FDG uptake regions, contrast in FDG uptake values (steepness), tumour volume, locoregional FDG distribution with an emphasis on low FDG uptake regions and on the rapidity of changes in SUV intensity between different regions. Conclusions PCA allowed to reduce the dataset of 38 features to a set of 5 uncorrelated new variables explaining approximately 82% of the total variance contained within the dataset. These principal components may prove more useful for multiple regression analysis considering the relatively low numbers of patients usually included in clinical trials on FDG PET texture analysis. Studies assessing the superior differential diagnostic, predictive or prognostic value of principal components derived using PCA as opposed to the initial texture features in clinical relevant settings are warranted. |
| first_indexed | 2024-04-14T08:11:52Z |
| format | Article |
| id | doaj.art-6d544ee1fcbf415d8d3ebcad8f1cf0d1 |
| institution | Directory Open Access Journal |
| issn | 2197-7364 |
| language | English |
| last_indexed | 2024-04-14T08:11:52Z |
| publishDate | 2022-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EJNMMI Physics |
| spelling | doaj.art-6d544ee1fcbf415d8d3ebcad8f1cf0d12022-12-22T02:04:32ZengSpringerOpenEJNMMI Physics2197-73642022-09-019111010.1186/s40658-022-00491-xPrincipal component analysis of texture features derived from FDG PET images of melanoma lesionsDeLeu Anne-Leen0Sathekge Machaba1Maes Alex2De Spiegeleer Bart3Beels Laurence4Sathekge Mike5Pottel Hans6Christophe Van de Wiele7Department of Nuclear Medicine, AZ GroeningeDepartment of Nuclear Medicine, University of PretoriaDepartment of Nuclear Medicine, AZ GroeningeLaboratory of Drug Quality and Registration, University GhentDepartment of Nuclear Medicine, AZ GroeningeDepartment of Nuclear Medicine, University of PretoriaDepartment of Public Health and Primary Care, KU Leuven Campus KULAK KortrtijkDepartment of Nuclear Medicine, AZ GroeningeAbstract Background The clinical utility of radiomics is hampered by a high correlation between the large number of features analysed which may result in the “bouncing beta” phenomenon which could in part explain why in a similar patient population texture features identified and/or cut-off values of prognostic significance differ from one study to another. Principal component analysis (PCA) is a technique for reducing the dimensionality of large datasets containing highly correlated variables, such as texture feature datasets derived from FDG PET images, increasing data interpretability whilst at the same time minimizing information loss by creating new uncorrelated variables that successively maximize variance. Here, we report on PCA of a texture feature dataset derived from 123 malignant melanoma lesions with a significant range in lesion size using the freely available LIFEx software. Results Thirty-eight features were derived from all lesions. All features were standardized. The statistical assumptions for carrying out PCA analysis were met. Seven principal components with an eigenvalue > 1 were identified. Based on the “elbow sign” of the Scree plot, only the first five were retained. The contribution to the total variance of these components derived using Varimax rotation was, respectively, 30.6%, 23.6%, 16.1%, 7.4% and 4.1%. The components provided summarized information on the locoregional FDG distribution with an emphasis on high FDG uptake regions, contrast in FDG uptake values (steepness), tumour volume, locoregional FDG distribution with an emphasis on low FDG uptake regions and on the rapidity of changes in SUV intensity between different regions. Conclusions PCA allowed to reduce the dataset of 38 features to a set of 5 uncorrelated new variables explaining approximately 82% of the total variance contained within the dataset. These principal components may prove more useful for multiple regression analysis considering the relatively low numbers of patients usually included in clinical trials on FDG PET texture analysis. Studies assessing the superior differential diagnostic, predictive or prognostic value of principal components derived using PCA as opposed to the initial texture features in clinical relevant settings are warranted.https://doi.org/10.1186/s40658-022-00491-xMelanomaRadiomicsLIFExPrincipal component analysis |
| spellingShingle | DeLeu Anne-Leen Sathekge Machaba Maes Alex De Spiegeleer Bart Beels Laurence Sathekge Mike Pottel Hans Christophe Van de Wiele Principal component analysis of texture features derived from FDG PET images of melanoma lesions EJNMMI Physics Melanoma Radiomics LIFEx Principal component analysis |
| title | Principal component analysis of texture features derived from FDG PET images of melanoma lesions |
| title_full | Principal component analysis of texture features derived from FDG PET images of melanoma lesions |
| title_fullStr | Principal component analysis of texture features derived from FDG PET images of melanoma lesions |
| title_full_unstemmed | Principal component analysis of texture features derived from FDG PET images of melanoma lesions |
| title_short | Principal component analysis of texture features derived from FDG PET images of melanoma lesions |
| title_sort | principal component analysis of texture features derived from fdg pet images of melanoma lesions |
| topic | Melanoma Radiomics LIFEx Principal component analysis |
| url | https://doi.org/10.1186/s40658-022-00491-x |
| work_keys_str_mv | AT deleuanneleen principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT sathekgemachaba principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT maesalex principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT despiegeleerbart principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT beelslaurence principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT sathekgemike principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT pottelhans principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions AT christophevandewiele principalcomponentanalysisoftexturefeaturesderivedfromfdgpetimagesofmelanomalesions |