Limits...
The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis.

Leijenaar RT, Nalbantov G, Carvalho S, van Elmpt WJ, Troost EG, Boellaard R, Aerts HJ, Gillies RJ, Lambin P - Sci Rep (2015)

Bottom Line: As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins.Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods.Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

View Article: PubMed Central - PubMed

Affiliation: Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+), Maastricht, the Netherlands.

ABSTRACT
FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) R(D), dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) R(B), maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, R(B) was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

No MeSH data available.


Related in: MedlinePlus

Graphical representation of pairwise ICCs for each feature for different values of B (ICCB) and D (ICCD), based on pre-treatment imaging.Blue lines extend from the minimum to the maximum observed ICC value. Median ICC values are represented by the red markers. Abbreviations of feature groups:gray-level co-occurrence (GLCM), gray-level run-length (GLRLM) and gray-level size-zone (GLSZM). Abbreviations of feature names: Difference Entropy (Diff. Entropy), Inverse difference moment normalized (IDMN), Inverse difference normalized (IDN), Informational measure of correlation 1 (IMC1), Informational measure of correlation 2 (IMC2), Maximum probability (MP), Gray-Level Nonuniformity (GLN), High Gray-Level Run Emphasis (HGLRE), Low Gray-Level Run Emphasis (LGLRE), Long Run Emphasis (LRE), Long Run High Gray-Level Emphasis (LRHGLE), Long Run Low Gray-Level Emphasis (LRLGLE), Run-Length Nonuniformity (RLN), Run Percentage (RP), Short Run Emphasis (SRE), Short Run High Gray-Level Emphasis (SRHGLE), Short Run Low Gray-Level Emphasis (SRLGLE), High Intensity Emphasis (HIE), High Intensity Large Area Emphasis (HILAE), High Intensity Small Area Emphasis (HISAE), Intensity Variability (IV), Large Area Emphasis (LAE), Low Intensity Emphasis (LIE), Low Intensity Large Area Emphasis (LILAE), Low Intensity Small Area Emphasis (LISAE), Small Area Emphasis (SAE), Size-Zone Variability (SZV), Zone Percentage (ZP)
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4525145&req=5

f3: Graphical representation of pairwise ICCs for each feature for different values of B (ICCB) and D (ICCD), based on pre-treatment imaging.Blue lines extend from the minimum to the maximum observed ICC value. Median ICC values are represented by the red markers. Abbreviations of feature groups:gray-level co-occurrence (GLCM), gray-level run-length (GLRLM) and gray-level size-zone (GLSZM). Abbreviations of feature names: Difference Entropy (Diff. Entropy), Inverse difference moment normalized (IDMN), Inverse difference normalized (IDN), Informational measure of correlation 1 (IMC1), Informational measure of correlation 2 (IMC2), Maximum probability (MP), Gray-Level Nonuniformity (GLN), High Gray-Level Run Emphasis (HGLRE), Low Gray-Level Run Emphasis (LGLRE), Long Run Emphasis (LRE), Long Run High Gray-Level Emphasis (LRHGLE), Long Run Low Gray-Level Emphasis (LRLGLE), Run-Length Nonuniformity (RLN), Run Percentage (RP), Short Run Emphasis (SRE), Short Run High Gray-Level Emphasis (SRHGLE), Short Run Low Gray-Level Emphasis (SRLGLE), High Intensity Emphasis (HIE), High Intensity Large Area Emphasis (HILAE), High Intensity Small Area Emphasis (HISAE), Intensity Variability (IV), Large Area Emphasis (LAE), Low Intensity Emphasis (LIE), Low Intensity Large Area Emphasis (LILAE), Low Intensity Small Area Emphasis (LISAE), Small Area Emphasis (SAE), Size-Zone Variability (SZV), Zone Percentage (ZP)

Mentions: To assess whether feature values (using either RB or RD) were consistent for different discretization values, we calculated the pairwise ICCs for each feature between different values of B (ICCB) and D (ICCD), respectively. This analysis was performed on the pre-treatment images. For each feature, we reported the range and median of all pairwise ICCs (Fig. 3). None of the observed pairwise ICCs was higher than 0.85, meaning that textural features and their ascribed value depend on the intensity resolution used for SUV discretization.


The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis.

Leijenaar RT, Nalbantov G, Carvalho S, van Elmpt WJ, Troost EG, Boellaard R, Aerts HJ, Gillies RJ, Lambin P - Sci Rep (2015)

Graphical representation of pairwise ICCs for each feature for different values of B (ICCB) and D (ICCD), based on pre-treatment imaging.Blue lines extend from the minimum to the maximum observed ICC value. Median ICC values are represented by the red markers. Abbreviations of feature groups:gray-level co-occurrence (GLCM), gray-level run-length (GLRLM) and gray-level size-zone (GLSZM). Abbreviations of feature names: Difference Entropy (Diff. Entropy), Inverse difference moment normalized (IDMN), Inverse difference normalized (IDN), Informational measure of correlation 1 (IMC1), Informational measure of correlation 2 (IMC2), Maximum probability (MP), Gray-Level Nonuniformity (GLN), High Gray-Level Run Emphasis (HGLRE), Low Gray-Level Run Emphasis (LGLRE), Long Run Emphasis (LRE), Long Run High Gray-Level Emphasis (LRHGLE), Long Run Low Gray-Level Emphasis (LRLGLE), Run-Length Nonuniformity (RLN), Run Percentage (RP), Short Run Emphasis (SRE), Short Run High Gray-Level Emphasis (SRHGLE), Short Run Low Gray-Level Emphasis (SRLGLE), High Intensity Emphasis (HIE), High Intensity Large Area Emphasis (HILAE), High Intensity Small Area Emphasis (HISAE), Intensity Variability (IV), Large Area Emphasis (LAE), Low Intensity Emphasis (LIE), Low Intensity Large Area Emphasis (LILAE), Low Intensity Small Area Emphasis (LISAE), Small Area Emphasis (SAE), Size-Zone Variability (SZV), Zone Percentage (ZP)
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4525145&req=5

f3: Graphical representation of pairwise ICCs for each feature for different values of B (ICCB) and D (ICCD), based on pre-treatment imaging.Blue lines extend from the minimum to the maximum observed ICC value. Median ICC values are represented by the red markers. Abbreviations of feature groups:gray-level co-occurrence (GLCM), gray-level run-length (GLRLM) and gray-level size-zone (GLSZM). Abbreviations of feature names: Difference Entropy (Diff. Entropy), Inverse difference moment normalized (IDMN), Inverse difference normalized (IDN), Informational measure of correlation 1 (IMC1), Informational measure of correlation 2 (IMC2), Maximum probability (MP), Gray-Level Nonuniformity (GLN), High Gray-Level Run Emphasis (HGLRE), Low Gray-Level Run Emphasis (LGLRE), Long Run Emphasis (LRE), Long Run High Gray-Level Emphasis (LRHGLE), Long Run Low Gray-Level Emphasis (LRLGLE), Run-Length Nonuniformity (RLN), Run Percentage (RP), Short Run Emphasis (SRE), Short Run High Gray-Level Emphasis (SRHGLE), Short Run Low Gray-Level Emphasis (SRLGLE), High Intensity Emphasis (HIE), High Intensity Large Area Emphasis (HILAE), High Intensity Small Area Emphasis (HISAE), Intensity Variability (IV), Large Area Emphasis (LAE), Low Intensity Emphasis (LIE), Low Intensity Large Area Emphasis (LILAE), Low Intensity Small Area Emphasis (LISAE), Small Area Emphasis (SAE), Size-Zone Variability (SZV), Zone Percentage (ZP)
Mentions: To assess whether feature values (using either RB or RD) were consistent for different discretization values, we calculated the pairwise ICCs for each feature between different values of B (ICCB) and D (ICCD), respectively. This analysis was performed on the pre-treatment images. For each feature, we reported the range and median of all pairwise ICCs (Fig. 3). None of the observed pairwise ICCs was higher than 0.85, meaning that textural features and their ascribed value depend on the intensity resolution used for SUV discretization.

Bottom Line: As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins.Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods.Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

View Article: PubMed Central - PubMed

Affiliation: Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+), Maastricht, the Netherlands.

ABSTRACT
FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) R(D), dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) R(B), maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, R(B) was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

No MeSH data available.


Related in: MedlinePlus