Repeatability of 18 F-FDG PET radiomic features: A phantom study to explore sensitivity to image reconstruction settings, noise, and delineation method

Abstract

Background: ¹⁸ F-fluoro-2-deoxy-D-Glucose positron emission tomography (¹⁸ F-FDG PET) radiomics has the potential to guide the clinical decision making in cancer patients, but validation is required before radiomics can be implemented in the clinical setting. The aim of this study was to explore how feature space reduction and repeatability of ¹⁸ F-FDG PET radiomic features are affected by various sources of variation such as underlying data (e.g., object size and uptake), image reconstruction methods and settings, noise, discretization method, and delineation method.

Methods: The NEMA image quality phantom was scanned with various sphere-to-background ratios (SBR), simulating different activity uptakes, including spheres with low uptake, that is, SBR smaller than 1. Furthermore, images of a phantom containing 3D printed inserts reflecting realistic heterogeneity uptake patterns were acquired. Data were reconstructed using various matrix sizes, reconstruction algorithms, and scan durations (noise). For every specific reconstruction and noise level, ten statistically equal replicates were generated. The phantom inserts were delineated using CT and PET-based segmentation methods. A total of 246 radiomic features was extracted from each image dataset. Images were discretized with a fixed number of 64 bins (FBN) and a fixed bin width (FBW) of 0.25 for the high and a FBW of 0.05 for the low uptake data. In terms of feature reduction, we determined the impact of these factors on the composition of feature clusters, which were defined on the basis of Spearman's correlation matrices. To assess feature repeatability, the intraclass correlation coefficient was calculated over the ten replicates.

Results: In general, larger spheres with high uptake resulted in better repeatability compared to smaller low uptake spheres. In terms of repeatability, features extracted from heterogeneous phantom inserts were comparable to features extracted from bigger high uptake spheres. For example, for an EARL-compliant reconstruction, larger and smaller high uptake spheres yielded good repeatability for 32% and 30% of the features, while the heterogeneous inserts resulted in 34% repeatable features. For the low uptake spheres, this was the case for 22% and 20% of the features for bigger and smaller spheres, respectively. Images reconstructed with point-spread-function (PSF) resulted in the highest repeatability when compared with OSEM or time-of-flight, for example, 53%, 30%, and 32% of repeatable features, respectively (for unsmoothed data, discretized with FBN, 300 s scan duration). Reducing image noise (increasing scan duration and smoothing) and using CT-based segmentation for the low uptake spheres yielded improved repeatability. FBW discretization resulted in higher repeatability than FBN discretization, for example, 89% and 35% of the features, respectively (for the EARL-compliant reconstruction and larger high uptake spheres).

Conclusion: Feature space reduction and repeatability of ¹⁸ F-FDG PET radiomic features depended on all studied factors. The high sensitivity of PET radiomic features to image quality suggests that a high level of image acquisition and preprocessing standardization is required to be used as clinical imaging biomarker.

Keywords: 18F-FDG PET/CT radiomic features; delineation; image reconstruction settings.

Figure 1

PET images showing results with 3D printed inserts: tumor 1 with homogeneous uptake, tumor 2 with heterogeneity over 2 compartments, and tumor 3 containing a necrotic core (from left to right) [Color figure can be viewed at wileyonlinelibrary.com]

Figure 2

Impact of discretization and reconstruction setting on the composition of feature clusters: feature clusters (red rectangles) were defined based on Spearman's correlation matrices. The default setting in the upper left corner consists of all activity uptakes and sphere sizes, matrix size 256 × 256 × 111, OSEM reconstruction, 120 s scan duration, FBW discretization, 4 mm FWHM, and CT‐based segmentation. The feature order of this setting was also used to display the correlation matrices of the other settings. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 3

Impact of sphere size and activity uptake on the composition of feature clusters: feature clusters (red rectangles) were defined based on Spearman's correlation matrices. The default setting in the upper left corner consists of the data of larger high uptake spheres, EARL reconstruction, matrix size 256 × 256 × 111, 120 s scan duration, FBW discretization, and CT‐based segmentation. The feature order of this setting was also used to display the correlation matrices of the other settings. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 4

Percentage of repeatable features discretized with FBW: Percentage of all features discretized with FBW and segmented based on CT exhibiting an ICC >0.8 for all studied settings and underlying data categories (from left to right: heterogeneous 3D prints, bigger spheres with high uptake, smaller spheres with high uptake, bigger spheres with low uptake, and smaller spheres with low uptake). TOFM400/P+TM400: TOF/PSF+TOF reconstruction with matrix size 400 × 400. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 5

Percentage of all features discretized with FBN: Percentage of all features discretized with FBN and segmented based on CT exhibiting an ICC >0.8 for all studied settings and underlying data categories (from left to right: heterogeneous 3D prints, bigger spheres with high uptake, smaller spheres with high uptake, bigger spheres with low uptake, and smaller spheres with low uptake). TOFM400/P+TM400: TOF/PSF+TOF reconstruction with matrix size 400 × 400. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 6

Percentage of repeatable features discretized with FBW: Percentage of all features discretized with FBW and segmented based on PET exhibiting an ICC >0.8 for all studied settings and underlying data categories (from left to right: heterogeneous 3D prints, bigger spheres with high uptake, smaller spheres with high uptake, bigger spheres with low uptake, and smaller spheres with low uptake). TOFM400/P+TM400: TOF/PSF+TOF reconstruction with matrix size 400 × 400. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 7

Percentage of repeatable features discretized with FBN: Percentage of all features discretized with FBW and segmented based on PET exhibiting an ICC >0.8 for all studied settings and underlying data categories (from left to right: heterogeneous 3D prints, bigger spheres with high uptake, smaller spheres with high uptake, bigger spheres with low uptake, and smaller spheres with low uptake). TOFM400/P+TM400: TOF/PSF+TOF reconstruction with matrix size 400 × 400. [Color figure can be viewed at wileyonlinelibrary.com]

Figure 8

Influence of noise on number of repeatable features extracted from NEMA IQ phantom scan with SBR 1:10 for all reconstructions, scan durations, smoothing factors, and matrix sizes: Number of repeatable features in the different subcategories as function of image noise