Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study.
Ontology highlight
ABSTRACT:
SUBMITTER: Keller H
PROVIDER: S-EPMC9025788 | biostudies-literature | 2022 Apr
REPOSITORIES: biostudies-literature
Publications
Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study.
Keller Harald H Shek Tina T Driscoll Brandon B Xu Yiwen Y Nghiem Brian B Nehmeh Sadek S Grkovski Milan M Schmidtlein Charles Ross CR Budzevich Mikalai M Balagurunathan Yoganand Y Sunderland John J JJ Beichel Reinhard R RR Uribe Carlos C Lee Ting-Yim TY Li Fiona F Jaffray David A DA Yeung Ivan I
Tomography (Ann Arbor, Mich.) 20220413 2
For multicenter clinical studies, characterizing the robustness of image-derived radiomics features is essential. Features calculated on PET images have been shown to be very sensitive to image noise. The purpose of this work was to investigate the efficacy of a relatively simple harmonization strategy on feature robustness and agreement. A purpose-built texture pattern phantom was scanned on 10 different PET scanners in 7 institutions with various different image acquisition and reconstruction ...[more]
Similar Datasets
Project description:BackgroundImage harmonization has been proposed to minimize heterogeneity in brain PET scans acquired in multi-center studies. However, standard validated methods and software tools are lacking. Here, we assessed the performance of a framework for the harmonization of brain PET scans in a multi-center European clinical trial.MethodHoffman 3D brain phantoms were acquired in 28 PET systems and reconstructed using site-specific settings. Full Width at Half Maximum (FWHM) of the Effective Image Resolution (EIR) and harmonization kernels were estimated for each scan. The target EIR was selected as the coarsest EIR in the imaging network. Using "Hoffman 3D brain Analysis tool," indicators of image quality were calculated before and after the harmonization: The Coefficient of Variance (COV%), Gray Matter Recovery Coefficient (GMRC), Contrast, Cold-Spot RC, and left-to-right GMRC ratio. A COV% ≤ 15% and Contrast ≥ 2.2 were set as acceptance criteria. The procedure was repeated to achieve a 6-mm target EIR in a subset of scans. The method's robustness against typical dose-calibrator-based errors was assessed.ResultsThe EIR across systems ranged from 3.3 to 8.1 mm, and an EIR of 8 mm was selected as the target resolution. After harmonization, all scans met acceptable image quality criteria, while only 13 (39.4%) did before. The harmonization procedure resulted in lower inter-system variability indicators: Mean ± SD COV% (from 16.97 ± 6.03 to 7.86 ± 1.47%), GMRC Inter-Quartile Range (0.040-0.012), and Contrast SD (0.14-0.05). Similar results were obtained with a 6-mm FWHM target EIR. Errors of ± 10% in the DRO activity resulted in differences below 1 mm in the estimated EIR.ConclusionHarmonizing the EIR of brain PET scans significantly reduced image quality variability while minimally affecting quantitative accuracy. This method can be used prospectively for harmonizing scans to target sharper resolutions and is robust against dose-calibrator errors. Comparable image quality is attainable in brain PET multi-center studies while maintaining quantitative accuracy.
| S-EPMC10618151 | biostudies-literature
Project description:The purpose of this study was to (i) evaluate the test-retest repeatability and reproducibility of radiomic features in virtual monoenergetic images (VMI) from dual-energy CT (DECT) depending on VMI energy (40, 50, 75, 120, 190 keV), radiation dose (5 and 15 mGy), and DECT approach (dual-source and split-filter DECT) in a phantom (ex vivo), and (ii) to assess the impact of VMI energy and feature repeatability on machine-learning-based classification in vivo in 72 patients with 72 hypodense liver lesions. Feature repeatability and reproducibility were determined by concordance-correlation-coefficient (CCC) and dynamic range (DR) ≥0.9. Test-retest repeatability was high within the same VMI energies and scan conditions (percentage of repeatable features ranging from 74% for SFDE mode at 40 keV and 15 mGy to 86% for DSDE at 190 keV and 15 mGy), while reproducibility varied substantially across different VMI energies and DECTs (percentage of reproducible features ranging from 32.8% for SFDE at 5 mGy comparing 40 with 190 keV to 99.2% for DSDE at 15 mGy comparing 40 with 50 keV). No major differences were observed between the two radiation doses (<10%) in all pair-wise comparisons. In vivo, machine learning classification using penalized regression and random forests resulted in the best discrimination of hemangiomas and metastases at low-energy VMI (40 keV), and for cysts at high-energy VMI (120 keV). Feature selection based on feature repeatability did not improve classification performance. Our results demonstrate the high repeatability of radiomics features when keeping scan and reconstruction conditions constant. Reproducibility diminished when using different VMI energies or DECT approaches. The choice of optimal VMI energy improved lesion classification in vivo and should hence be adapted to the specific task.
| S-EPMC8467875 | biostudies-literature
Project description:Background18 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.MethodsThe 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.ResultsIn 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).ConclusionFeature 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.
| S-EPMC7380016 | biostudies-literature
Project description:BackgroundPhoton-counting detector computed tomography (PCD-CT) may influence imaging characteristics for various clinical conditions due to higher signal and contrast-to-noise ratio in virtual monoenergetic images (VMI). Radiomics analysis relies on quantification of image characteristics. We evaluated the impact of different VMI reconstructions on radiomic features in in vitro and in vivo PCD-CT datasets.MethodsAn organic phantom consisting of twelve samples (four oranges, four onions, and four apples) was scanned five times. Twenty-three patients who had undergone coronary computed tomography angiography on a first generation PCD-CT system with the same image acquisitions were analyzed. VMIs were reconstructed at 6 keV levels (40, 55, 70, 90, 120, and 190 keV). The phantoms and the patients' left ventricular myocardium (LVM) were segmented for all reconstructions. Ninety-three original radiomic features were extracted. Repeatability and reproducibility were evaluated through intraclass correlations coefficient (ICC) and post hoc paired samples ANOVA t test.ResultsThere was excellent repeatability for radiomic features in phantom scans (all ICC = 1.00). Among all VMIs, 36/93 radiomic features (38.7%) in apples, 28/93 (30.1%) in oranges, and 33/93 (35.5%) in onions were not significantly different. For LVM, the percentage of stable features was high between VMIs ≥ 90 keV (90 versus 120 keV, 77.4%; 90 versus 190 keV, 83.9%; 120 versus 190 keV, 89.3%), while comparison to lower VMI levels led to fewer reproducible features (40 versus 55 keV, 8.6%).ConclusionsVMI levels influence the stability of radiomic features in an organic phantom and patients' LVM; stability decreases considerably below 90 keV.Relevance statementSpectral reconstructions significantly influence radiomic features in vitro and in vivo, necessitating standardization and careful attention to these reconstruction parameters before clinical implementation.Key points• Radiomic features have an excellent repeatability within the same PCD-CT acquisition and reconstruction. • Differences in VMI lead to decreased reproducibility for radiomic features. • VMI ≥ 90 keV increased the reproducibility of the radiomic features.
| S-EPMC10597903 | biostudies-literature
Project description:Previously, we developed an "activity painting" tool for PET image simulation; however, it could simulate heterogeneous patterns only in the air. We aimed to improve this phantom technique to simulate arbitrary lesions in a radioactive background to perform relevant multi-center radiomic analysis. We conducted measurements moving a 22Na point source in a 20-liter background volume filled with 5 kBq/mL activity with an adequately controlled robotic system to prevent the surge of the water. Three different lesion patterns were "activity-painted" in five PET/CT cameras, resulting in 8 different reconstructions. We calculated 46 radiomic indeces (RI) for each lesion and imaging setting, applying absolute and relative discretization. Reproducibility and reliability were determined by the inter-setting coefficient of variation (CV) and the intraclass correlation coefficient (ICC). Hypothesis tests were used to compare RI between lesions. By simulating precisely the same lesions, we confirmed that the reconstructed voxel size and the spatial resolution of different PET cameras were critical for higher order RI. Considering conventional RIs, the SUVpeak and SUVmean proved the most reliable (CV<10%). CVs above 25% are more common for higher order RIs, but we also found that low CVs do not necessarily imply robust parameters but often rather insensitive RIs. Based on the hypothesis test, most RIs could clearly distinguish between the various lesions using absolute resampling. ICC analysis also revealed that most RIs were more reproducible with absolute discretization. The activity painting method in a real radioactive environment proved suitable for precisely detecting the radiomic differences derived from the different camera settings and texture characteristics. We also found that inter-setting CV is not an appropriate metric for analyzing RI parameters' reliability and robustness. Although multicentric cohorts are increasingly common in radiomics analysis, realistic texture phantoms can provide indispensable information on the sensitivity of an RI and how an individual RI parameter measures the texture.
| S-EPMC11500893 | biostudies-literature
Project description:ObjectiveSimultaneous PET/MRIs vary in their quantitative PET performance due to inherent differences in the physical systems and differences in the image reconstruction implementation. This variability in quantitative accuracy confounds the ability to meaningfully combine and compare data across scanners. In this work, we define image reconstruction parameters that lead to comparable contrast recovery curves across simultaneous PET/MRI systems.MethodThe NEMA NU-2 image quality phantom was imaged on one GE Signa and on one Siemens mMR PET/MRI scanner. The phantom was imaged at 9.7:1 contrast with standard spheres (diameter 10, 13, 17, 22, 28, 37 mm) and with custom spheres (diameter: 8.5, 11.5, 15, 25, 32.5, 44 mm) using a standardized methodology. Analysis was performed on a 30 min listmode data acquisition and on 6 realizations of 5 min from the listmode data. Images were reconstructed with the manufacturer provided iterative image reconstruction algorithms with and without point spread function (PSF) modeling. For both scanners, a post-reconstruction Gaussian filter of 3-7 mm in steps of 1 mm was applied. Attenuation correction was provided from a scaled computed tomography (CT) image of the phantom registered to the MR-based attenuation images and verified to align on the non-attenuation corrected PET images. For each of these image reconstruction parameter sets, contrast recovery coefficients (CRCs) were determined for the SUVmean, SUVmax and SUVpeak for each sphere. A hybrid metric combining the root-mean-squared discrepancy (RMSD) and the absolute CRC values was used to simultaneously optimize for best match in CRC between the two scanners while simultaneously weighting toward higher resolution reconstructions. The image reconstruction parameter set was identified as the best candidate reconstruction for each vendor for harmonized PET image reconstruction.ResultsThe range of clinically relevant image reconstruction parameters demonstrated widely different quantitative performance across cameras. The best match of CRC curves was obtained at the lowest RMSD values with: for CRCmean, 2 iterations-7 mm filter on the GE Signa and 4 iterations-6 mm filter on the Siemens mMR, for CRCmax, 4 iterations-6 mm filter on the GE Signa, 4 iterations-5 mm filter on the Siemens mMR and for CRCpeak, 4 iterations-7 mm filter with PSF on the GE Signa and 4 iterations-7 mm filter on the Siemens mMR. Over all reconstructions, the RMSD between CRCs was 1.8%, 3.6% and 2.9% for CRC mean, max and peak, respectively. The solution of 2 iterations-3 mm on the GE Signa and 4 iterations-3 mm on Siemens mMR, both with PSF, led to simultaneous harmonization and with high CRC and low RMSD for CRC mean, max and peak with RMSD values of 2.8%, 5.8% and 3.2%, respectively.ConclusionsFor two commercially available PET/MRI scanners, user-selectable parameters that control iterative updates, image smoothing and PSF modeling provide a range of contrast recovery curves that allow harmonization in harmonization strategies of optimal match in CRC or high CRC values. This work demonstrates that nearly identical CRC curves can be obtained on different commercially available scanners by selecting appropriate image reconstruction parameters.
| S-EPMC8571452 | biostudies-literature
Project description:IntroductionThe standardized uptake value ratio (SUVR) is used to measure amyloid beta-positron emission tomography (Aβ-PET) uptake in the brainDifferences in PET scanner technologies and image reconstruction techniques can lead to variability in PET images across scanners. This poses a challenge for Aβ-PET studies conducted in multiple centers. The aim of harmonization is to achieve consistent Aβ-PET measurements across different scanners. In this study, we propose an Aβ-PET harmonization method of matching spatial resolution, as measured via a barrel phantom, across PET scanners. Our approach was validated using paired subject data, for which patients were imaged on multiple scanners.MethodsIn this study, three different PET scanners were evaluated: the Siemens Biograph Vision 600, Siemens Biograph molecular computed tomography (mCT), and Philips Gemini TF64. A total of five, eight, and five subjects were each scanned twice with [18F]-NAV4694 across Vision-mCT, mCT-Philips, and Vision-Philips scanner pairs. The Vision and mCT scans were reconstructed using various iterations, subsets, and post-reconstruction Gaussian smoothing, whereas only one reconstruction configuration was used for the Philips scans. The full-width at half-maximum (FWHM) of each reconstruction configuration was calculated using [18F]-filled barrel phantom scans with the Society of Nuclear Medicine and Molecular Imaging (SNMMI) phantom analysis toolkit. Regional SUVRs were calculated from 72 brain regions using the automated anatomical labelling atlas 3 (AAL3) atlas for each subject and reconstruction configuration. Statistical similarity between SUVRs was assessed using paired (within subject) t-tests for each pair of reconstructions across scanners; the higher the p-value, the greater the similarity between the SUVRs.ResultsVision-mCT harmonization: Vision reconstruction with FWHM = 4.10 mm and mCT reconstruction with FWHM = 4.30 mm gave the maximal statistical similarity (maximum p-value) between regional SUVRs. Philips-mCT harmonization: The FWHM of the Philips reconstruction was 8.2 mm and the mCT reconstruction with the FWHM of 9.35 mm, which gave the maximal statistical similarity between regional SUVRs. Philips-Vision harmonization: The Vision reconstruction with an FWHM of 9.1 mm gave the maximal statistical similarity between regional SUVRs when compared with the Philips reconstruction of 8.2 mm and were selected as the harmonized for each scanner pair.ConclusionBased on data obtained from three sets of participants, each scanned on a pair of PET scanners, it has been verified that using reconstruction configurations that produce matched-barrel, phantom spatial resolutions results in maximally harmonized Aβ-PET quantitation between scanner pairs. This finding is encouraging for the use of PET scanners in multi-center trials or updates during longitudinal studies.HighlightsQuestion: Does the process of matching the barrel phantom-derived spatial resolution between scanners harmonize amyloid beta-standardized uptake value ratio (Aβ-SUVR) quantitation? Pertinent findings: It has been validated that reconstruction pairs with matched barrel phantom-derived spatial resolution maximize the similarity between subjects paired Aβ-PET (positron emission tomography) SUVR values recorded on two scanners. Implications for patient care: Harmonization between scanners in multi-center trials and PET camera updates in longitudinal studies can be achieved using a simple and efficient phantom measurement procedure, beneficial for the validity of Aβ-PET quantitation measurements.
| S-EPMC10927914 | biostudies-literature
Project description:The repeatability and reproducibility of radiomic features extracted from CT scans need to be investigated to evaluate the temporal stability of imaging features with respect to a controlled scenario (test-retest), as well as their dependence on acquisition parameters such as slice thickness, or tube current. Only robust and stable features should be used in prognostication/prediction models to improve generalizability across multiple institutions. In this study, we investigated the repeatability and reproducibility of radiomic features with respect to three different scanners, variable slice thickness, tube current, and use of intravenous (IV) contrast medium, combining phantom studies and human subjects with non-small cell lung cancer. In all, half of the radiomic features showed good repeatability (ICC > 0.9) independent of scanner model. Within acquisition protocols, changes in slice thickness was associated with poorer reproducibility compared to the use of IV contrast. Broad feature classes exhibit different behaviors, with only few features appearing to be the most stable. 108 features presented both good repeatability and reproducibility in all the experiments, most of them being wavelet and Laplacian of Gaussian features.
| S-EPMC7820018 | biostudies-literature
Project description:PurposeTo improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.MethodsGAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the clinical impact of GAN-harmonization was analyzed by predicting the development of distant metastases using a logistic regression model incorporating first-order statistics and texture features from baseline 18F-FDG PET before and after harmonization.ResultsImage quality remained high (structural similarity: left kidney ≥ 0.800, right kidney ≥ 0.806, liver ≥ 0.780, lung ≥ 0.838, spleen ≥ 0.793, whole-body ≥ 0.832) after image harmonization across all utilized datasets. Using GAN-harmonization, inter-site reproducibility of radiomic features in healthy liver tissue increased at least by ≥ 5 ± 14% (first-order), ≥ 16 ± 7% (GLCM), ≥ 19 ± 5% (GLRLM), ≥ 16 ± 8% (GLSZM), ≥ 17 ± 6% (GLDM), and ≥ 23 ± 14% (NGTDM). In the head and neck cancer cohort, the outcome prediction improved from AUC 0.68 (95% CI 0.66-0.71) to AUC 0.73 (0.71-0.75) by application of GAN-harmonization.ConclusionsGANs are capable of performing image harmonization and increase reproducibility and predictive performance of radiomic features derived from different centers and scanners.
| S-EPMC11224088 | biostudies-literature
Project description:PurposeLow photon count in 89Zr-Immuno-PET results in images with a low signal-to-noise ratio (SNR). Since PET radiomics are sensitive to noise, this study focuses on the impact of noise on radiomic features from 89Zr-Immuno-PET clinical images. We hypothesise that 89Zr-Immuno-PET derived radiomic features have: (1) noise-induced variability affecting their precision and (2) noise-induced bias affecting their accuracy. This study aims to identify those features that are not or only minimally affected by noise in terms of precision and accuracy.MethodsCount-split 89Zr-Immuno-PET patient scans from previous studies with three different 89Zr-labelled monoclonal antibodies were used to extract radiomic features at 50% (S50p) and 25% (S25p) of their original counts. Tumour lesions were manually delineated on the original full-count 89Zr-Immuno-PET scans. Noise-induced variability and bias were assessed using intraclass correlation coefficient (ICC) and similarity distance metric (SDM), respectively. Based on the ICC and SDM values, the radiomic features were categorised as having poor [0, 0.5), moderate [0.5, 0.75), good [0.75, 0.9), or excellent [0.9, 1] precision and accuracy. The number of features classified into these categories was compared between the S50p and S25p images using Fisher's exact test. All p values < 0.01 were considered statistically significant.ResultsFor S50p, a total of 92% and 90% features were classified as having good or excellent ICC and SDM respectively, while for S25p, these decreased to 81% and 31%. In total, 148 features (31%) showed robustness to noise with good or moderate ICC and SDM in both S50p and S25p. The number of features classified into the four ICC and SDM categories between S50p and S25p was significantly different statistically.ConclusionSeveral radiomic features derived from low SNR 89Zr-Immuno-PET images exhibit noise-induced variability and/or bias. However, 196 features (43%) that show minimal noise-induced variability and bias in S50p images have been identified. These features are less affected by noise and are, therefore, suitable candidates to be further studied as prognostic and predictive quantitative biomarkers in 89Zr-Immuno-PET studies.
| S-EPMC8894530 | biostudies-literature