Influence of CT acquisition and reconstruction parameters on radiomic feature reproducibility

Midya, Abhishek; Chakraborty, Jayasree; Gönen, Mithat; Richard, K. G.; Simpson, Amber L.

doi:10.1117/1.jmi.5.1.011020

Cited by 75 publications

(84 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[11][12][13] Studies have shown that feature reproducibility may be affected by differences in image acquisition parameters, such as slice thickness and reconstruction algorithm. [14][15][16][17] Since clinical image acquisition protocols are one of the major sources of variation among different hospitals, phantoms allow testing, comparison, and harmonization of radiomic features in similar vein to diagnostic imaging quality assurance. We hypothesize that even simplified phantoms allow us to test for radiomic features that may already become unstable even under tightly constrained conditions.…”

Section: Introductionmentioning

confidence: 99%

Multicenter CT phantoms public dataset for radiomics reproducibility tests

et al. 2019

View full text Add to dashboard Cite

PurposeThe aim of this paper is to describe a public, open‐access, computed tomography (CT) phantom image set acquired at three centers and collected especially for radiomics reproducibility research. The dataset is useful to test radiomic features reproducibility with respect to various parameters, such as acquisition settings, scanners, and reconstruction algorithms.Acquisition and validation methodsThree phantoms were scanned in three independent institutions. Images of the following phantoms were acquired: Catphan 700 and COPDGene Phantom II (Phantom Laboratory, Greenwich, NY, USA), and the Triple modality 3D Abdominal Phantom (CIRS, Norfolk, VA, USA). Data were collected at three Dutch medical centers: MAASTRO Clinic (Maastricht, NL), Radboud University Medical Center (Nijmegen, NL), and University Medical Center Groningen (Groningen, NL) with scanners from two different manufacturers Siemens Healthcare and Philips Healthcare. The following acquisition parameter were varied in the phantom scans: slice thickness, reconstruction kernel, and tube current.Data format and usage notesWe made the dataset publically available on the Dutch instance of “Extensible Neuroimaging Archive Toolkit‐XNAT” (https://xnat.bmia.nl). The dataset is freely available and reusable with attribution (Creative Commons 3.0 license).Potential applicationsOur goal was to provide a findable, open‐access, annotated, and reusable CT phantom dataset for radiomics reproducibility studies. Reproducibility testing and harmonization are fundamental requirements for wide generalizability of radiomics‐based clinical prediction models. It is highly desirable to include only reproducible features into models, to be more assured of external validity across hitherto unseen contexts. In this view, phantom data from different centers represent a valuable source of information to exclude CT radiomic features that may already be unstable with respect to simplified structures and tightly controlled scan settings. The intended extension of our shared dataset is to include other modalities and phantoms with more realistic lesion simulations.

show abstract

Section: Introductionmentioning

confidence: 99%

Multicenter CT phantoms public dataset for radiomics reproducibility tests

et al. 2019

View full text Add to dashboard Cite

show abstract

“…However, due to the use of non-standardized 9 imaging protocols, variations in acquisition and image re-10 construction parameters may cause inconsistency in radiomic 11 features extracted from images, which poses a barrier to the 12 practice of radiomics in large-scale [10], [24], [25]. 13 A. CT Image Acquisition Parameters 14 In modern CT imaging, there are a large number of imaging 15 protocols, and using non-standardized imaging protocols is 16 common [6]. The CT image acquisition parameters includ kV 17 (the x-tube voltage), mAs (the product of x-ray tube current 18 and exposure time), collimation, pitch, reconstruction kernel, 19 field-of-view, and slice thickness [27], [28].…”

Section: Introductionmentioning

confidence: 99%

“…In the example 3 shown in Figure 1, each lung tumor was acquired twice using 4 two different reconstruction kernels (Bl64 and Br40, Siemens 5 Healthineers, Erlangen, Germany). The figure demonstrates 6 that the appearances (as well as the radiomic features) of the 7 same tumor can be strongly affected by the selection of CT 8 acquisition parameters. 9 To overcome the barriers that prevent the use of CT images 10 in large-scale radiomic studies, algorithms have been devel- 11 oped aiming to integrate and standardize CT images from 12 multiple sources.…”

mentioning

confidence: 99%

“…the differences between any two adjacent values (in 4 our case, the absolute errors between any two adjacent saved 5 model states) are measured and are compared with a threshold 6. CUSUM is computed as the number of the difference values7 higher than a threshold (called out-of-control points).…”

mentioning

confidence: 99%

“…The training 5 state of every 2.5 training epochs was saved. We compared6 all the three models using the same validation data at every 7 saved model state (Figure 9A). The normalized sum of the8 CUSUM values of cGAN, GAN ai singleDG , and GANai over 9…”

mentioning

confidence: 99%

See 2 more Smart Citations

GANai: Standardizing CT Images using Generative Adversarial Network with Alternative Improvement

Liang

Zhang

Brooks

et al. 2018

Preprint

View full text Add to dashboard Cite

Computed tomography (CT) is a widely-used diag-1 nostic image modality routinely used for assessing anatomical 2 tissue characteristics. However, non-standardized imaging pro-3 tocols are commonplace, which poses a fundamental challenge 4 in large-scale cross-center CT image analysis. One approach 5to address the problem is to standardize CT images using 6 generative adversarial network models (GAN). GAN learns the 7 data distribution of training images and generate synthesized 8 images under the same distribution. However, existing GAN 9 models are not directly applicable to this task mainly due to the 10 lack of constraints on the mode of data to generate. Furthermore, 11 they treat every image equally, but in real applications, some 12 images are more difficult to standardize than the others. All these 13 may lead to the lack-of-detail problem in CT image synthesis. 14 We present a new GAN model called GANai to mitigate the 15 differences in radiomic features across CT images captured 16 using non-standard imaging protocols. Given source images, 17 GANai composes new images by specifying a high-level goal 18 that the image features of the synthesized images should be 19 similar to those of the standard images. GANai introduces an 20 alternative improvement training strategy to alternatively and 21 steadily improve model performance. The new training strategy 22 enables a series of technical improvements, including phase-23 specific loss functions, phase-specific training data, and the adop-24 tion of ensemble learning, leading to better model performance. 25 The experimental results show that GANai is significantly better 26 than the existing state-of-the-art image synthesis algorithms on 27 CT image standardization. Also, it significantly improves the 28 efficiency and stability of GAN model training. 29 Index Terms-computed tomography, image synthesis, generative 30 adversarial network, alternative training 31

show abstract

Investigating the role of imaging factors in the variability of CT‐based texture analysis metrics

Varghese,

Cen,

Jensen

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

ObjectiveThis study assesses the robustness of first‐order radiomic texture features namely interquartile range (IQR), coefficient of variation (CV) and standard deviation (SD) derived from computed tomography (CT) images by varying dose, reconstruction algorithms and slice thickness using scans of a uniform water phantom, a commercial anthropomorphic liver phantom, and a human liver in‐vivo.Materials and MethodsScans were acquired on a 16 cm detector GE Revolution Apex Edition CT scanner with variations across three different nominal slice thicknesses: 0.625, 1.25, and 2.5 mm, three different dose levels: CTDIvol of 13.86 mGy for the standard dose, 40% reduced dose and 60% reduced dose and two different reconstruction algorithms: a deep learning image reconstruction (DLIR‐high) algorithm and a hybrid iterative reconstruction (IR) algorithm ASiR‐V50% (AV50) were explored, varying one at a time. To assess the effect of non‐linear modifications of images by AV50 and DLIR‐high, images of the water phantom were also reconstructed using filtered back projection (FBP). Quantitative measures of IQR, CV and SD were extracted from twelve pre‐selected, circular (1 cm diameter) regions of interest (ROIs) capturing different texture patterns across all scans.ResultsAcross all scans, imaging, and reconstruction settings, CV, IQR and SD were observed to increase with reduction in dose and slice thickness. An exception to this observation was found when using FBP reconstruction. Lower values of CV, IQR and SD were observed in DLIR‐high reconstructions compared to AV50 and FBP. The Poisson statistics were more stringently noted in FBP than DLIR‐high and AV50, due to the non‐linear nature of the latter two algorithms.ConclusionVariation in image noise due to dose reduction algorithms, tube current, and slice thickness show a consistent trend across phantom and patient scans. Prospective evaluation across multiple centers, scanners and imaging protocols is needed for establishing quality assurance standards of radiomics.

show abstract

Influence of CT acquisition and reconstruction parameters on radiomic feature reproducibility

Cited by 75 publications

References 43 publications

Multicenter CT phantoms public dataset for radiomics reproducibility tests

Multicenter CT phantoms public dataset for radiomics reproducibility tests

GANai: Standardizing CT Images using Generative Adversarial Network with Alternative Improvement

Investigating the role of imaging factors in the variability of CT‐based texture analysis metrics

Contact Info

Product

Resources

About