Using a Generative Adversarial Network for CT Normalization and Its Impact on Radiomic Features

Cardiac magnetic resonance (MR) images are often collected with different imaging parameters, which may impact the calculated values of myocardial radiomic features. To investigate the sensitivity of myocardial radiomic features to changes in imaging parameters in cardiac MR images. Prospective. A total of 11 healthy participants/five patients. A 3 T/cine balanced steady-state free-precession, T1 -weighted spoiled gradient-echo, T2 -weighted turbo spin-echo, and quantitative T1 and T2 mapping. For each sequence, the flip angle, in-plane resolution, slice thickness, and parallel imaging technique were varied to study the sensitivity of radiomic features to alterations in imaging parameters. Myocardial contours were manually delineated by experienced readers, and a total of 1023 radiomic features were extracted using PyRadiomics with 11 image filters and six feature families. Sensitivity was defined as the standardized mean difference (D effect size), and the robust features were defined at sensitivity < 0.2. Sensitivity analysis was performed on predefined sets of reproducible features. The analysis was performed using the entire cohort of 16 subejcts. 64% of radiomic features were robust (sensitivity < 0.2) to changes in any imaging parameter. In qualitative sequences, radiomic features were most sensitive to changes in in-plane spatial resolution (spatial resolution: 0.6 vs. flip angle: 0.19, parallel imaging: 0.18, slice thickness: 0.07; P < 0.01 for all); in quantitative sequences, radiomic features were least sensitive to changes in spatial resolution (spatial resolution: 0.07 vs. slice thickness: 0.16, flip angle: 0.24; P < 0.01 for all). In an individual feature level, no singular feature family/image filter was identified as robust (sensitivity < 0.2) across sequences; however, highly sensitive features were predominantly associated with high-frequency wavelet filters across all sequences (32/50 features). In cardiac MR, a considerable number of radiomic features are sensitive to changes in sequence parameters. 1 TECHNICAL EFFICACY: Stage 1.

Objective. The study aims to systematically characterize the effect of CT parameter variations on images and lung radiomic and deep features, and to evaluate the ability of different image harmonization methods to mitigate the observed variations.Approach. A retrospective in-house sinogram dataset of 100 low-dose chest CT scans was reconstructed by varying radiation dose (100%, 25%, 10%) and reconstruction kernels (smooth, medium, sharp). A set of image processing, convolutional neural network (CNNs), and generative adversarial network-based (GANs) methods were trained to harmonize all image conditions to a reference condition (100% dose, medium kernel). Harmonized scans were evaluated for image similarity using peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS), and for the reproducibility of radiomic and deep features using concordance correlation coefficient (CCC).Main Results. CNNs consistently yielded higher image similarity metrics amongst others; for Sharp/10%, which exhibited the poorest visual similarity, PSNR increased from a mean ± CI of 17.763 ± 0.492 to 31.925 ± 0.571, SSIM from 0.219 ± 0.009 to 0.754 ± 0.017, and LPIPS decreased from 0.490 ± 0.005 to 0.275 ± 0.016. Texture-based radiomic features exhibited a greater degree of variability across conditions, i.e. a CCC of 0.500 ± 0.332, compared to intensity-based features (0.972 ± 0.045). GANs achieved the highest CCC (0.969 ± 0.009 for radiomic and 0.841 ± 0.070 for deep features) amongst others. CNNs are suitable if downstream applications necessitate visual interpretation of images, whereas GANs are better alternatives for generating reproducible quantitative image features needed for machine learning applications.Significance. Understanding the efficacy of harmonization in addressing multi-parameter variability is crucial for optimizing diagnostic accuracy and a critical step toward building generalizable models suitable for clinical use.

We aim to interrogate the role of positron emission tomography (PET) image discretization parameters on the prognostic value of radiomic features in patients with oropharyngeal cancer. A prospective clinical trial (NCT01908504) enrolled patients with oropharyngeal squamous cell carcinoma (; mixed HPV status) undergoing definitive radiotherapy and evaluated intra-treatment 18fluorodeoxyglucose PET as a potential imaging biomarker of early metabolic response. The primary tumor volume was manually segmented by a radiation oncologist on PET/CT images acquired two weeks into treatment (20Gy). From this, 54 radiomic texture features were extracted. Two image discretization techniques-fixed bin number (FBN) and fixed bin size (FBS)-were considered to evaluate systematic changes in the bin number ({32, 64, 128, 256} gray levels) and bin size ({0.10, 0.15, 0.22, 0.25} bin-widths). For each discretization-specific radiomic feature space, an LASSO-regularized logistic regression model was independently trained to predict residual and/or recurrent disease. The model training was based on Monte Carlo cross-validation with a 20% testing hold-out, 50 permutations, and minor-class up-sampling to account for imbalanced outcomes data. Performance differences among the discretization-specific models were quantified via receiver operating characteristic curve analysis. A final parameter-optimized logistic regression model was developed by incorporating different settings parameterizations into the same model. FBN outperformed FBS in predicting residual and/or recurrent disease. The four FBN models achieved AUC values of 0.63, 0.61, 0.65, and 0.62 for 32, 64, 128, and 256 gray levels, respectively. By contrast, the average AUC of the four FBS models was 0.53. The parameter-optimized model, comprising features joint entropy (FBN = 64) and information measure correlation 1 (FBN = 128), achieved an AUC of 0.70. Kaplan-Meier analyses identified these features to be associated with disease-free survival ( and , respectively; log-rank test). Our findings suggest that the prognostic value of individual radiomic features may depend on feature-specific discretization parameter settings.

Superiority of Radiomics Information Compared to Clinical Factors in Characterization of Human Papilloma Virus (HPV) Status in Patients With Oropharyngeal Squamous Cell Carcinomas

Aim: To assess the difference in radiomic feature values between pairs of mammographic images used for processing(FOR PROC) and for presentation(FOR PRES) as well as the ability to determine the BIRADS density classification from these radiomic features with different classification models. Methods: A dataset of FOR PROC and FOR PRES image pairs annotated with labels for the BI-RADS classification done by a radiologist is used in this study. The differences in radiomic feature values between the image types are evaluated with the intraclass correlation coefficient(ICC). Additionally, the discriminative power of radiomic feature values regarding the BI-RADS score is evaluated with Logistic Regression, Random Forest and a 5-layer deep Neural Network. The results of these models are evaluated with a 5-fold crossvalidation. Results: The reliability of radiomic feature is generally low between pairs of FOR PROC and FOR PRES images for all radiomic feature groups. Furthermore, the simple models used to determine the ability to assign the BI-RADS density classification based on the radiomic feature values reached insufficient accuracy to be considered adequate. Conclusion: The study revealed low reliability between both image types. Furthermore radiomic features alone seem to be insufficient to determine the BI-RADS classification using simple models.

MRI pulse sequences and imaging parameters substantially influence the variation of MRI radiomics features, thus impose a critical challenge on MRI radiomics reproducibility and reliability. This study aims to prospectively investigate the impact of various imaging parameters on MRI radiomics features in a 3D T2-weighted (T2W) turbo-spin-echo (TSE) pulse sequence for MR-guided-radiotherapy (MRgRT). An anthropomorphic phantom was scanned using a 3D-T2W-TSE MRgRT sequence at 1.5T under a variety of acquisition imaging parameter changes. T1 and T2 relaxation times of the phantom were also measured. 93 first-order and texture radiomics features in the original and 14 transformed images, yielding 1,395 features in total, were extracted from 10 volumes-of-interest (VOIs). The percentage deviation (d%) of radiomics feature values from the baseline values and intra-class correlation coefficient (ICC) with the baseline were calculated. Robust radiomics features were identified based on the excellent agreement of radiomics feature values with the baseline, i.e., the averaged d% <5% and ICC >0.90 in all VOIs for all imaging parameter variations. The radiomics feature values changed considerably but to different degrees with different imaging parameter adjustments, in the ten VOIs. The deviation d% ranged from 0.02% to 321.3%, with a mean of 12.5% averaged for all original features in all ten VOIs. First-order and GLCM features were generally more robust to imaging parameters than other features in the original images. There were also significantly different radiomics feature values (ANOVA, P<0.001) between the original and the transformed images, exhibiting quite different robustness to imaging parameters. 330 out of 1395 features (23.7%) robust to imaging parameters were identified. GLCM and GLSZM features had the most (42.5%, 153/360) and least (3.8%, 9/240) robust features in the original and transformed images, respectively. This study helps better understand the quantitative dependence of radiomics feature values on imaging parameters in a 3D-T2W-TSE sequence for MRgRT. Imaging parameter heterogeneity should be considered as a significant source of radiomics variability and uncertainty, which must be well harmonized for reliable clinical use. The identified robust features to imaging parameters are helpful for the pre-selection of radiomics features for reliable radiomics modeling.

Ranking the most influential predictors of CT-based radiomics feature values in metastatic lung adenocarcinoma

The value of radiomic features in chronic obstructive pulmonary disease assessment: a prospective study

EDITORIAL article Front. Oncol., 07 February 2023Sec. Cancer Imaging and Image-directed Interventions Volume 13 - 2023 | https://doi.org/10.3389/fonc.2023.1143204

This study addresses the lack of systematic investigation into the prognostic value of hand-crafted radiomic features derived from diffusion tensor imaging (DTI) in isocitrate dehydrogenase (IDH) wild-type glioblastoma (GBM), as well as the limited understanding of the biological interpretation of individual DTI radiomic features and metrics. To develop and validate a DTI-based radiomic model for predicting prognosis in patients with IDH wild-type GBM and reveal the biological underpinning of individual DTI radiomic features and metrics. The DTI-based radiomic signature was an independent prognostic factor (p < 0.001). Incorporating the radiomic signature into a clinical model resulted in a radiomic-clinical nomogram that predicted survival better than either the radiomic model or clinical model alone, with a better calibration and classification accuracy. Four categories of pathways (synapse, proliferation, DNA damage response, and complex cellular functions) were significantly correlated with the DTI-based radiomic features and DTI metrics. The prognostic radiomic features derived from DTI are driven by distinct pathways involved in synapse, proliferation, DNA damage response, and complex cellular functions of GBM.

Radiomic Feature Robustness and Reproducibility in Quantitative Bone Radiography: A Study on Radiologic Parameter Changes

Recent advances in convolutional neural networks have shown promising results in 3D shape completion. But due to GPU memory limitations, these methods can only produce low-resolution outputs. To inpaint 3D models with semantic plausibility and contextual details, we introduce a hybrid framework that combines a 3D Encoder-Decoder Generative Adversarial Network (3D-ED-GAN) and a Longterm Recurrent Convolutional Network (LRCN). The 3DED- GAN is a 3D convolutional neural network trained with a generative adversarial paradigm to fill missing 3D data in low-resolution. LRCN adopts a recurrent neural network architecture to minimize GPU memory usage and incorporates an Encoder-Decoder pair into a Long Shortterm Memory Network. By handling the 3D model as a sequence of 2D slices, LRCN transforms a coarse 3D shape into a more complete and higher resolution volume. While 3D-ED-GAN captures global contextual structure of the 3D shape, LRCN localizes the fine-grained details. Experimental results on both real-world and synthetic data show reconstructions from corrupted models result in complete and high-resolution 3D objects.

To retrospectively assess the effect of CT slice thickness on the reproducibility of radiomic features (RFs) of lung cancer, and to investigate whether convolutional neural network (CNN)-based super-resolution (SR) algorithms can improve the reproducibility of RFs obtained from images with different slice thicknesses. CT images with 1-, 3-, and 5-mm slice thicknesses obtained from 100 pathologically proven lung cancers between July 2017 and December 2017 were evaluated. CNN-based SR algorithms using residual learning were developed to convert thick-slice images into 1-mm slices. Lung cancers were semi-automatically segmented and a total of 702 RFs (tumor intensity, texture, and wavelet features) were extracted from 1-, 3-, and 5-mm slices, as well as the 1-mm slices generated from the 3- and 5-mm images. The stabilities of the RFs were evaluated using concordance correlation coefficients (CCCs). The mean CCCs for the comparisons of original 1 mm vs. 3 mm, 1 mm vs. 5 mm, and 3 mm vs. 5 mm images were 0.41, 0.27, and 0.65, respectively (p < 0.001 for all comparisons). Tumor intensity features showed the best reproducibility while wavelets showed the lowest reproducibility. The majority of RFs failed to achieve reproducibility (CCC ≥ 0.85; 3.6%, 1.0%, and 21.5%, respectively). After applying the CNN-based SR algorithms, the reproducibility significantly improved in all three pairings (mean CCCs: 0.58, 0.45, and 0.72; p < 0.001 for all comparisons). The reproducible RFs also increased (36.3%, 17.4%, and 36.9%, respectively). The reproducibility of RFs in lung cancer is significantly influenced by CT slice thickness, which can be improved by the CNN-based SR algorithms.

Objective.Lung nodule appearance may provide prognostic information, as the presence of spiculation increases the suspicion of a nodule being cancerous. Spiculations can be quantified using morphological radiomics features extracted from CT images. Radiomics features can be affected by the acquisition parameters and scanner technologies; thus, it is essential to identify imaging conditions that provide reliable measurements, particularly for emerging technologies like photon-counting CT (PCCT). This study aimed to systematically quantify the effect of imaging parameters on the radiomics measurements using a virtual imaging trial (VIT) platform, and further verify the findings with human clinical data.Approach.The VIT utilized nine virtual patients, each with three 6 mm nodules of varying spiculations. The virtual patients were run through a validated CT simulator (DukeSim) to acquire images at three dose levels (CTDIvol = 2.85, 5.69, and 11.38 mGy) with a clinical energy-integrating CT and a PCCT. The acquired projection images were reconstructed using multiple slice thicknesses, kernels, and matrix sizes. The reconstructed images were processed to extract morphological features using three segmentation methods. The features were clustered into three broad type categories. Features extracted from the acquired CT images were compared to their corresponding ground truth values, across all imaging conditions.Main results.Among all imaging conditions, slice thickness had the greatest effect on the radiomics measurements. When the thickest slices were used, the coefficient of variation increased by [1.19%-9.66%] in the energy integrating CT images, and [3.94%-24.43%] in the PCCT images. For both scanners, varying the kernel sharpness and dose affected the radiomics measurements insignificantly, while pixel size and segmentation method were observed to have stronger effects. Under varying imaging conditions, the trends and magnitude of radiomics features measurements were coherent with virtual trial results.Significance.The findings stress the importance of choosing optimal reconstruction settings for radiomics extraction to achieve precise feature quantifications.

This study aims to establish and validate a cross‐institutional prediction system for estimating patient‐specific organ doses from chest CT scans. By collaborating across multiple institutions, the study seeks to develop models that allow rapid online estimation of organ doses, eliminating the need for complex organ segmentation. Researchers delineate skin outlines from chest CT images obtained from two different institutions. Radiomics features are extracted from the chest CT data and skin contours. Organ doses are computed using Monte Carlo simulations as reference organ doses. Single‐ and cross‐institutional support vector regression (SVR) models are trained with radiomics features to predict organ doses from chest CT scans. Model performance is assessed using metrics like maean absolute percentage error (MAPE) and R‐squared (R2). For chest organs (lungs, heart, spinal cord, trachea, and esophagus), single‐institutional SVR models achieve MAPE values ranging from 4.72% to 15.31% and R2 values from 0.73 to 0.93. Cross‐institutional models have MAPE values in the range of 2.16–7.49% and R2 values from 0.84 to 0.99. SVR models trained with radiomics features from skin outlines can reliably estimate organ doses from chest CT scans. The proposed method is applicable across different institutions, and cross‐institutional models enhance predictive accuracy, generality, and robustness.