Reproducibility of tumor uptake heterogeneity characterization through textural feature analysis in 18F-FDG PET

Preoperative prediction of lymph node metastasis in endometrial cancer patients via an intratumoral and peritumoral multiparameter MRI radiomics nomogram

Introduction

While lymph node metastasis (LNM) plays a critical role in determining treatment options for endometrial cancer (EC) patients, the existing preoperative methods for evaluating the lymph node state are not always satisfactory. This study aimed to develop and validate a nomogram based on intra- and peritumoral radiomics features and multiparameter magnetic resonance imaging (MRI) features to preoperatively predict LNM in EC patients.

Methods

Three hundred and seventy-four women with histologically confirmed EC were divided into training (n = 220), test (n = 94), and independent validation (n = 60) cohorts. Radiomic features were extracted from intra- and peritumoral regions via axial T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) mapping. A radiomics model (annotated as the Radscore) was established using the selected features from different regions. The clinical parameters were statistically analyzed. A nomogram was developed by combining the Radscore and the most predictive clinical parameters. Decision curve analysis (DCA) and the net reclassification index (NRI) were used to assess the clinical benefit of using the nomogram.

Results

Nine radiomics features were ultimately selected from the intra- and peritumoral regions via ADC mapping and T2WI. The nomogram combining the Radscore, serum CA125 level, and tumor area ratio achieved the highest AUCs in the training, test and independent validation sets (nomogram vs. Radscore vs. clinical model: 0.878 vs. 0.850 vs. 0.674 (training), 0.877 vs. 0.838 vs. 0.668 (test), and 0.864 vs. 0.836 vs. 0.618 (independent validation)). The DCA and NRI results revealed the nomogram had greater diagnostic performance and net clinical benefits than the Radscore alone.

Conclusion

The combined intra- and peritumoral region multiparameter MRI radiomics nomogram showed good diagnostic performance and could be used to preoperatively predict LNM in patients with EC.

Stability of radiomic features from positron emission tomography images: a phantom study comparing advanced reconstruction algorithms and ordered subset expectation maximization

In this study, we compared the repeatability and reproducibility of radiomic features obtained from positron emission tomography (PET) images according to the reconstruction algorithm used-advanced reconstruction algorithms, such as HYPER iterative (IT), HYPER deep learning reconstruction (DLR), and HYPER deep progressive reconstruction (DPR), or traditional Ordered Subset Expectation Maximization (OSEM)-to understand the potential variations and implications of using advanced reconstruction techniques in PET-based radiomics. We used a heterogeneous phantom with acrylic spherical beads (4- or 8-mm diameter) filled with 18F. PET images were acquired and reconstructed using OSEM, IT, DLR, and DPR. Original and wavelet radiomic features were calculated using SlicerRadiomics. Radiomic feature repeatability was assessed using the Coefficient of Variance (COV) and intraclass correlation coefficient (ICC), and inter-acquisition time reproducibility was assessed using the concordance correlation coefficient (CCC). For the 4- and 8-mm diameter beads phantom, the proportion of radiomic features with a COV < 10% was equivocal or higher for the advanced reconstruction algorithm than for OSEM. ICC indicated that advanced methods generally outperformed OSEM in repeatability, except for the original features of the 8-mm beads phantom. In the inter-acquisition time reproducibility analysis, the combinations of 3 and 5 min exhibited the highest reproducibility in both phantoms, with IT and DPR showing the highest proportion of radiomic features with CCC > 0.8. Advanced reconstruction methods provided enhanced stability of radiomic features compared with OSEM, suggesting their potential for optimal image reconstruction in PET-based radiomics, offering potential benefits in clinical diagnostics and prognostics.

Difference in Laterality of the Dorsal Striatum in Schizoaffective Disorder

BACKGROUND

Recent research has demonstrated that the dorsal striatum is directly associated with the integration of cognitive, sensory-motor, and motivational/emotional data. Disruptions in the corticostriatal circuit have been implicated in the pathophysiology of psychosis. The dorsal striatum was reported to show lateralized pathology in psychotic disorders. In this study, we aimed to analyze the laterality of the dorsal striatum with texture analysis of T2-weighted magnetic resonance imaging (MRI) images from schizoaffective disorder (SAD) patients.

METHODS

Twenty SAD patients, met the inclusion criteria and had available cranial MRI data were assigned as the patient group. Twenty healthy individuals were determined as the control group. Texture analysis values were obtained from striatum region of interests (ROI) generated from T2-weighted MRI images. Data are presented as mean and standard deviation. The suitability of the data for normal distribution was analyzed with the Kolmogorov-Smirnov test. Analysis of variance (ANOVA) test (Post Hoc TUKEY) was employed to compare the group data based on test findings.

RESULTS

There was no significant difference between the groups in terms of gender and age. There were differences in the values of texture analysis parameters of both caudate and putamen nuclei in comparison to controls. We identified differences in the left dorsal striatum nuclei in SAD. The differences in the putamen were more and more pronounced than in the caudate.

CONCLUSIONS

Texture analyses suggest that the left dorsal striatum nuclei may be different in SAD patients. Further studies are needed to determine the pathophysiology of SAD and how it may affect disease treatment.

Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods

PURPOSE

To evaluate robustness of a radiomics-based support vector machine (SVM) model for detection of visually occult PDA on pre-diagnostic CTs by simulating common variations in image acquisition and radiomics workflow using image perturbation methods.

METHODS

Eighteen algorithmically generated-perturbations, which simulated variations in image noise levels (σ, 2σ, 3σ, 5σ), image rotation [both CT image and the corresponding pancreas segmentation mask by 45° and 90° in axial plane], voxel resampling (isotropic and anisotropic), gray-level discretization [bin width (BW) 32 and 64)], and pancreas segmentation (sequential erosions by 3, 4, 6, and 8 pixels and dilations by 3, 4, and 6 pixels from the boundary), were introduced to the original (unperturbed) test subset (n = 128; 45 pre-diagnostic CTs, 83 control CTs with normal pancreas). Radiomic features were extracted from pancreas masks of these additional test subsets, and the model's performance was compared vis-a-vis the unperturbed test subset.

RESULTS

The model correctly classified 43 out of 45 pre-diagnostic CTs and 75 out of 83 control CTs in the unperturbed test subset, achieving 92.2% accuracy and 0.98 AUC. Model's performance was unaffected by a three-fold increase in noise level except for sensitivity declining to 80% at 3σ (p = 0.02). Performance remained comparable vis-a-vis the unperturbed test subset despite variations in image rotation (p = 0.99), voxel resampling (p = 0.25-0.31), change in gray-level BW to 32 (p = 0.31-0.99), and erosions/dilations up to 4 pixels from the pancreas boundary (p = 0.12-0.34).

CONCLUSION

The model's high performance for detection of visually occult PDA was robust within a broad range of clinically relevant variations in image acquisition and radiomics workflow.

The correlation between tumor radiological features and spread through air spaces in peripheral stage IA lung adenocarcinoma: a propensity score-matched analysis

BACKGROUND

The consolidation tumor ratio (CTR) is a predictor of invasiveness in peripheral T1N0M0 lung adenocarcinoma. However, its association with spread through air spaces (STAS) remains largely unexplored. We aimed to explore the correlation between the CTR of primary tumors and STAS in peripheral T1N0M0 lung adenocarcinoma.

METHODS

We collected data from patients who underwent surgery for malignant lung neoplasms between January and November 2022. Univariate and multivariate analyses following propensity-score matching with sex, age, BMI, were performed to identify the independent risk factors for STAS. The incidence of STAS was compared based on pulmonary nodule type. A smooth fitting curve between CTR and STAS was produced by the generalized additive model (GAM) and a multiple regression model was established using CTR and STAS to determine the dose-response relationship and calculate the odds ratio (OR) and 95% confidence interval (CI).

RESULTS

17 (14.5%) were diagnosed with STAS. The univariate analysis demonstrated that the history of the diabetes, size of solid components, spiculation, pleural indentation, pulmonary nodule type, consolidation/tumor ratio of the primary tumor were statistically significant between the STAS-positive and STAS-negative groups following propensity-score matching(p = 0.047, 0.049, 0.030, 0.006, 0.026, and < 0.001, respectively), and multivariate analysis showed that the pleural indentation was independent risk factors for STAS (with p-value and 95% CI of 0.043, (8.543-68.222)). Moreover, the incidence of STAS in the partially solid nodule was significantly different from that in the solid nodule and ground-glass nodule (Pearson Chi-Square = 7.49, p = 0.024). Finally, the smooth fitting curve showed that CTR tended to be linearly associated with STAS by GAM, and the multivariate regression model based on CTR showed an OR value of 1.24 and a p-value of 0.015.

CONCLUSIONS

In peripheral stage IA lung adenocarcinoma, the risk of STAS was increased with the solid component of the primary tumor. The pleural indentation of the primary tumor could be used as a predictor in evaluating the risk of the STAS.

Enhancing Interoperability and Harmonisation of Nuclear Medicine Image Data and Associated Clinical Data

Nuclear imaging techniques such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) in combination with computed tomography (CT) are established imaging modalities in clinical practice, particularly for oncological problems. Due to a multitude of manufacturers, different measurement protocols, local demographic or clinical workflow variations as well as various available reconstruction and analysis software, very heterogeneous datasets are generated. This review article examines the current state of interoperability and harmonisation of image data and related clinical data in the field of nuclear medicine. Various approaches and standards to improve data compatibility and integration are discussed. These include, for example, structured clinical history, standardisation of image acquisition and reconstruction as well as standardised preparation of image data for evaluation. Approaches to improve data acquisition, storage and analysis will be presented. Furthermore, approaches are presented to prepare the datasets in such a way that they become usable for projects applying artificial intelligence (AI) (machine learning, deep learning, etc.). This review article concludes with an outlook on future developments and trends related to AI in nuclear medicine, including a brief research of commercial solutions.

Impact of Tracer Dose Reduction in [18 F]-Labelled Fluorodeoxyglucose-Positron Emission Tomography ([18 F]-FDG)-PET) on Texture Features and Histogram Indices: A Study in Homogeneous Tissues of Phantom and Patient

BACKGROUND

Histogram indices (HIs) and texture features (TFs) are considered to play an important role in future oncologic PET-imaging and it is unknown how these indices are affected by changes of tracer doses. A randomized undersampling of PET list mode data enables a simulation of tracer dose reduction. We performed a phantom study to compare HIs/TFs of simulated and measured tracer dose reductions and evaluated changes of HIs/TFs in the liver of patients with PETs from simulated reduced tracer doses. Overall, 42 HIs/TFs were evaluated in a NEMA phantom at measured and simulated doses (stepwise reduction of [18 F] from 100% to 25% of the measured dose). [18 F]-FDG-PET datasets of 15 patients were simulated from 3.0 down to 0.5 MBq/kgBW in intervals of 0.25 MBq/kgBW. HIs/TFs were calculated from two VOIs placed in physiological tissue of the right and left liver lobe and linear correlations and coefficients of variation analysis were performed.

RESULTS

All 42 TFs did not differ significantly in measured and simulated doses (p > 0.05). Also, 40 TFs showed the same behaviour over dose reduction regarding differences in the same group (measured or simulated), and for 26 TFs a linear behaviour over dose reduction for measured and simulated doses could be validated. Out of these, 13 TFs could be identified, which showed a linear change in TF value in both the NEMA phantom and patient data and therefore should maintain the same informative value when transferred in a dose reduction setting. Out of this Homogeneity 2, Entropy and Zone size non-uniformity are of special interest because they have been described as preferentially considerable for tumour heterogeneity characterization.

CONCLUSIONS

We could show that there was no significant difference of measured and simulated HIs/TFs in the phantom study and most TFs reveal a linear behaviour over dose reduction, when tested in homogeneous tissue. This indicates that texture analysis in PET might be robust to dose modulations.

Preoperative prediction of lymphovascular space invasion in endometrioid adenocarcinoma: an MRI-based radiomics nomogram with consideration of the peritumoral region

BACKGROUND

Lymphovascular space invasion (LVSI) of endometrial cancer (EC) is a postoperative histological index, which is associated with lymph node metastases. A preoperative acknowledgement of LVSI status might aid in treatment decision-making.

PURPOSE

To explore the utility of multiparameter magnetic resonance imaging (MRI) and radiomic features obtained from intratumoral and peritumoral regions for predicting LVSI in endometrioid adenocarcinoma (EEA).

MATERIAL AND METHODS

A total of 334 EEA tumors were retrospectively analyzed. Axial T2-weighted (T2W) imaging and apparent diffusion coefficient (ADC) mapping were conducted. Intratumoral and peritumoral regions were manually annotated as the volumes of interest (VOIs). A support vector machine was applied to train the prediction models. Multivariate logistic regression analysis was used to develop a nomogram based on clinical and tumor morphological parameters and the radiomics score (RadScore). The predictive performance of the nomogram was assessed by the area under the receiver operator characteristic curve (AUC) in the training and validation cohorts.

RESULTS

Among the features obtained from different imaging modalities (T2W imaging and ADC mapping) and VOIs, the RadScore had the best performance in predicting LVSI classification (AUCtrain = 0.919, and AUCvalidation = 0.902). The nomogram based on age, CA125, maximum anteroposterior tumor diameter on sagittal T2W images, tumor area ratio, and RadScore was established to predict LVSI had AUC values in the training and validation cohorts of 0.962 (sensitivity 94.0%, specificity 86.0%) and 0.965 (sensitivity 90.0%, specificity 85.3%), respectively.

CONCLUSION

The intratumoral and peritumoral imaging features were complementary, and the MRI-based radiomics nomogram might serve as a non-invasive biomarker to preoperatively predict LVSI in patients with EEA.

Standardized Radiomics Analysis of Clinical Myocardial Perfusion Stress SPECT Images to Identify Coronary Artery Calcification

PURPOSE

Myocardial perfusion (MP) stress single-photon emission computed tomography (SPECT) is an established diagnostic test for patients suspected of coronary artery disease (CAD). Meanwhile, coronary artery calcification (CAC) scoring obtained from diagnostic CT is a highly sensitive test, offering incremental diagnostic information in identifying patients with significant CAD yet normal MP stress SPECT (MPSS) scans. However, after decades of wide utilization of MPSS, CAC is not commonly reimbursed (e.g. by the CMS), nor widely deployed in community settings. We studied the potential of complementary information deduced from the radiomics analysis of normal MPSS scans in predicting the CAC score.

METHODS

We collected data from 428 patients with normal (non-ischemic) MPSS (99mTc-sestamibi; consensus reading). A nuclear medicine physician verified iteratively reconstructed images (attenuation-corrected) to be free from fixed perfusion defects and artifactual attenuation. Three-dimensional images were automatically segmented into four regions of interest (ROIs), including myocardium and three vascular segments (left anterior descending [LAD]-left circumference [LCX]-right coronary artery [RCA]). We used our software package, standardized environment for radiomics analysis (SERA), to extract 487 radiomic features in compliance with the image biomarker standardization initiative (IBSI). Isotropic cubic voxels were discretized using fixed bin-number discretization (eight schemes). We first performed blind-to-outcome feature selection focusing on a priori usefulness, dynamic range, and redundancy of features. Subsequently, we performed univariate and multivariate machine learning analyses to predict CAC scores from i) selected radiomic features, ii) 10 clinical features, and iii) combined radiomics + clinical features. Univariate analysis invoked Spearman correlation with Benjamini-Hotchberg false-discovery correction. The multivariate analysis incorporated stepwise linear regression, where we randomly selected a 15% test set and divided the other 85% of data into 70% training and 30% validation sets. Training started from a constant (intercept) model, iteratively adding/removing features (stepwise regression), invoking the Akaike information criterion (AIC) to discourage overfitting. Validation was run similarly, except that the training output model was used as the initial model. We randomized training/validation sets 20 times, selecting the best model using log-likelihood for evaluation in the test set. Assessment in the test set was performed thoroughly by running the entire operation 50 times, subsequently employing Fisher's method to verify the significance of independent tests.

RESULTS

Unsupervised feature selection significantly reduced 8×487 features to 56. In univariate analysis, no feature survived the false-discovery rate (FDR) to directly correlate with CAC scores. Applying Fisher's method to the multivariate regression results demonstrated combining radiomics with the clinical features to enhance the significance of the prediction model across all cardiac segments.  Conclusions: Our standardized and statistically robust multivariate analysis demonstrated significant prediction of the CAC score for all cardiac segments when combining MPSS radiomic features with clinical features, suggesting radiomics analysis can add diagnostic or prognostic value to standard MPSS for wide clinical usage.

Utility of pre-treatment 18 F-fluorodeoxyglucose PET radiomic analysis in assessing nodal involvement in cervical cancer

OBJECTIVE

Intratumor heterogeneity has prognostic value in cervical cancer, which can be depicted on 18 F-fluorodeoxyglucose ( 18 F-FDG) PET/computed tomography (PET/CT) and then quantitatively characterized by texture features. This study aimed to evaluate the discriminative performance and predictive ability of the texture features in determining lymph node involvement in cervical cancer.

METHODS

A total of 101 patients with newly diagnosed cervical cancer, who underwent pre-treatment whole-body 18 F-FDG PET/CT imaging were retrospectively recruited. Patients were categorized based on their nodal status. Thirty-five radiomic features together with the maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of the primary cervical tumors were extracted. Conventional indices were used to build logistic regression model and texture features were used to build random forest model. The performances for differentiating nodal status were assessed by receiver operating characteristic analysis.

RESULTS

Conventional PET indices were significantly higher in patients with nodal involvement compared to those without: SUVmax = 14.22 vs. 10.05; MTV = 57.02 vs. 28.73; TLG = 492.8 vs. 188.8 ( P  < 0.05). Nineteen radiomic features describing regional heterogeneity were significantly different between nodal involvements. Area under the curves of the models with conventional indices and PET texture features for discriminating nodal status were 0.72 and 0.76, respectively.

CONCLUSION

PET-derived radiomic features had moderate performance in discriminating nodal involvement in cervical cancer; and they did not outperform model based on conventional indices.

External validation of an 18F-FDG-PET radiomic model predicting survival after radiotherapy for oropharyngeal cancer

PURPOSE/OBJECTIVE

The purpose of the study is to externally validate published ¹⁸F-FDG-PET radiomic models for outcome prediction in patients with oropharyngeal cancer treated with chemoradiotherapy.

MATERIAL/METHODS

Outcome data and pre-radiotherapy PET images of 100 oropharyngeal cancer patients (stage IV:78) treated with concomitant chemotherapy to 66-69 Gy/30 fr were available. Tumors were segmented using a previously validated semi-automatic method; 450 radiomic features (RF) were extracted according to IBSI (Image Biomarker Standardization Initiative) guidelines. Only one model for cancer-specific survival (CSS) prediction was suitable to be independently tested, according to our criteria. This model, in addition to HPV status, SUVmean and SUVmax, included two independent meta-factors (F_i), resulting from combining selected RF clusters. In a subgroup of 66 patients with complete HPV information, the global risk score R was computed considering the original coefficients and was tested by Cox regression as predictive of CSS. Independently, only the radiomic risk score R_F derived from F_i was tested on the same subgroup to learn about the radiomics contribution to the model. The metabolic tumor volume (MTV) was also tested as a single predictor and its prediction performances were compared to the global and radiomic models. Finally, the validation of MTV and the radiomic score R_F were also tested on the entire dataset.

RESULTS

Regarding the analysis of the subgroup with HPV information, with a median follow-up of 41.6 months, seven patients died due to cancer. R was confirmed to be associated to CSS (p value = 0.05) with a C-index equal 0.75 (95% CI=0.62-0.85). The best cut-off value (equal to 0.15) showed high ability in patient stratification (p=0.01, HR=7.4, 95% CI=1.6-11.4). The 5-year CSS for R were 97% (95% CI: 93-100%) vs 74% (56-92%) for low- and high-risk groups, respectively. R_F and MTV alone were also significantly associated to CSS for the subgroup with an almost identical C-index. According to best cut-off value (R_F>0.12 and MTV>15.5cc), the 5-year CSS were 96% (95% CI: 89-100%) vs 65% (36-94%) and 97% (95% CI: 88-100%) vs 77% (58-93%) for RF and MTV, respectively. Results regarding RF and MTV were confirmed in the overall group.

CONCLUSION

A previously published PET radiomic model for CSS prediction was independently validated. Performances of the model were similar to the ones of using only the MTV, without improvement of prediction accuracy.

Impact of Aggregation Methods for Texture Features on Their Robustness Performance: Application to Nasopharyngeal 18F-FDG PET/CT

PURPOSE

This study aims to investigate the impact of aggregation methods used for the generation of texture features on their robustness of nasopharyngeal carcinoma (NPC) based on ¹⁸F-FDG PET/CT images.

METHODS

128 NPC patients were enrolled and 95 texture features were extracted for each patient including six feature families under different aggregation methods. For GLCM and GLRLM features, six aggregation methods were considered. For GLSZM, GLDZM, NGTDM and NGLDM features, three aggregation methods were considered. The robustness of the features affected by aggregation methods was assessed by the pair-wise intra-class correlation coefficient (ICC). Furthermore, the effects of discretization and partial volume correction (PVC) on the percent of ICC categories of all texture features were evaluated by overall ICC instead of the pair-wise ICC.

RESULTS

There were 12 features with excellent pair-wise ICCs varying aggregation methods, namely joint average, sum average, autocorrelation, long run emphasis, high grey level run emphasis, short run high grey level emphasis, long run high grey level emphasis, run length variance, SZM high grey level emphasis, DZM high grey level emphasis, high grey level count emphasis and dependence count percentage. For GLCM and GLRLM features, 19/25 and 14/16 features showed excellent pair-wise ICCs varying aggregation methods (averaged and merged) on the same dimensional features (2D, 2.5D or 3D). Different discretization levels and partial volume corrections lead to consistent robustness of textural features affected by aggregation methods.

CONCLUSION

Different dimensional features with the same aggregation methods showed worse robustness compared with the same dimensional features with different aggregation methods. Different discretization levels and PVC algorithms had a negligible effect on the percent of ICC categories of all texture features.

Primary tumor heterogeneity on pretreatment 18F-FDG PET/CT to predict outcome in patients with rectal cancer who underwent surgery after neoadjuvant therapy

PURPOSE

This retrospective study aimed to investigate the value of texture features of primary tumors in pretreatment ¹⁸F-FDG PET/CT in the prediction of response to treatment, progression, and overall survival in patients with rectal cancer who underwent surgery after neoadjuvant therapy(NAT).

METHODS

Patients with rectal cancer who had pretreatment ¹⁸F-FDG PET/CT, and underwent surgery after NAT were included in this study. Clinicopathologic features, date of last follow-up, progression, and death were recorded. Textural and conventional PET parameters(maximum standardized uptake value-SUVmax, metabolic tumor volume-MTV, total lesion glycolysis-TLG) were obtained from PET/CT images using LifeX program. Parameters were grouped using Youden index in ROC analysis. Factors predicting the pathological response to treatment, progression, and overall survival were determined using logistic regression and Cox regression analyses.

RESULTS

Forty-four patients (26(59%) male, 18(41%) female; 60.1±11.4 years) with rectal cancer were included in this study. The numbers of patients with responders and non-responders to NAT were 15(34.9%) and 28(65.1%), respectively. One patient' pathology report did not contain the response status to NAT. The median of follow-up duration was 29.9 months. 9(20.5%) showed disease progression, and 8(18.2%) died during the follow-up period. Difference entropy_GLCM and correlation_GLCM parameters were found as independent predictors for response to NAT. The positivity of surgical margin, intensity interquartile range_CONV and AUC-CSH_DISC texture parameters were independent predictors of progression, while normalized inverse difference_GLCM and LZLGE_GLZLM parameters were independent predictors of mortality.

CONCLUSION

The texture parameters obtained from pretreatment ¹⁸F-FDG PET/CT have presented a more robust predictive value than conventional parameters in patients with rectal cancer who underwent surgery after NAT.

CT radiomic predictors of local relapse after SBRT for lung oligometastases from colorectal cancer: a single institute pilot study

OBJECTIVES

To assess the potential of radiomic features (RFs) extracted from simulation computed tomography (CT) images in discriminating local progression (LP) after stereotactic body radiotherapy (SBRT) in the management of lung oligometastases (LOM) from colorectal cancer (CRC).

MATERIALS AND METHODS

Thirty-eight patients with 70 LOM treated with SBRT were analyzed. The largest LOM was considered as most representative for each patient and was manually delineated by two blinded radiation oncologists. In all, 141 RFs were extracted from both contours according to IBSI (International Biomarker Standardization Initiative) recommendations. Based on the agreement between the two observers, 134/141 RFs were found to be robust against delineation (intraclass correlation coefficient [ICC] > 0.80); independent RFs were then assessed by Spearman correlation coefficients. The association between RFs and LP was assessed with Mann-Whitney test and univariate logistic regression (ULR): the discriminative power of the most informative RF was quantified by receiver-operating characteristics (ROC) analysis through area under curve (AUC).

RESULTS

In all, 15/38 patients presented LP. Median time to progression was 14.6 months (range 2.4-66 months); 5/141 RFs were significantly associated to LP at ULR analysis (p < 0.05); among them, 4 RFs were selected as robust and independent: Statistical_Variance (AUC = 0.75, p = 0.002), Statistical_Range (AUC = 0.72, p = 0.013), Grey Level Size Zone Matrix (GLSZM) _zoneSizeNonUniformity (AUC = 0.70, p = 0.022), Grey Level Dependence Zone Matrix (GLDZM) _zoneDistanceEntropy (AUC = 0.70, p = 0.026). Importantly, the RF with the best performance (Statisical_Variance) is simply representative of density heterogeneity within LOM.

CONCLUSION

Four RFs extracted from planning CT were significantly associated with LP of LOM from CRC treated with SBRT. Results encourage further research on a larger population aiming to define a usable radiomic score combining the most predictive RFs and, possibly, additional clinical features.

Asphericity of tumor [123 I]mIBG uptake as a prognostic factor in high-risk neuroblastoma

BACKGROUND

In recent years, many research groups have attempted to identify a subgroup of "ultra-high risk" patients within the high-risk neuroblastoma (NB) category. The aim of our study was to evaluate the prognostic significance of parameters derived from pretherapeutic ¹²³ I-meta-iodobenzylguanidine ([¹²³ I]mIBG) integrated single photon emission computed tomography and computed tomography in high-risk patients with NB.

METHODS

The established parameters metabolic tumor volume (MTV), maximal standardized uptake value (SUV_max ) and the novel parameter tumor asphericity as well as clinical (age, stage) and genetic factors (1p/11q deletions and MYCN amplification) were analyzed in this single-center retrospective study of high-risk patients with newly diagnosed NB. Univariate/multivariable Cox regression and propensity score matching were performed for clinical and radiological parameters.

RESULTS

Twenty-eight high-risk patients with NB were included (14 males, median age 28.8 (11.3-41.0), range 3-74 months). Multivariable analysis of "full" cohort identified high asphericity (≥65%, adjusted hazard ratio [HR] 5.32, 95% confidence interval [CI]: 1.18-24.07, p = .03) and MTV (≥50 ml, adjusted HR 4.31, 95% CI: 1.18-15.80, p = .027) as the only factors associated with worse event-free survival. In matched cohort, tumor asphericity was a significant predictor of relapse/progression (HR 3.83, 95% CI: 1.03-14.26, p = .046).

CONCLUSION

In this exploratory study, imaging parameters related to tumor metabolic activity, tumor asphericity and MTV, provided prognostic value for event-free survival in high-risk NB patients. Asphericity ≥65% and MTV ≥50 ml may serve as additional prognostic factors to those already used.

Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs

BACKGROUND

As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low-dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics' reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect.

PURPOSE

In this article, we investigate the possibility of denoising low-dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets.

METHODS AND MATERIALS

Two cycle GANs were trained: (1) from paired data, by simulating low-dose CTs (i.e., introducing noise) from high-dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice-paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low-dose CT images and (2) same-day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder-decoder network (EDN) trained on simulated paired data.

RESULTS

The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]).

CONCLUSION

The results show that cycle GANs trained on both simulated and real data can improve radiomics' reproducibility and performance in low-dose CT and achieve similar results compared to CGANs and EDNs.

Radiomic study on preoperative multi-modal magnetic resonance images identifies IDH-mutant TERT promoter-mutant gliomas

OBJECTIVES

Gliomas with comutations of isocitrate dehydrogenase (IDH) genes and telomerase reverse transcriptase (TERT) gene promoter (IDHmut pTERTmut) show distinct biological features and respond to first-line treatment differently in comparison with other gliomas. This study aimed to characterize the IDHmut pTERTmut gliomas in multimodal MRI using the radiomic method and establish a precise diagnostic model identifying this group of gliomas.

METHODS

A total of 140 patients with untreated primary gliomas were admitted between 2016 and 2020 to West China Hospital as a discovery cohort, including 22 IDHmut pTERTmut patients. Thirty-four additional cases from a different hospital were included in the study as an independent validation cohort. A total of 3654 radiomic features were extracted from the preoperative multimodal MRI images (T1c, FLAIR, and ADC maps) and filtered in a data-driven approach. The discovery cohort was split into training and test sets by a 4:1 ratio. A diagnostic model (multilayer perceptron classifier) for detecting the IDHmut pTERTmut gliomas was trained using an automatic machine-learning algorithm named tree-based pipeline optimization tool (TPOT). The most critical radiomic features in the model were identified and visualized.

RESULTS

The model achieved an area under the receiver-operating curve (AUROC) of 0.971 (95% CI, 0.902-1.000), the sensitivity of 0.833 (95% CI, 0.333-1.000), and the specificity of 0.966 (95% CI, 0.931-1.000) in the test set. The area under the precision-recall curve (AUCPR) was 0.754 (95% CI, 0.572-0.833) and the F1 score was 0.833 (95% CI, 0.500-1.000). In the independent validation set, the model reached 0.952 AUROC, 0.714 sensitivity, 0.963 specificity, 0.841 AUCPR, and 0.769 F1 score. MR radiomic features of the IDHmut pTERTmut gliomas represented homogenous low-complexity texture in three modalities.

CONCLUSIONS

An accurate diagnostic model was constructed for detecting IDHmut pTERTmut gliomas using multimodal radiomic features. The most important features were associated with the homogenous simple texture of IDHmut pTERTmut gliomas in MRI images transformed using Laplacian of Gaussian and wavelet filters.

Frontiers and hotspots of 18F-FDG PET/CT radiomics: A bibliometric analysis of the published literature

Objective

To illustrate the knowledge hotspots and cutting-edge research trends of ¹⁸F-FDG PET/CT radiomics, the knowledge structure of was systematically explored and the visualization map was analyzed.

Methods

Studies related to ¹⁸F-FDG PET/CT radiomics from 2013 to 2021 were identified and selected from the Web of Science Core Collection (WoSCC) using retrieval formula based on an interview. Bibliometric methods are mainly performed by CiteSpace 5.8.R3, which we use to build knowledge structures including publications, collaborative and co-cited studies, burst analysis, and so on. The performance and relevance of countries, institutions, authors, and journals were measured by knowledge maps. The research foci were analyzed through research of keywords, as well as literature co-citation analysis. Predicting trends of ¹⁸F-FDG PET/CT radiomics in this field utilizes a citation burst detection method.

Results

Through a systematic literature search, 457 articles, which were mainly published in the United States (120 articles) and China (83 articles), were finally included in this study for analysis. Memorial Sloan-Kettering Cancer Center and Southern Medical University are the most productive institutions, both with a frequency of 17. ¹⁸F-FDG PET/CT radiomics–related literature was frequently published with high citation in European Journal of Nuclear Medicine and Molecular Imaging (IF9.236, 2020), Frontiers in Oncology (IF6.244, 2020), and Cancers (IF6.639, 2020). Further cluster profile of keywords and literature revealed that the research hotspots were primarily concentrated in the fields of image, textural feature, and positron emission tomography, and the hot research disease is a malignant tumor. Document co-citation analysis suggested that many scholars have a co-citation relationship in studies related to imaging biomarkers, texture analysis, and immunotherapy simultaneously. Burst detection suggests that adenocarcinoma studies are frontiers in ¹⁸F-FDG PET/CT radiomics, and the landmark literature put emphasis on the reproducibility of ¹⁸F-FDG PET/CT radiomics features.

Conclusion

First, this bibliometric study provides a new perspective on ¹⁸F-FDG PET/CT radiomics research, especially for clinicians and researchers providing scientific quantitative analysis to measure the performance and correlation of countries, institutions, authors, and journals. Above all, there will be a continuing growth in the number of publications and citations in the field of ¹⁸F-FDG PET/CT. Second, the international research frontiers lie in applying ¹⁸F-FDG PET/CT radiomics to oncology research. Furthermore, new insights for researchers in future studies will be adenocarcinoma-related analyses. Moreover, our findings also offer suggestions for scholars to give attention to maintaining the reproducibility of ¹⁸F-FDG PET/CT radiomics features.

Radiomics software comparison using digital phantom and patient data: IBSI-compliance does not guarantee concordance of feature values

Introduction Radiomics is a promising imaging-based tool which could enhance clinical observation and identify representative features. To avoid different interpretations, the Image Biomarker Standardisation Initiative (IBSI) imposed conditions for harmonisation. This study evaluates IBSI-compliant radiomics applications against a known benchmark and clinical datasets for agreements. Materials and methods The applications compared were RadiomiX Research Toolbox, LIFEx v7.0.0, and syngo.via Frontier Radiomics v1.2.5 (based on PyRadiomics v2.1). Basic assessment included comparing feature names and their formulas. The IBSI digital phantom was used for evaluation against reference values. For agreement evaluation (including same software but different versions), two clinical datasets were used: 27 contrast-enhanced computed tomography (CECT) of colorectal liver metastases and 39 magnetic resonance imaging (MRI) of breast cancer, including intravoxel incoherent motion and dynamic contrast-enhanced (DCE) MRI. The lower 95% confidence interval of intraclass correlation coefficient was used to define excellent agreement (>0.9). Results The three radiomics applications share 41 (3 shape, 8 intensity, 30 texture) out of 172, 84 and 110 features for RadiomiX, LIFEx and syngo.via, respectively, as well as wavelet filtering. The naming convention is, however, different between them. Syngo.via had excellent agreement with the IBSI benchmark, while LIFEx and RadiomiX showed slightly worse agreement. Excellent reproducibility was achieved for shape features only, while intensity and texture features varied considerably with the imaging type. For intensity, excellent agreement ranged from 46% for the DCE maps to 100% for CECT, while this lowered to 44% and 73% for texture features, respectively. Wavelet features produced the greatest variation between applications, with an excellent agreement for only 3% to 11% features. Conclusion Even with IBSI-compliance, the reproducibility of features between radiomics applications is not guaranteed. To evaluate variation, quality assurance of radiomics applications should be performed and repeated when updating to a new version or adding a new modality.

Impact of image quality on radiomics applications

Radiomics features extracted from medical images have been widely reported to be useful in the patient specific outcome modeling for variety of assessment and prediction purposes. Successful application of radiomics features as imaging biomarkers, however, is dependent on the robustness of the approach to the variation in each step of the modeling workflow. Variation in the input image quality is one of the main sources that impacts the reproducibility of radiomics analysis when a model is applied to broader range of medical imaging data. The quality of medical image is generally affected by both the scanner related factors such as image acquisition/reconstruction settings and the patient related factors such as patient motion. This article aimed to review the published literatures in this field that reported the impact of various imaging factors on the radiomics features through the change in image quality. The literatures were categorized by different imaging modalities and also tabulated based on the imaging parameters and the class of radiomics features included in the study. Strategies for image quality standardization were discussed based on the relevant literatures and recommendations for reducing the impact of image quality variation on the radiomics in multi-institutional clinical trial were summarized at the end of this article.

Impact of Interfractional Error on Dosiomic Features

Objectives

The purpose of this study was to investigate the stability of dosiomic features under random interfractional error. We investigated the differences in the values of features with different fractions and the error in the values of dosiomic features under interfractional error.

Material and Methods

The isocenters of the treatment plans of 15 lung cancer patients were translated by a maximum of ±3 mm in each axis with a mean of (0, 0, 0) and a standard deviation of (1.2, 1.2, 1.2) mm in the x, y, and z directions for each fraction. A total of 81 dose distributions for each patient were then calculated considering four fraction number groups (2, 10, 20, and 30). A total of 93 dosiomic features were extracted from each dose distribution in four different regions of interest (ROIs): gross tumor volume (GTV), planning target volume (PTV), heart, and both lungs. The stability of dosiomic features was analyzed for each fraction number group by the coefficient of variation (CV) and intraclass correlation coefficient (ICC). The agreements in the means of dosiomic features among the four fraction number groups were tested by ICC. The percent differences (PD) between the dosiomic features extracted from the original dose distribution and the dosiomic features extracted from the dose distribution with interfractional error were calculated.

Results

Eleven out of 93 dosiomic features demonstrated a large CV (CV ≥ 20%). Overall CV values were highest in GTV ROIs and lowest in lung ROIs. The stability of dosiomic features decreased as the total number of fractions decreased. The ICC results showed that five out of 93 dosiomic features had an ICC lower than 0.75, which indicates intermediate or poor stability under interfractional error. The mean dosiomic feature values were shown to be consistent with different numbers of fractions (ICC ≥ 0.9). Some of the dosiomic features had PD greater than 50% and showed different PD values with different numbers of fractions.

Conclusion

Some dosiomic features have low stability under interfractional error. The stability and values of the dosiomic features were affected by the total number of fractions. The effect of interfractional error on dosiomic features should be considered in further studies regarding dosiomics for reproducible results.

Generative models improve radiomics performance in different tasks and different datasets: An experimental study

PURPOSE

Radiomics is an active area of research focusing on high throughput feature extraction from medical images with a wide array of applications in clinical practice, such as clinical decision support in oncology. However, noise in low dose computed tomography (CT) scans can impair the accurate extraction of radiomic features. In this article, we investigate the possibility of using deep learning generative models to improve the performance of radiomics from low dose CTs.

METHODS

We used two datasets of low dose CT scans - NSCLC Radiogenomics and LIDC-IDRI - as test datasets for two tasks - pre-treatment survival prediction and lung cancer diagnosis. We used encoder-decoder networks and conditional generative adversarial networks (CGANs) trained in a previous study as generative models to transform low dose CT images into full dose CT images. Radiomic features extracted from the original and improved CT scans were used to build two classifiers - a support vector machine (SVM) and a deep attention based multiple instance learning model - for survival prediction and lung cancer diagnosis respectively. Finally, we compared the performance of the models derived from the original and improved CT scans.

RESULTS

Denoising with the encoder-decoder network and the CGAN improved the area under the curve (AUC) of survival prediction from 0.52 to 0.57 (p-value < 0.01). On the other hand, the encoder-decoder network and the CGAN improved the AUC of lung cancer diagnosis from 0.84 to 0.88 and 0.89 respectively (p-value < 0.01). Finally, there are no statistically significant improvements in AUC using encoder-decoder networks and CGAN (p-value = 0.34) when networks trained at 75 and 100 epochs.

CONCLUSION

Generative models can improve the performance of low dose CT-based radiomics in different tasks. Hence, denoising using generative models seems to be a necessary pre-processing step for calculating radiomic features from low dose CTs.

Radiomics in Triple Negative Breast Cancer: New Horizons in an Aggressive Subtype of the Disease

In the last decade, the analysis of the medical images has evolved significantly, applications and tools capable to extract quantitative characteristics of the images beyond the discrimination capacity of the investigator's eye being developed. The applications of this new research field, called radiomics, presented an exponential growth with direct implications in the diagnosis and prediction of response to therapy. Triple negative breast cancer (TNBC) is an aggressive breast cancer subtype with a severe prognosis, despite the aggressive multimodal treatments applied according to the guidelines. Radiomics has already proven the ability to differentiate TNBC from fibroadenoma. Radiomics features extracted from digital mammography may also distinguish between TNBC and non-TNBC. Recent research has identified three distinct subtypes of TNBC using IRM breast images voxel-level radiomics features (size/shape related features, texture features, sharpness). The correlation of these TNBC subtypes with the clinical response to neoadjuvant therapy may lead to the identification of biomarkers in order to guide the clinical decision. Furthermore, the variation of some radiomics features in the neoadjuvant settings provides a tool for the rapid evaluation of treatment efficacy. The association of radiomics features with already identified biomarkers can generate complex predictive and prognostic models. Standardization of image acquisition and also of radiomics feature extraction is required to validate this method in clinical practice.

Risk analysis in peripheral clinical T1 non-small cell lung cancer correlations between tumor-to-blood standardized uptake ratio on 18F-FDG PET-CT and primary tumor pathological invasiveness: a real-world observational study

BACKGROUND

Sublobar resection is not suitable for patients with pathological invasiveness [including lymph node metastasis (LNM), visceral pleural invasion (VPI), and lymphovascular invasion (LVI)] of peripheral clinical T1 (cT1) non-small cell lung cancer (NSCLC), while primary tumor maximum standardized uptake value (SUV_max) on ¹⁸F-FDG PET-CT is related to pathological invasiveness, the significance differed among different institutions is still challenging. This study explored the relationship between the tumor-to-blood standardized uptake ratio (SUR) of ¹⁸F-FDG PET-CT and primary tumor pathological invasiveness in peripheral cT1 NSCLC patients.

METHODS

This retrospective study included 174 patients with suspected lung neoplasms who underwent preoperative ¹⁸F-FDG PET-CT. We compared the differences of the clinicopathological variables, metabolic and morphological parameters in the pathological invasiveness and less-invasiveness group. We performed a trend test for these parameters based on the tertiles of SUR. The relationship between SUR and pathological invasiveness was evaluated by univariate and multivariate logistics regression models (included unadjusted, simple adjusted, and fully adjusted models), odds ratios (ORs), and 95% confidence intervals (95% CIs) were calculated. A smooth fitting curve between SUR and pathological invasiveness was produced by the generalized additive model (GAM).

RESULTS

Thirty-eight point five percent of patients had pathological invasiveness and tended to have a higher SUR value than the less-invasiveness group [6.50 (4.82-11.16) vs. 4.12 (2.04-6.61), P<0.001]. The trend of SUV_max, mean standardized uptake value (SUV_mean), metabolic tumor volume (MTV), total lesion glycolysis (TLG), mean CT value (CT_mean), size of the primary tumor, neuron-specific enolase (NSE), the incidence of LNM, adenocarcinoma (AC), and poor differentiation in the tertiles of SUR value were statistically significant (P were <0.001, <0.001, 0.010, <0.001, <0.001, 0.002, 0.033, <0.001, 0.002, and <0.001, respectively). Univariate analysis showed that the risk of pathological invasiveness increased significantly with increasing SUR [OR: 1.13 (95% CI: 1.06-1.21), P<0.001], and multivariate analysis demonstrated SUR, as a continuous variable, was still significantly related to pathological invasiveness [OR: 1.09 (95% CI: 1.01-1.18), P=0.032] after adjusting for confounding covariates. GAM revealed that SUR tended to be linearly and positively associated with pathological invasiveness and E-value analysis suggested robustness to unmeasured confounding.

CONCLUSIONS

SUR is linearly and positively associated with primary tumor pathological invasiveness independent of confounding covariates in peripheral cT1 NSCLC patients and could be used as a supplementary risk maker to assess the risk of pathological invasiveness.

Relationship between total lesion glycolysis of primary lesions based on 18F-FDG PET/CT and lymph node metastasis in gastric adenocarcinoma: a cross-sectional preliminary study

OBJECTIVES

We explored the relationship between lymph node metastasis (LNM) and total lesion glycolysis (TLG) of primary lesions determined by 18fluoro-2-deoxyglucose PET/computed tomography (18F-FDG PET/CT) in patients with gastric adenocarcinoma, and evaluated the independent effect of this association.

METHODS

This retrospective study included 106 gastric adenocarcinoma patients who were examined by preoperative 18F-FDG PET/CT imaging between April 2016 and April 2020. We measured TLG of primary gastric lesions and evaluated its association with LNM. Multivariate logistic regression and a two-piece-wise linear regression were performed to evaluate the relationship between TLG of primary lesions and LNM.

RESULTS

Of the 106 patients, 75 cases (71%) had LNM and 31 cases (29%) did not have LNM. Univariate analyses revealed that a per-SD increase in TLG was independently associated with LNM [odds ratio (OR) = 2.37; 95% confidence interval (CI), 1.42-3.98; P = 0.0010]. After full adjustment of confounding factors, multivariate analyses exhibited that TLG of primary lesions was still significantly associated with LNM (OR per-SD: 2.20; 95% CI, 1.16-4.19; P = 0.0164). Generalized additive model indicated a nonlinear relationship and saturation effect between TLG of primary lesions and LNM. When TLG of primary lesions was <23.2, TLG was significantly correlated with LNM (OR = 1.26; 95% CI, 1.07-1.48; P = 0.0053), whereas when TLG of primary lesions was ≥ 23.2, the probability of LNM was greater than 60%, gradually reached saturation effect, as high as 80% or more.

CONCLUSIONS

In this preliminary study, there were saturation and segmentation effects between TLG of primary lesions determined by preoperative 18F-FDG PET/CT and LNM. When TLG of primary lesions was ≥ 23.2, the probability of LNM was greater than 60%, gradually reached saturation effect, as high as 80% or more. TLG of primary lesions is helpful in the preoperative diagnosis of LNM in patients with gastric adenocarcinoma.

Preoperative 18F-FDG SUVmax >6.3 or Size >2.3 cm of primary lesions predict lymph nodes metastasis with higher negative predictive value in peripheral cT1 non-small-cell lung cancer

BACKGROUND

Sublobar resection is suitable for peripheral cT1N0M0 non-small-cell lung cancer (NSCLC). The traditional PET-CT criterion (lymph node size ≥1.0 cm or SUVmax ≥2.5) for predicting lymph nodes metastasis (LNM) has unsatisfactory performance.

OBJECTIVE

We explore the clinical role of preoperative SUVmax and the size of the primary lesions for predicting peripheral cT1 NSCLC LNM.

METHODS

We retrospectively analyzed 174 peripheral cT1 NSCLC patients underwent preoperative 18F-FDG PET-CT and divided into the LNM and non-LNM group by pathology. We compared the differences of primary lesions' baseline characteristics between the two groups. The risk factors of LNM were determined by univariate and multivariate analysis, and we assessed the diagnostic efficacy with the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value (NPV).

RESULTS

Of the enrolled cases, the incidence of LNM was 24.7%. The preoperative SUVmax >6.3 or size >2.3 cm of the primary lesions were independent risk factors of peripheral cT1 NSCLC LNM (ORs, 95% CIs were 6.18 (2.40-15.92) and 3.03 (1.35-6.81). The sensitivity, NPV of SUVmax >6.3 or size >2.3 cm of the primary lesions were higher than the traditional PET-CT criterion for predicting LNM (100.0 vs. 86.0%, 100.0 vs. 89.7%). A Hosmer-Lemeshow test showed a goodness-of-fit (P = 0.479).

CONCLUSIONS

The excellent sensitivity and NPV of preoperative of the SUVmax >6.3 or size >2.3 cm of the primary lesions based on 18F-FDG PET-CT might identify the patients at low-risk LNM in peripheral cT1 NSCLC.

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

Radiomics holds great promise in the field of cancer management. However, the clinical application of radiomics has been hampered by uncertainty about the robustness of the features extracted from the images. Previous studies have reported that radiomics features are sensitive to changes in voxel size resampling and interpolation, image perturbation, or slice thickness. This study aims to observe the variability of positron emission tomography (PET) radiomics features under the impact of co-registration with magnetic resonance imaging (MRI) using the difference percentage coefficient, and the Spearman’s correlation coefficient for three groups of images: (i) original PET, (ii) PET after co-registration with T1-weighted MRI and (iii) PET after co-registration with FLAIR MRI. Specifically, seventeen patients with brain cancers undergoing [11C]-Methionine PET were considered. Successively, PET images were co-registered with MRI sequences and 107 features were extracted for each mentioned group of images. The variability analysis revealed that shape features, first-order features and two subgroups of higher-order features possessed a good robustness, unlike the remaining groups of features, which showed large differences in the difference percentage coefficient. Furthermore, using the Spearman’s correlation coefficient, approximately 40% of the selected features differed from the three mentioned groups of images. This is an important consideration for users conducting radiomics studies with image co-registration constraints to avoid errors in cancer diagnosis, prognosis, and clinical outcome prediction.

Prognostication Based on Texture Analysis of Baseline 18F Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in Nonsmall-Cell Lung Carcinoma Patients Who Underwent Platinum-Based Chemotherapy as First-Line Treatment

Objective:

Our study aims to establish the potential for tumor heterogeneity evaluated using ¹⁸F fluorodeoxyglucose positron emission tomography/computed tomography (F-18 FDG PET/CT) texture analysis in nonsmall-cell lung carcinoma (NSCLC) patients who underwent platinum-based chemotherapy to provide an independent marker for overall survival (OS) of more than 1-year.

Materials and Methods:

A total of 42 patients (34 male and 8 female) with biopsy-proven NSCLC and mean age 55.33 ± 10.71 years who underwent a baseline F-18 FDG PET/CT and received platinum-based chemotherapy as first-line treatment were retrospectively included in the study. Ten first order, 21 s order texture parameters and 7 SUV and metabolic tumor volume (MTV) based metabolic parameters were calculated. All these parameters were compared between the two survival groups based on OS ≥1 year and OS <1 year. Cut-offs of significant parameters were determined using receiver operating characteristic curve analysis. Survival patterns were compared by log-rank test and presented using Kaplan-Meier curves. Cox proportion hazard model was used to determine the independent prognostic marker for 1 year OS.

Results:

In univariate survival analysis, 3 first order texture parameters (i.e. mean, median, root mean square with hazard ratios [HRs] 2.509 [P = 0.034], 2.590 [P = 0.05], 2.509 [P = 0.034], respectively) and 6 s order texture parameters (i.e. mean, auto correlation, cluster prominence, cluster shade, sum average and sum variance with HRs 2.509 [P = 0.034], 2.509 [P = 0.034], 3.929 [0.007], 2.903 [0.018], 2.954 [0.016] and 2.906 [0.014], respectively) were significantly associated with 1 year OS in these patients. Among the metabolic parameters, only metabolic tumor volume whole-body was significantly associated with 1 year OS. In multivariate survival analysis, cluster prominence came out as the independent predictor of 1 year OS.

Conclusion:

Texture analysis based on F-18 FDG PET/CT is potentially beneficial in the prediction of OS ≥1 year in NSCLC patients undergoing platinum-based chemotherapy as first-line treatment. Thus, can be used to stratify the patients which will not be benefitted with platinum-based chemotherapy and essentially needs to undergo some other therapy option.

Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review

Radiomics research is rapidly growing in recent years, but more concerns on radiomics reliability are also raised. This review attempts to update and overview the current status of radiomics reliability research in the ever expanding medical literature from the perspective of a single reliability metric of intraclass correlation coefficient (ICC). To conduct this systematic review, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. After literature search and selection, a total of 481 radiomics studies using CT, PET, or MRI, covering a wide range of subject and disease types, were included for review. In these highly heterogeneous studies, feature reliability to image segmentation was much more investigated than reliability to other factors, such as image acquisition, reconstruction, post-processing, and feature quantification. The reported ICCs also suggested high radiomics feature reliability to image segmentation. Image acquisition was found to introduce much more feature variability than image segmentation, in particular for MRI, based on the reported ICC values. Image post-processing and feature quantification yielded different levels of radiomics reliability and might be used to mitigate image acquisition-induced variability. Some common flaws and pitfalls in ICC use were identified, and suggestions on better ICC use were given. Due to the extremely high study heterogeneities and possible risks of bias, the degree of radiomics feature reliability that has been achieved could not yet be safely synthesized or derived in this review. More future researches on radiomics reliability are warranted.

Fluorine-18 fluorodeoxyglucose positron emission tomography-based textural features for prediction of event prone carotid atherosclerotic plaques

BACKGROUND

Texture analysis has been increasingly used in the field of positron emission tomography (PET)/computed tomography (CT) imaging with Fluorine-18 fluorodeoxyglucose (18F-FDG), aiming at assessing tumor heterogeneity. The purpose of the present study is to examine the feasibility of performing texture analysis in carotid arteries, investigate the value of textural features as predictors of potential plaque vulnerability using as reference standards histological and immunohistochemical data and compare their performance with conventional uptake measurements.

METHODS

67 different 18F-FDG PET-based textural features were extracted from carotid images of 21 patients with high-grade carotid stenosis undergoing endarterectomy. To identify the more reliable predictors, univariate logistic regression analysis was performed. The accuracy was satisfactory in case of an Area Under the Receiver Operating Characteristic (ROC) curve (AUC) ≥ 0.80.

RESULTS

First measure of information correlation (AUC = 0.87, P < 0.001), large zone low gray level emphasis (AUC = 0.87, P < 0.001), and normalized run length non-uniformity (AUC = 0.84, P < 0.001) were the most optimal textural features for identifying characteristics of plaque vulnerability based on histological analysis. Addition of textural features to target-to-background ratio (TBR) (AUC = 0.74, P = 0.031) resulted in an AUC = 0.92 (P < 0.001), however, this did not reach statistical significance (Pdiff = 0.09). Intensity histogram standard deviation (AUC = 0.87, P < 0.001) and joint variance (AUC = 0.81, P = 0.001) were the most efficient features for signal differential in relation to immunohistochemical findings and provided incremental value compared to TBR (Pdiff = 0.02).

CONCLUSION

Texture analysis can be applied in 18F-FDG PET carotid imaging providing valuable information for plaque characterization.

Variation in textural parameters of hepatic lesions during contrast medium injection

BACKGROUND

Textural parameters extracted using quantitative imaging techniques have been shown to have prognostic value for hepatocellular carcinoma (HCC).

PURPOSE

To evaluate whether the contrast medium timing of the image acquisition affects the reproducibility of textural parameters in HCC and hepatic tissue.

MATERIAL AND METHODS

This retrospective study included 17 patients with 37 HCC lesions. Perfusion computed tomography (CT) was obtained after 50 mL contrast medium injection. HCC lesions were segmented for analysis. The gray-level co-occurrence (GLCM) textural analysis parameters, homogeneity, energy, entropy, inertia, and correlation were calculated. Variation was quantified by calculating the SD of each parameter during respective perfusion series and the inter lesion variation as the SD among the lesions.

RESULTS

The average change in texture parameters in both HCC and hepatic tissue per second after injection was 0.01% to 0.3% of the respective texture parameter. In HCC, the average variation in homogeneity, energy, and entropy within each lesion after contrast medium injection was significantly less than the variation observed among the lesions (23% to 74%, P < 0.001). Significant differences in energy, entropy, inertia, and correlation between hepatic tissue and HCC were observed. However, when considering the intra-individual variation of hepatic tissue over time, only the HCC parameter energy was significantly outside that 95% confidence interval (P < 0.02).

CONCLUSION

The contrast medium timing does not affect the reproducibility of textural parameters in HCC and hepatic tissue. Thus, contrast medium timing should not be an issue at CT texture analysis of HCC.

Radiomics and Digital Image Texture Analysis in Oncology (Review)

One of the most promising areas of diagnosis and prognosis of diseases is radiomics, a science combining radiology, mathematical modeling, and deep machine learning. The main concept of radiomics is image biomarkers (IBMs), the parameters characterizing various pathological changes and calculated based on the analysis of digital image texture. IBMs are used for quantitative assessment of digital imaging results (CT, MRI, ultrasound, PET). The use of IBMs in the form of “virtual biopsy” is of particular relevance in oncology.

The article provides the basic concepts of radiomics identifying the main stages of obtaining IBMs: data collection and preprocessing, tumor segmentation, data detection and extraction, modeling, statistical processing, and data validation. The authors have analyzed the possibilities of using IBMs in oncology, describing the currently known features and advantages of using radiomics and image texture analysis in the diagnosis and prognosis of cancer. The limitations and problems associated with the use of radiomics data are considered.

Although the novel effective tool for performing virtual biopsy of human tissue is at the development stage, quite a few projects have already been implemented, and medical software packages for radiomics analysis of digital images have been created.

Heterogeneity by global and textural feature analysis in F-18 FP-CIT brain PET images for diagnosis of Parkinson's disease

BACKGROUND

The quantification of heterogeneity for the striatum and whole brain with F-18 FP-CIT PET images will be useful for diagnosis. The index obtained from texture analysis on PET images is related to pathological change that the neuronal loss of the nigrostriatal tract is heterogeneous according to the disease state. The aim of this study is to evaluate various heterogeneity indices of F-18 FP-CIT PET images in the diagnosis of Parkinson's disease (PD) patients and to access the diagnostic accuracy of the indices using machine learning (ML).

METHODS

This retrospective study included F-18 FP-CIT PET images of 31 PD and 31 age-matched health controls (HC). The volume of interest was delineated according to iso-contour lines around standardized uptake value (SUV) 3.0 g/ml for each region of the striatum by PMod 3.603. One hundred eight heterogeneity indices were calculated using CGITA to find indices from which the PD and HC were classified using statistical significance. PD group was classified by constructing a 2-dimensional or 3-dimensional phase space quantifier using these heterogeneity indices. We used 71 heterogeneity indices to classify PD from HC using ML for dimensional reduction.

RESULTS

The heterogeneity indices for classifying PD from HC were size-zone variability, contrast, inverse difference-moment, and homogeneity in the order of low P value. Three-dimensional quantifiers composed of normalized-contrast, code-similarity, and contrast were more clearly classified than 2-dimensional ones. After 71-dimensional reduction using PCA, classification was possible by logistic regression with 91.3% accuracy. The 2 groups were classified with an accuracy of 85.5% using the support vector machine and 88.4% using the random forest. The classification accuracy using the eXtreme Gradient Boosting was 95.7%, and feature importance was highest in order of SUV bias-corrected kurtosis, size-zone-variability, intensity-variability, and high-intensity-zone-variability.

CONCLUSION

It was confirmed that PD patients is more clearly classified than the conventional 2-dimensional quantifier by introducing a 3-dimensional phase space quantifier. We observed that ML can be used to classify the 2 groups in an easy and explanatory manner. For the discrimination of the disease, 24 heterogeneity indices were found to be statistically useful, and the major cut-off values of 3 heterogeneity indices were size-zone variability (1906.44), intensity variability (129.21), and high intensity zone emphasis (800.29).

Texture analysis of dorsal striatum in functional neurological (conversion) disorder

In this study, it was aimed to evaluate the dorsal striatum nuclei of patients diagnosed with Functional Neurological Disorder by texture analysis method from magnetic resonance imaging images and to compare them with healthy controls. Study groups consisted of 20 female patients and 20 healthy women. The brains of patients and controls were scanned for high-resolution images with a 1.5T scanner using the sagittal plane and 3D spiral fast spin echo sequence. Using the texture analysis method, mean, standard deviation, minimum, maximum, median, variance, entropy, size %L, size %U, size %M, kurtosis, skewness and homogeneity values of the dorsal striatum nuclei were calculated from the images. The data were compared with comparison tests according to Kolmogorov-Smirnov test results. There was no statistically significant difference between paired regions in terms of texture analysis findings in the cross-sectional images of the participants. In patients, mean, standard deviation, minimum, maximum, median, variance and entropy values for the putamen nucleus, and mean, standard deviation, minimum, maximum, median, variance, entropy and kurtosis values for the caudate nucleus were found significantly higher than controls. Additional receiver operating characteristic curve and logistic regression analyzes were performed. The implications of the results of the study are that there are significant microstructural changes in the dorsal striatum nuclei of patients and their reflection on brain images. Texture analysis is a useful technique to show tissue changes in the dorsal striatum of patients using images. It is highly recommended to use texture analysis to identify and evaluate potentially affected areas of the brain in new studies.

Repeatability of image features extracted from FET PET in application to post-surgical glioblastoma assessment

Positron emission tomography (PET) imaging using the amino acid tracer O-[2-(¹⁸F)fluoroethyl]-L-tyrosine (FET) has gained increased popularity within the past decade in the management of glioblastoma (GBM). Radiomics features extracted from FET PET images may be sensitive to variations when imaging at multiple time points. It is therefore necessary to assess feature robustness to test-retest imaging. Eight patients with histologically confirmed GBM that had undergone post-surgical test-retest FET PET imaging were recruited. In total, 1578 radiomic features were extracted from biological tumour volumes (BTVs) delineated using a semi-automatic contouring method. Feature repeatability was assessed using the intraclass correlation coefficient (ICC). The effect of both bin width and filter choice on feature repeatability was also investigated. 59/106 (55.7%) features from the original image and 843/1472 (57.3%) features from filtered images had an ICC ≥ 0.85. Shape and first order features were most stable. Choice of bin width showed minimal impact on features defined as stable. The Laplacian of Gaussian (LoG, σ = 5 mm) and Wavelet filters (HLL and LHL) significantly improved feature repeatability (p ≪ 0.0001, p = 0.003, p = 0.002, respectively). Correlation of textural features with tumour volume was reported for transparency. FET PET radiomic features extracted from post-surgical images of GBM patients that are robust to test-retest imaging were identified. An investigation with a larger dataset is warranted to validate the findings in this study.

Generative models improve radiomics reproducibility in low dose CTs: a simulation study

Radiomics is an active area of research in medical image analysis, however poor reproducibility of radiomics has hampered its application in clinical practice. This issue is especially prominent when radiomic features are calculated from noisy images, such as low dose computed tomography (CT) scans. In this article, we investigate the possibility of improving the reproducibility of radiomic features calculated on noisy CTs by using generative models for denoising. Our work concerns two types of generative models-encoder-decoder network (EDN) and conditional generative adversarial network (CGAN). We then compared their performance against a more traditional 'non-local means' denoising algorithm. We added noise to sinograms of full dose CTs to mimic low dose CTs with two levels of noise: low-noise CT and high-noise CT. Models were trained on high-noise CTs and used to denoise low-noise CTs without re-training. We tested the performance of our model in real data, using a dataset of same-day repeated low dose CTs in order to assess the reproducibility of radiomic features in denoised images. EDN and the CGAN achieved similar improvements on the concordance correlation coefficients (CCC) of radiomic features for low-noise images from 0.87 [95%CI, (0.833, 0.901)] to 0.92 [95%CI, (0.909, 0.935)] and for high-noise images from 0.68 [95%CI, (0.617, 0.745)] to 0.92 [95%CI, (0.909, 0.936)], respectively. The EDN and the CGAN improved the test-retest reliability of radiomic features (mean CCC increased from 0.89 [95%CI, (0.881, 0.914)] to 0.94 [95%CI, (0.927, 0.951)]) based on real low dose CTs. These results show that denoising using EDN and CGANs could be used to improve the reproducibility of radiomic features calculated from noisy CTs. Moreover, images at different noise levels can be denoised to improve the reproducibility using the above models without need for re-training, provided the noise intensity is not excessively greater that of the high-noise CTs. To the authors' knowledge, this is the first effort to improve the reproducibility of radiomic features calculated on low dose CT scans by applying generative models.

The Effect of Heterogenous Subregions in Glioblastomas on Survival Stratification: A Radiomics Analysis Using the Multimodality MRI

Intratumor heterogeneity is partly responsible for the poor prognosis of glioblastoma (GBM) patients. In this study, we aimed to assess the effect of different heterogeneous subregions of GBM on overall survival (OS) stratification. A total of 105 GBM patients were retrospectively enrolled and divided into long-term and short-term OS groups. Four MRI sequences, including contrast-enhanced T1-weighted imaging (T1C), T1, T2, and FLAIR, were collected for each patient. Then, 4 heterogeneous subregions, i.e. the region of entire abnormality (rEA), the regions of contrast-enhanced tumor (rCET), necrosis (rNec) and edema/non-contrast-enhanced tumor (rE/nCET), were manually drawn from the 4 MRI sequences. For each subregion, 50 radiomics features were extracted. The stratification performance of 4 heterogeneous subregions, as well as the performances of 4 MRI sequences, was evaluated both alone and in combination. Our results showed that rEA was superior in stratifying long-and short-term OS. For the 4 MRI sequences used in this study, the FLAIR sequence demonstrated the best performance of survival stratification based on the manual delineation of heterogeneous subregions. Our results suggest that heterogeneous subregions of GBMs contain different prognostic information, which should be considered when investigating survival stratification in patients with GBM.

Prognostic value of 18F-FDG PET/CT with texture analysis in patients with rectal cancer treated by surgery

PURPOSE

The aim of this study was to evaluate the ability of texture analysis using pretreatment 18F-FDG PET/CT to predict prognosis in patients with surgically treated rectal cancer.

METHODS

We analyzed 94 patients with pathologically proven rectal cancer who underwent pretreatment 18F-FDG PET/CT and were subsequently treated with surgery. The volume of interest of the primary tumor was defined using a threshold of 40% of the maximum standardized uptake value (SUVmax), and conventional (SUVmax, metabolic tumor volume [MTV], total lesion glycolysis [TLG]) and textural PET features were extracted. Harmonization of PET features was performed with the ComBat method. The study endpoints were overall survival (OS) and progression-free survival (PFS), and the prognostic value of PET features was evaluated by Cox regression analysis.

RESULTS

In the follow-up period (median 41.7 [interquartile range, 30.5-60.4] months), 21 (22.3%) and 30 (31.9%) patients had cancer-related death or disease progression, respectively. Univariate analysis revealed a significant association of (1) MTV, TLG, and gray-level co-occurrence matrix (GLCM) entropy with OS; and (2) SUVmax, MTV, TLG, and GLCM entropy with PFS. In multivariate analysis including clinical characteristics, GLCM entropy (≥ 2.13) was the only relevant prognostic PET feature for poor OS (hazard ratio [HR]: 4.16, p = 0.035) and PFS (HR: 2.70, p = 0.046).

CONCLUSION

GLCM entropy, which indicates metabolic intratumoral heterogeneity, was an independent prognostic factor in patients with surgically treated rectal cancer. Compared with conventional PET features, GLCM entropy has better predictive value and shows potential to facilitate precision medicine.

The role of FDG PET/CT or PET/MRI in assessing response to neoadjuvant therapy for patients with borderline or resectable pancreatic cancer: a systematic literature review

The aim of the present systematic review is to examine the role of fluorodeoxyglucose (FDG) positron emission tomography (PET) associated with computed tomography (CT) or magnetic resonance imaging (MRI) in assessing response to preoperative chemotherapy or chemoradiotherapy (CRT) for patients with borderline and resectable pancreatic ductal adenocarcinoma (PDAC). Three researchers ran a database query in PubMed, Web of Science and EMBASE. The total number of patients considered was 488. The most often used parameters of response to therapy were the reductions in the maximum standardized uptake value (SUVmax) or the peak standardized uptake lean mass (SULpeak). Patients whose SUVs were higher at the baseline (before CRT) were associated with a better response to therapy and a better overall survival. SUVs remaining high after neoadjuvant therapy correlated with a poor prognosis. Available data indicate that FDG PET/CT or PET/MRI can be useful for predicting and assessing response to CRT in patients with resectable or borderline PDAC.

Plasma Lipidomics Profiling Reveals Biomarkers for Papillary Thyroid Cancer Diagnosis

The objective of this study was to identify potential biomarkers and possible metabolic pathways of malignant and benign thyroid nodules through lipidomics study. A total of 47 papillary thyroid carcinomas (PTC) and 33 control check (CK) were enrolled. Plasma samples were collected for UPLC-Q-TOF MS system detection, and then OPLS-DA model was used to identify differential metabolites. Based on classical statistical methods and machine learning, potential biomarkers were characterized and related metabolic pathways were identified. According to the metabolic spectrum, 13 metabolites were identified between PTC group and CK group, and a total of five metabolites were obtained after further screening. Its metabolic pathways were involved in glycerophospholipid metabolism, linoleic acid metabolism, alpha-linolenic acid metabolism, glycosylphosphatidylinositol (GPI)—anchor biosynthesis, Phosphatidylinositol signaling system and the metabolism of arachidonic acid metabolism. The metabolomics method based on PROTON nuclear magnetic resonance (NMR) had great potential for distinguishing normal subjects from PTC. GlcCer(d14:1/24:1), PE-NME (18:1/18:1), SM(d16:1/24:1), SM(d18:1/15:0), and SM(d18:1/16:1) can be used as potential serum markers for the diagnosis of PTC.

Experimental phantom evaluation to identify robust positron emission tomography (PET) radiomic features

Background

Radiomics analysis usually involves, especially in multicenter and large hospital studies, different imaging protocols for acquisition, reconstruction, and processing of data. Differences in protocols can lead to differences in the quantification of the biomarker distribution, leading to radiomic feature variability. The aim of our study was to identify those radiomic features robust to the different degrading factors in positron emission tomography (PET) studies. We proposed the use of the standardized measurements of the European Association Research Ltd. (EARL) accreditation to retrospectively identify the radiomic features having low variability to the different systems and reconstruction protocols. In addition, we presented a reproducible procedure to identify PET radiomic features robust to PET/CT imaging metal artifacts. In 27 heterogeneous homemade phantoms for which ground truth was accurately defined by CT segmentation, we evaluated the segmentation accuracy and radiomic feature reliability given by the contrast-oriented algorithm (COA) and the 40% threshold PET segmentation. In the comparison of two data sets, robustness was defined by Wilcoxon rank tests, bias was quantified by Bland–Altman (BA) plot analysis, and strong correlations were identified by Spearman correlation test (r > 0.8 and p satisfied multiple test Bonferroni correction).

Results

Forty-eight radiomic features were robust to system, 22 to resolution, 102 to metal artifacts, and 42 to different PET segmentation tools. Overall, only 4 radiomic features were simultaneously robust to all degrading factors. Although both segmentation approaches significantly underestimated the volume with respect to the ground truth, with relative deviations of −62 ± 36% for COA and −50 ± 44% for 40%, radiomic features derived from the ground truth were strongly correlated and/or robust to 98 radiomic features derived from COA and to 102 from 40%.

Conclusion

In multicenter studies, we recommend the analysis of EARL accreditation measurements in order to retrospectively identify the robust PET radiomic features. Furthermore, 4 radiomic features (area under the curve of the cumulative SUV volume histogram, skewness, kurtosis, and gray-level variance derived from GLRLM after application of an equal probability quantization algorithm on the voxels within lesion) were robust to all degrading factors. In addition, the feasibility of 40% and COA segmentations for their use in radiomics analysis has been demonstrated.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40658-021-00390-7.

Potential and limitations of radiomics in neuro-oncology

Radiomics seeks to apply classical methods of image processing to obtain quantitative parameters from imaging. Derived features are subsequently fed into algorithmic models to aid clinical decision making. The application of radiomics and machine learning techniques to clinical medicine remains in its infancy. The great potential of radiomics lies in its objective, granular approach to investigating clinical imaging. In neuro-oncology, advanced machine learning techniques, particularly deep learning, are at the forefront of new discoveries in the field. However, despite the great promise of machine learning aided radiomic approaches, the current use remains confined to scholarly research, without real-world deployment in neuro-oncology. The paucity of data, inconsistencies in preprocessing, radiomic feature instability, and the rarity of the events of interest are critical barriers to clinical translation. In this article, we will outline the major steps in the process of radiomics, as well as review advances and challenges in the field as they pertain to neuro-oncology.

Repeatability of 18F-FDG PET Radiomic Features in Cervical Cancer

Knowledge of the intrinsic variability of radiomic features is essential to the proper interpretation of changes in these features over time. The primary aim of this study was to assess the test-retest repeatability of radiomic features extracted from 18F-FDG PET images of cervical tumors. The impact of different image preprocessing methods was also explored. Methods: Patients with cervical cancer underwent baseline and repeat 18F-FDG PET/CT imaging within 7 d. PET images were reconstructed using 2 methods: ordered-subset expectation maximization (PETOSEM) or ordered-subset expectation maximization with point-spread function (PETPSF). Tumors were segmented to produce whole-tumor volumes of interest (VOIWT) and 40% isocontours (VOI40). Voxels were either left at the default size or resampled to 3-mm isotropic voxels. SUV was discretized to a fixed number of bins (32, 64, or 128). Radiomic features were extracted from both VOIs, and repeatability was then assessed using the Lin concordance correlation coefficient (CCC). Results: Eleven patients were enrolled and completed the test-retest PET/CT imaging protocol. Shape, neighborhood gray-level difference matrix, and gray-level cooccurrence matrix features were repeatable, with a mean CCC value of 0.81. Radiomic features extracted from PETOSEM images showed significantly better repeatability than features extracted from PETPSF images (P < 0.001). Radiomic features extracted from VOI40 were more repeatable than features extracted from VOIWT (P < 0.001). For most features (78.4%), a change in bin number or voxel size resulted in less than a 10% change in feature value. All gray-level emphasis and gray-level run emphasis features showed poor repeatability (CCC values < 0.52) when extracted from VOIWT but were highly repeatable (mean CCC values > 0.96) when extracted from VOI40Conclusion: Shape, gray-level cooccurrence matrix, and neighborhood gray-level difference matrix radiomic features were consistently repeatable, whereas gray-level run length matrix and gray-level zone length matrix features were highly variable. Radiomic features extracted from VOI40 were more repeatable than features extracted from VOIWT Changes in voxel size or SUV discretization parameters typically resulted in relatively small differences in feature value, though several features were highly sensitive to these changes.

Relationship between tumor heterogeneity and volume in cervical cancer: Evidence from integrated fluorodeoxyglucose 18 PET/MR texture analysis

OBJECTIVE

The aim of this study was to evaluate the effect of cervical cancer volume on PET/magnetic resonance (MR) texture heterogeneity.

MATERIALS AND METHODS

We retrospectively analyzed the PET/MR images of 138 patients with pathologically diagnosed cervical squamous cell carcinoma, including 50 patients undergoing surgery and 88 patients receiving concurrent chemoradiotherapy. Fluorodeoxyglucose 18 (18FDG)-PET/MR examination were performed for each patient before treatment, and the PET and MR texture analysis were undertaken. The texture features of the tumor based on gray-level co-occurrence matrices were extracted, and the correlation between tumor texture features and volume parameters was analyzed using Spearman's rank correlation coefficient. Finally, the variation trend of tumor texture heterogeneity was analyzed as tumor volumes increased.

RESULTS

PET texture features were highly correlated with metabolic tumor volume (MTV), including entropy-log2, entropy-log10, energy, homogeneity, dissimilarity, contrast, correlation, and the correlation coefficients (rs) were 0.955, 0.955, -0.897, 0.883, -0.881, -0.876, and 0.847 (P < 0.001), respectively. In the range of smaller MTV, the texture heterogeneity of energy, entropy-log2, and entropy-log10 increases with an increase in tumor volume, whereas the texture heterogeneity of homogeneity, dissimilarity, contrast, and correlation decreases with an increase in tumor volume. Only homogeneity, contrast, correlation, and dissimilarity had high correlation with tumor volume on MRI. The correlation coefficients (rs) were 0.76, -0.737, 0.644, and -0.739 (P < 0.001), respectively. The texture heterogeneity of MRI features that are highly correlated with tumor volume decreases with increasing tumor volume.

CONCLUSION

In the small tumor volume range, the heterogeneity variation trend of PET texture features is inconsistent as the tumor volume increases, but the variation trend of MRI texture heterogeneity is consistent, and MRI texture heterogeneity decreases as tumor volume increases. These results suggest that MRI is a better imaging modality when compared with PET in determining tumor texture heterogeneity in the small tumor volume range.

Considerable effects of imaging sequences, feature extraction, feature selection, and classifiers on radiomics-based prediction of microvascular invasion in hepatocellular carcinoma using magnetic resonance imaging

Background

Microvascular invasion (MVI) has a significant effect on the prognosis of hepatocellular carcinoma (HCC), but its preoperative identification is challenging. Radiomics features extracted from medical images, such as magnetic resonance (MR) images, can be used to predict MVI. In this study, we explored the effects of different imaging sequences, feature extraction and selection methods, and classifiers on the performance of HCC MVI predictive models.

Methods

After screening against the inclusion criteria, 69 patients with HCC and preoperative gadoxetic acid-enhanced MR images were enrolled. In total, 167 features were extracted from the MR images of each sequence for each patient. Experiments were designed to investigate the effects of imaging sequence, number of gray levels (Ng), quantization algorithm, feature selection method, and classifiers on the performance of radiomics biomarkers in the prediction of HCC MVI. We trained and tested these models using leave-one-out cross-validation (LOOCV).

Results

The radiomics model based on the images of the hepatobiliary phase (HBP) had better predictive performance than those based on the arterial phase (AP), portal venous phase (PVP), and pre-enhanced T1-weighted images [area under the receiver operating characteristic (ROC) curve (AUC) =0.792 vs. 0.641/0.634/0.620, P=0.041/0.021/0.010, respectively]. Compared with the equal-probability and Lloyd-Max algorithms, the radiomics features obtained using the Uniform quantization algorithm had a better performance (AUC =0.643/0.666 vs. 0.792, P=0.002/0.003, respectively). Among the values of 8, 16, 32, 64, and 128, the best predictive performance was achieved when the Ng was 64 (AUC =0.792 vs. 0.584/0.697/0.677/0.734, P<0.001/P=0.039/0.001/0.137, respectively). We used a two-stage feature selection method which combined the least absolute shrinkage and selection operator (LASSO) and recursive feature elimination (RFE) gradient boosting decision tree (GBDT), which achieved better stability than and outperformed LASSO, minimum redundancy maximum relevance (mRMR), and support vector machine (SVM)-RFE (stability =0.967 vs. 0.837/0.623/0.390, respectively; AUC =0.850 vs. 0.792/0.713/0.699, P=0.142/0.007/0.003, respectively). The model based on the radiomics features of HBP images using the GBDT classifier showed a better performance for the preoperative prediction of MVI compared with logistic regression (LR), SVM, and random forest (RF) classifiers (AUC =0.895 vs. 0.850/0.834/0.884, P=0.558/0.229/0.058, respectively). With the optimal combination of these factors, we established the best model, which had an AUC of 0.895, accuracy of 87.0%, specificity of 82.5%, and sensitivity of 93.1%.

Conclusions

Imaging sequences, feature extraction and selection methods, and classifiers can have a considerable effect on the predictive performance of radiomics models for HCC MVI.