Value Of Radiomic Features Research Articles

ESR Essentials: radiomics-practice recommendations by the European Society of Medical Imaging Informatics.

Radiomics is a method to extract detailed information from diagnostic images that cannot be perceived by the naked eye. Although radiomics research carries great potential to improve clinical decision-making, its inherent methodological complexities make it difficult to comprehend every step of the analysis, often causing reproducibility and generalizability issues that hinder clinical adoption. Critical steps in the radiomics analysis and model development pipeline-such as image, application of image filters, and selection of feature extraction parameters-can greatly affect the values of radiomic features. Moreover, common errors in data partitioning, model comparison, fine-tuning, assessment, and calibration can reduce reproducibility and impede clinical translation. Clinical adoption of radiomics also requires a deep understanding of model explainability and the development of intuitive interpretations of radiomic features. To address these challenges, it is essential for radiomics model developers and clinicians to be well-versed in current best practices. Proper knowledge and application of these practices is crucial for accurate radiomics feature extraction, robust model development, and thorough assessment, ultimately increasing reproducibility, generalizability, and the likelihood of successful clinical translation. In this article, we have provided researchers with our recommendations along with practical examples to facilitate good research practices in radiomics. KEY POINTS: Radiomics' inherent methodological complexity should be understood to ensure rigorous radiomic model development to improve clinical decision-making. Adherence to radiomics-specific checklists and quality assessment tools ensures methodological rigor. Use of standardized radiomics tools and best practices enhances clinical translation of radiomics models.

The clinical predictive value of radiomic features from [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET in patients with prostate cancer: a preliminary comparative study

The clinical predictive value of radiomic features from [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET in patients with prostate cancer: a preliminary comparative study

Incremental Value of Radiomics Features of Epicardial Adipose Tissue for Detecting the Severity of COVID-19 Infection.

Epicardial adipose tissue (EAT) is known for its pro-inflammatory properties and association with Coronavirus Disease 2019 (COVID-19) severity. However, existing detection methods for COVID-19 severity assessment often lack consideration of organs and tissues other than the lungs, which limits the accuracy and reliability of these predictive models. The retrospective study included data from 515 COVID-19 patients (Cohort 1, n=415; Cohort 2, n=100) from two centers (Shanghai Public Health Center and Brazil Niteroi Hospital) between January 2020 and July 2020. Firstly, a three-stage EAT segmentation method was proposed by combining object detection and segmentation networks. Lung and EAT radiomics features were then extracted, and feature selection was performed. Finally, a hybrid model, based on seven machine learning models, was built for detecting COVID-19 severity. The hybrid model's performance and uncertainty were evaluated in both internal and external validation cohorts. For EAT extraction, the Dice similarity coefficients (DSC) of the two centers were 0.972 (±0.011) and 0.968 (±0.005), respectively. For severity detection, the area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) of the hybrid model increased by 0.09 (p<0.001), 19.3 % (p<0.05), and 18.0 % (p<0.05) in the internal validation cohort, and by 0.06 (p<0.001), 18.0 % (p<0.05) and 18.0 % (p<0.05) in the external validation cohort, respectively. Uncertainty and radiomics features analysis confirmed the interpretability of increased certainty in case prediction after inclusion of EAT features. This study proposed a novel three-stage EAT extraction method. We demonstrated that adding EAT radiomics features to a COVID-19 severity detection model results in increased accuracy and reduced uncertainty. The value of these features was also confirmed through feature importance ranking and visualization.

Radiomics analysis of cerebral blood flow suggests a possible link between perfusion homogeneity and poor glioblastoma multiforme prognosis

Objectives. This study investigates the association between cerebral blood flow (CBF) and overall survival (OS) in glioblastoma multiforme (GBM) patients receiving chemoradiation. Identifying CBF biomarkers could help predict patient response to this treatment, facilitating the development of personalized therapeutic strategies. Materials and Methods. This retrospective study analyzed CBF data from dynamic susceptibility contrast (DSC) MRI in 30 newly diagnosed GBM patients (WHO grade IV). Radiomics features were extracted from CBF maps, tested for robustness, and correlated with OS. Kaplan-Meier analysis was used to assess the predictive value of radiomic features significantly associated with OS, aiming to stratify patients into groups with distinct post-treatment survival outcomes. Results. While mean relative CBF and CBV failed to serve as independent prognostic markers for OS, the prognostic potential of radiomic features extracted from CBF maps was explored. Ten out of forty-three radiomic features with highest intraclass correlation coefficients (ICC > 0.9), were selected for characterization. While Correlation and Zone Size Variance (ZSV) features showed significant OS correlations, indicating prognostic potential, Kaplan-Meier analysis did not significantly stratify patients based on these features. Visual analysis of the graphs revealed a predominant association between the identified radiomic features and OS under two years. Focusing on this subgroup, Correlation, ZSV, and Gray-Level Nonuniformity (GLN) emerged as significant, suggesting that a lack of heterogeneity in perfusion patterns may be indicative of a poorer outcome. Kaplan-Meier analysis effectively stratified this cohort based on the features mentioned above. Receiver operating characteristic (ROC) analysis further validated their prognostic value, with ZSV demonstrating the highest sensitivity and specificity (0.75 and 0.85, respectively). Conclusion. Our findings underscored radiomics features sensitive to CBF heterogeneity as pivotal predictors for patient stratification. Our results suggest that these markers may have the potential to identify patients who are unlikely to benefit from standard chemoradiation therapy.

CT-based radiomics for predicting breast cancer radiotherapy side effects

Skin inflammation with the potential sequel of moist epitheliolysis and edema constitute the most frequent breast radiotherapy (RT) acute side effects. The aim of this study was to compare the predictive value of tissue-derived radiomics features to the total breast volume (TBV) for the moist cells epitheliolysis as a surrogate for skin inflammation, and edema. Radiomics features were extracted from computed tomography (CT) scans of 252 breast cancer patients from two volumes of interest: TBV and glandular tissue (GT). Machine learning classifiers were trained on radiomics and clinical features, which were evaluated for both side effects. The best radiomics model was a least absolute shrinkage and selection operator (LASSO) classifier, using TBV features, predicting moist cells epitheliolysis, achieving an area under the receiver operating characteristic (AUROC) of 0.74. This was comparable to TBV breast volume (AUROC of 0.75). Combined models of radiomics and clinical features did not improve performance. Exclusion of volume-correlated features slightly reduced the predictive performance (AUROC 0.71). We could demonstrate the general propensity of planning CT-based radiomics models to predict breast RT-dependent side effects. Mammary tissue was more predictive than glandular tissue. The radiomics features performance was influenced by their high correlation to TBV volume.

Enhancing lymph node metastasis prediction in adenocarcinoma of the esophagogastric junction: A study combining radiomic with clinical features.

The incidence of adenocarcinoma of the esophagogastric junction (AEJ) is increasing, and with poor prognosis. Lymph node status (LNs) is particularly important for planning treatment and evaluating the prognosis of patients with AEJ. However, the use of radiomic based on enhanced computed tomography (CT) to predict the preoperative lymph node metastasis (PLNM) status of the AEJ has yet to be reported. We sought to investigate the value of radiomic features based on enhanced CT in the accurate prediction of PLNM in patients with AEJ. Clinical features and enhanced CT data of 235 patients with AEJ from October 2017 to May 2023 were retrospectively analyzed. The data were randomly assigned to the training cohort (n=164) or the external testing cohort (n=71) at a ratio of 7:3. A CT-report model, clinical model, radiomic model, and radiomic-clinical combined model were developed to predict PLNM in patients with AEJ. Univariate and multivariate logistic regression were used to screen for independent clinical risk factors. Least absolute shrinkage and selection operator (LASSO) regression was used to select the radiomic features. Finally, a nomogram for the preoperative prediction of PLNM in AEJ was constructed by combining Radiomics-score and clinical risk factors. The models were evaluated by area under the receiver operating characteristic curve (AUC-ROC), calibration curve, and decision curve analyses. A total of 181 patients (181/235, 77.02%) had LNM. In the testing cohort, the AUC of the radiomic-clinical model was 0.863 [95% confidence interval (CI)=0.738-0.957], and the radiomic model (0.816; 95% CI=0.681-0.929), clinical model (0.792; 95% CI=0.677-0.888), and CT-report model (0.755; 95% CI=0.647-0.840). The radiomic-clinical model is a feasible method for predicting PLNM in patients with AEJ, helping to guide clinical decision-making and personalized treatment planning.

Beyond hand-crafted features for pretherapeutic molecular status identification of pediatric low-grade gliomas

The use of targeted agents in the treatment of pediatric low-grade gliomas (pLGGs) relies on the determination of molecular status. It has been shown that genetic alterations in pLGG can be identified non-invasively using MRI-based radiomic features or convolutional neural networks (CNNs). We aimed to build and assess a combined radiomics and CNN non-invasive pLGG molecular status identification model. This retrospective study used the tumor regions, manually segmented from T2-FLAIR MR images, of 336 patients treated for pLGG between 1999 and 2018. We designed a CNN and Random Forest radiomics model, along with a model relying on a combination of CNN and radiomic features, to predict the genetic status of pLGG. Additionally, we investigated whether CNNs could predict radiomic feature values from MR images. The combined model (mean AUC: 0.824) outperformed the radiomics model (0.802) and CNN (0.764). The differences in model performance were statistically significant (p-values < 0.05). The CNN was able to learn predictive radiomic features such as surface-to-volume ratio (average correlation: 0.864), and difference matrix dependence non-uniformity normalized (0.924) well but was unable to learn others such as run-length matrix variance (− 0.017) and non-uniformity normalized (− 0.042). Our results show that a model relying on both CNN and radiomic-based features performs better than either approach separately in differentiating the genetic status of pLGGs, and that CNNs are unable to express all handcrafted features.

An approach leveraging radiomics and model checking for the automatic early diagnosis of adhesive capsulitis

Adhesive Capsulitis of the shoulder is a painful pathology limiting shoulder movements, commonly known as “Frozen Shoulder”. Since this pathology limits movement, it is important to make an early diagnosis. Diagnosing capsulitis relies on clinical assessment, although diagnostic imaging, such as Magnetic Resonance Imaging, can provide predictive or supportive information for specific characteristic signs. However, its diagnosis is not so simple nor so immediate, indeed it remains a difficult topic for many general radiologists and expert musculoskeletal radiologists. This study aims to investigate whether it is possible to use disease signs within a medical image to automatically diagnose Adhesive Capsulitis. To this purpose, we propose an automatic Model Checking-based approach to quickly diagnose the Adhesive Capsulitis taking as input the radiomic feature values from the medical images. Furthermore, we compare the performance achieved by our method with diagnostic results obtained by professional radiologists with different levels of experience. To the best of our knowledge, this is the first method for the automatic diagnosis of Adhesive Capsulitis of the Shoulder.

The value of radiomics features of the spleen as surrogates for differentiating subtypes of common pediatric lymphomas.

Lymphoma is a common malignant tumor in children. The pathologic subtyping of lymphoma is high complex, and the treatment options vary. The different pathologic subtypes of lymphomas have no significant differences on computed tomography (CT) images. As it is a hematologic disease, patients with lymphoma often show abnormalities in the spleen, and so the aim of this study was to construct a model for differentiating Burkitt lymphoma (BL) from lymphoblastic lymphoma through the extraction of radiomic features of the spleen from CT images. This could provide an efficient, noninvasive method that can differentiate the common pathological subtypes in patients with pediatric lymphoma. The clinical data and imaging data of 48 patients with lymphoblastic lymphoma and 61 patients with BL were retrospectively analyzed. The dataset was divided into a training set (n=76) and a test set (n=33) through complete randomization. Radiomics features of the spleen were separately extracted from CT images in the noncontrast enhanced, arterial, and venous phases. These phase-specific features were integrated to construct fusion models. Three classifiers, quadratic discriminant analysis (QDA), logistic regression (LR), and support vector machine (SVM), were employed to build the models. The fusion model exhibited superior performance compared to individual models. There was no significant difference between the fusion models constructed by QDA and LR in either the training set or the test set. Among the four fusion models constructed with the SVM classifier, SVM_4 emerged as the best performing model. The area under the curve, sensitivity, specificity, and F1-score of the SVM_4 model were 0.967 [95% confidence interval (CI): 0.935-0.998], 0.86, 0.97, and 0.913 in the training set, respectively, and 0.754 (95% CI: 0.584-0.924), 0.611, 0.867, and 0.71 in the test set, respectively. The radiomics features of the spleen demonstrated the capability to distinguish between the two most common lymphoma subtypes in pediatric patients. This noninvasive approach holds promise for efficient and accurate discrimination.

The Value of Radiomic Features of Primary Breast Tumor in STIR Sequences in Predicting Axilla Metastasis

Background: Detection of axillary metastases in breast cancer is critical for treatment options and prognosis. The aim of this study is to investigate the value of radiomic features obtained from short tau inversion recovery (STIR) sequences in magnetic resonance imaging (MRI) of primary tumor in breast cancer in predicting axillary lymph node metastasis (ALNM). Methods: Lesions of 165 patients with a mean age of 51.12 ±11 (range 28-82) with newly diagnosed invasive breast cancer who underwent breast MRI before treatment were manually segmented from STIR sequences in the 3D Slicer program in all sections. Machine learning (ML) analysis was performed using the extracted 851 features Python 3.11, Pycaret library program. Datasets were randomly divided into train (123, 80%) and independent test (63, 20%) datasets. The performances of ML algorithms were compared with area under curve (AUC), accuracy, recall, presicion and F1 scores. Results: Accuracy and AUC in the training set were in the range of 57 %-86 % and 0.50-0.95, respectively. The best model in the training set was the catBoost classifier with an AUC of 0.95 and 84% accuracy. The AUC, accuracy, recall, precision values and F1 score of the CatBoost classifier on the test set were 0.92, 84 %, 89 %, 85 %, 86 %, respectively. Conclusion: Radiomic features obtained from primary tumors on STIR sequences have the potential to predict ALNM in invasive breast cancer.

Radiomic feature robustness in CT scans affected by fiducial marker induced streak artifacts for patients with hepatocellular carcinoma.

Stereotactic body radiation therapy for hepatocellular carcinoma necessitates the implantation of gold fiducial markers in the liver, resulting in artifacts on computed tomography (CT) scans, which affect radiomic feature values. This report aims to assess the effect of these artifacts on radiomic features and how removing CT slices affects radiomic features extracted from 3D regions of interest (ROI). First, the range variation in 38 tumor contours unaffected by artifacts was assessed after sequentially and randomly removing 25%, 50%, 75% of slices. Subsequently, the agreement of feature values before and after removing ROI slices containing artifacts from 186 patients' CT scans was assessed with Lin's concordance correlation coefficient (CCC) and a Wilcoxon signed-rank test. In artifact-free tumor volumes, at least 71% of features remain robust with up to 50% of slices removed, while 56% remains robust with up to 75% of slices removed. When comparing contours before and after removing slices containing artifacts, around a third of features in the tumor contour and surrounding area remain robust (CCC>0.9), compared to 44% in the healthy liver. Concerning the tumor, 13% (Gray Level Size Zone Matrix) to 61% (first order) of the features remain robust (CCC>0.9). Over 90% of features differ significantly as assessed by Wilcoxon signed-rank test, however. This study demonstrates that removing slices containing artifacts is a feasible solution for the CT fiducial problem in this patient population and provides insight into which features are affected.

The Value of Radiomics Features Based on HRCT in Predicting whether the Lung Sub-Centimeter Pure Ground Glass Nodule is Benign or Malignant.

In this study, a radiomics model was created based on High-Resolution Computed Tomography (HRCT) images to noninvasively predict whether the sub-centimeter pure Ground Glass Nodule (pGGN) is benign or malignant. A total of 235 patients (251 sub-centimeter pGGNs) who underwent preoperative HRCT scans and had postoperative pathology results were retrospectively evaluated. The nodules were randomized in a 7:3 ratio to the training (n=175) and the validation cohort (n=76). The volume of interest was delineated in the thin-slice lung window, from which 1316 radiomics features were extracted. The Least Absolute Shrinkage and Selection Operator (LASSO) was used to select the radiomics features. Univariate and multivariable logistic regression were used to evaluate the independent risk variables. The performance was assessed by obtaining Receiver Operating Characteristic (ROC) curves for the clinical, radiomics, and combined models, and then the Decision Curve Analysis (DCA) assessed the clinical applicability of each model. Sex, volume, shape, and intensity mean were chosen by univariate analysis to establish the clinical model. Two radiomics features were retained by LASSO regression to build the radiomics model. In the training cohort, the Area Under the Curve (AUC) of the radiomics (AUC=0.844) and combined model (AUC=0.871) was higher than the clinical model (AUC=0.773). In evaluating whether or not the sub-centimeter pGGN is benign, the DCA demonstrated that the radiomics and combined model had a greater overall net benefit than the clinical model. The radiomics model may be useful in predicting the benign and malignant sub-centimeter pGGN before surgery.</p>.

Coronary CTA-based radiomic signature of pericoronary adipose tissue predict rapid plaque progression

ObjectivesTo explore the value of radiomic features derived from pericoronary adipose tissue (PCAT) obtained by coronary computed tomography angiography for prediction of coronary rapid plaque progression (RPP).MethodsA total of 1233 patients from two centers were included in this multicenter retrospective study. The participants were divided into training, internal validation, and external validation cohorts. Conventional plaque characteristics and radiomic features of PCAT were extracted and analyzed. Random Forest was used to construct five models. Model 1: clinical model. Model 2: plaque characteristics model. Model 3: PCAT radiomics model. Model 4: clinical + radiomics model. Model 5: plaque characteristics + radiomics model. The evaluation of the models encompassed identification accuracy, calibration precision, and clinical applicability. Delong’ test was employed to compare the area under the curve (AUC) of different models.ResultsSeven radiomic features, including two shape features, three first-order features, and two textural features, were selected to build the PCAT radiomics model. In contrast to the clinical model and plaque characteristics model, the PCAT radiomics model (AUC 0.85 for training, 0.84 for internal validation, and 0.81 for external validation; p < 0.05) achieved significantly higher diagnostic performance in predicting RPP. The separate combination of radiomics with clinical and plaque characteristics model did not further improve diagnostic efficacy statistically (p > 0.05).ConclusionRadiomic feature analysis derived from PCAT significantly improves the prediction of RPP as compared to clinical and plaque characteristics. Radiomic analysis of PCAT may improve monitoring RPP over time.Critical relevance statementOur findings demonstrate PCAT radiomics model exhibited good performance in the prediction of RPP, with potential clinical value.Key PointsRapid plaque progression may be predictable with radiomics from pericoronary adipose tissue.Fibrous plaque volume, diameter stenosis, and fat attenuation index were identified as risk factors for predicting rapid plaque progression.Radiomics features of pericoronary adipose tissue can improve the predictive ability of rapid plaque progression.Graphical

Preoperative prediction of lymph node metastasis in colorectal cancer using 18F-FDG PET/CT peritumoral radiomics analysis.

Radiomics has been used in the diagnosis of tumor lymph node metastasis (LNM). However, to date, most studies have been based on intratumoral radiomics. Few studies have focused on the use of 18F-fluorodeoxyglucose positron emission computed tomography (18F-FDG PET/CT) peritumoral radiomics for the diagnosis of LNM in colorectal cancer (CRC). Determining the value of radiomics features extracted from 18F-FDG PET/CT images of the peritumoral region in predicting LNM in patients with CRC. The clinical data and preoperative 18F-FDG PET/CT images of 244 CRC patients were retrospectively analyzed. Intratumoral and peritumoral radiomics features were screened using the mutual information method, and least absolute shrinkage and selection operator regression. Based on the selected radiomics features, a radiomics score (Rad-score) was calculated, and independent risk factors obtained from univariate and multivariate logistic regression analyses were used to construct clinical and combined (Radiomics + Clinical) models. The performance of these models was evaluated using the DeLong test, while their clinical utility was assessed by decision curve analysis. Finally, a nomogram was constructed to visualize the predictive model. The most optimal set of features retained by the feature filtering process were all peritumoral radiomic features. Carcinoembryonic antigen levels, PET/CT-reported lymph node status and Rad-score were found to be independent risk factors for LNM. All three LNM risk assessment models exhibited good predictive performance, with the combined model showing the best classification results, with areas under the curve of 0.85 and 0.76 in the training and validation groups, respectively. The DeLong test revealed that the performance of the combined model was superior to that of the clinical and radiomics models in both the training and validation groups, although this difference was only statistically significant in the training group. DCA indicated that the combined model displayed better clinical utility. 18F-FDG PET/CT peritumoral radiomics is uniquely suited to predict the presence of LNM in patients with CRC. In particular, the predictive efficacy of LNM for precision therapy and individualized patient management can be improved by using a combination of clinical risk factors.

Value of magnetic resonance imaging radiomics features in predicting histologic grade of invasive ductal carcinoma of the breast.

Breast cancer has the second highest mortality rate of all cancers and occurs mainly in women. To investigate the relationship between magnetic resonance imaging (MRI) radiomics features and histological grade of invasive ductal carcinoma (IDC) of the breast and to evaluate its diagnostic efficacy. The two conventional MRI quantitative indicators, i.e. the apparent diffusion coefficient (ADC) and the initial enhancement rate, were collected from 112 patients with breast cancer. The breast cancer lesions were manually segmented in dynamic contrast-enhanced MRI (DCE-MRI) and ADC images, the differences in radiomics features between Grades I, II and III IDCs were compared and the diagnostic efficacy was evaluated. The ADC values (0.77 ± 0.22 vs 0.91 ± 0.22 vs 0.92 ± 0.20, F= 4.204, p< 0.01), as well as the B_sum_variance (188.51 ± 67.803 vs 265.37 ± 77.86 vs 263.74 ± 82.58, F= 6.040, p< 0.01), L_energy (0.03 ± 0.02 vs 0.13 ± 0.11 vs 0.12 ± 0.14, F= 7.118, p< 0.01) and L_sum_average (0.78 ± 0.32 vs 16.34 ± 4.23 vs 015.45 ± 3.74, F= 21.860, p< 0.001) values of patients with Grade III IDC were significantly lower than those of patients with Grades I and II IDC. The B_uniform (0.15 ± 0.12 vs 0.11 ± 0.04 vs 0.12 ± 0.03, F= 3.797, p< 0.01) and L_SRE (0.85 ± 0.07 vs 0.78 ± 0.03 vs 0.79 ± 0.32, F= 3.024, p< 0.01) values of patients with Grade III IDC were significantly higher than those of patients with Grades I and II IDC. All differences were statistically significant (p< 0.05). The ADC radiomics signature model had a higher area-under-the-curve value in identifying different grades of IDC than the ADC value model and the DCE radiomics signature model (0.869 vs 0.711 vs 0.682). The accuracy (0.812 vs 0.647 vs 0.710), specificity (0.731 vs 0.435 vs 0.342), positive predictive value (0.815 vs 0.663 vs 0.669) and negative predictive value (0.753 vs 0.570 vs 0.718) of the ADC radiomics signature model were all significantly better than the ADC value model and the DCE radiomics signature model. ADC values and breast MRI radiomics signatures are significant in identifying the histological grades of IDC, with the ADC radiomics signatures having greater value.

Prognostic value of the combination of volume, massiveness and fragmentation parameters measured on baseline FDG pet in high-burden follicular lymphoma

The prognostic value of radiomic quantitative features measured on pre-treatment 18F-FDG PET/CT was investigated in patients with follicular lymphoma (FL). We conducted a retrospective study of 126 FL patients (grade 1-3a) diagnosed between 2006 and 2020. A dozen of PET/CT-derived features were extracted via a software (Oncometer3D) from baseline 18F-FDG PET/CT images. The receiver operating characteristic (ROC) curve, Kaplan–Meier method and Cox analysis were used to assess the prognostic factors for progression of disease within 24 months (POD24) and progression-free survival at 24 months. Four different clusters were identified among the twelve PET parameters analyzed: activity, tumor burden, fragmentation-massiveness and dispersion. On ROC analyses, TMTV, the total metabolic tumor volume, had the highest AUC (0.734) followed by medPCD, the median distance between the centroid of the tumors and their periphery (AUC: 0.733). Patients with high TMTV (HR = 4.341; p < 0.001), high Tumor Volume Surface Ratio (TVSR) (HR = 3.204; p < 0.003) and high medPCD (HR = 4.507; p < 0.001) had significantly worse prognosis in both Kaplan–Meier and Cox univariate analyses. Furthermore, a synergistic effect was observed in Kaplan–Meier and Cox analyses combining these three PET/CT-derived parameters (HR = 12.562; p < 0.001). Having two or three high parameters among TMTV, TVSR and medPCD was able to predict POD24 status with a specificity of 68% and a sensitivity of 75%. TMTV, TVSR and baseline medPCD are strong prognostic factors in FL and their combination better predicts disease prognosis.

Prognostic value of different discretization parameters in 18fluorodeoxyglucose positron emission tomography radiomics of oropharyngeal squamous cell carcinoma.

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

Synthesis of virtual monoenergetic images from kilovoltage peak images using wavelet loss enhanced CycleGAN for improving radiomics features reproducibility.

Dual-energy computed tomography (CT) can provide a range of image information beyond conventional CT through virtual monoenergetic images (VMIs). The purpose of this study was to investigate the impact of material decomposition in detector-based spectral CT on radiomics features and effectiveness of using deep learning-based image synthesis to improve the reproducibility of radiomics features. In this paper, spectral CT image data from 45 esophageal cancer patients were collected for investigation retrospectively. First, we computed the correlation coefficient of radiomics features between conventional kilovoltage peak (kVp) CT images and VMI. Then, a wavelet loss-enhanced CycleGAN (WLL-CycleGAN) with paired loss terms was developed to synthesize virtual monoenergetic CT images from the corresponding conventional single-energy CT (SECT) images for improving radiomics reproducibility. Finally, the radiomic features in 6 different categories, including gray-level co-occurrence matrix (GLCM), gray-level difference matrix (GLDM), gray-level run-length matrix (GLRLM), gray-level size-zone matrix (GLSZM), neighborhood gray-tone difference matrix (NGTDM), and wavelet, were extracted from the gross tumor volumes from conventional single energy CT, synthetic virtual monoenergetic CT images, and virtual monoenergetic CT images. Comparison between errors in the VMI and synthetic VMI (sVMI) suggested that the performance of our proposed deep learning method improved the radiomic feature accuracy. Material decomposition of dual-layer dual-energy CT (DECT) can substantially influence the reproducibility of the radiomic features, and the degree of impact is feature dependent. The average reduction of radiomics errors for 15 patients in testing sets was 96.9% for first-order, 12.1% for GLCM, 12.9% for GLDM, 15.7% for GLRLM, 50.3% for GLSZM, 53.4% for NGTDM, and 6% for wavelet features. The work revealed that material decomposition has a significant effect on the radiomic feature values. The deep learning-based method reduced the influence of material decomposition in VMIs and might improve the robustness and reproducibility of radiomic features in esophageal cancer. Quantitative results demonstrated that our proposed wavelet loss-enhanced paired CycleGAN outperforms the original CycleGAN.

Predictive value of delta radiomics in xerostomia after chemoradiotherapy in patients with stage III-IV nasopharyngeal carcinoma

BackgroundXerostomia is one of the most common side effects in nasopharyngeal carcinoma (NPC) patients after chemoradiotherapy. To establish a Delta radiomics model for predicting xerostomia secondary to chemoradiotherapy for NPC based on magnetic resonance T1-weighted imaging (T1WI) sequence and evaluate its diagnostic efficacy.MethodsClinical data and Magnetic resonance imaging (MRI) data before treatment and after induction chemotherapy (IC) of 255 NPC patients with stage III-IV were collected retrospectively. Within one week after CCRT, the patients were divided into mild (92 cases) and severe (163 cases) according to the grade of xerostomia. Parotid glands in T1WI sequence images before and after IC were delineated as regions of interest for radiomics feature extraction, and Delta radiomics feature values were calculated. Univariate logistic analysis, correlation, and Gradient Boosting Decision Tree (GBDT) methods were applied to reduce the dimension, select the best radiomics features, and establish pretreatment, post-IC, and Delta radiomics xerostomia grading predictive models. The receiver operating characteristic (ROC) curve and decision curve were drawn to evaluate the predictive efficacy of different models.ResultsFinally, 15, 10, and 12 optimal features were selected from pretreatment, post-IC, and Delta radiomics features, respectively, and a xerostomia prediction model was constructed with AUC values of 0.738, 0.751, and 0.843 in the training set, respectively. Only age was statistically significant in the clinical data of both groups (P < 0.05).ConclusionDelta radiomics can predict the degree of xerostomia after chemoradiotherapy for NPC patients and it has certain guiding significance for clinical early intervention measures.

A radiomics-based brain network in T1 images: construction, attributes, and applications.

T1 image is a widely collected imaging sequence in various neuroimaging datasets, but it is rarely used to construct an individual-level brain network. In this study, a novel individualized radiomics-based structural similarity network was proposed from T1 images. In detail, it used voxel-based morphometry to obtain the preprocessed gray matter images, and radiomic features were then extracted on each region of interest in Brainnetome atlas, and an individualized radiomics-based structural similarity network was finally built using the correlational values of radiomic features between any pair of regions of interest. After that, the network characteristics of individualized radiomics-based structural similarity network were assessed, including graph theory attributes, test-retest reliability, and individual identification ability (fingerprinting). At last, two representative applications for individualized radiomics-based structural similarity network, namely mild cognitive impairment subtype discrimination and fluid intelligence prediction, were exemplified and compared with some other networks on large open-source datasets. The results revealed that the individualized radiomics-based structural similarity network displays remarkable network characteristics and exhibits advantageous performances in mild cognitive impairment subtype discrimination and fluid intelligence prediction. In summary, the individualized radiomics-based structural similarity network provides a distinctive, reliable, and informative individualized structural brain network, which can be combined with other networks such as resting-state functional connectivity for various phenotypic and clinical applications.