Search

To date, studies investigating radiomics-based predictive models have tended to err on the side of data-driven or exploratory analysis of many thousands of extracted features. In particular, spatial assessments of texture have proven to be especially adept at assessing for features of intratumoral heterogeneity in oncologic imaging, which likewise may correspond with tumor biology and behavior. These spatial assessments can be generally classified as spatial filters, which detect areas of rapid change within the grayscale in order to enhance edges and/or textures within an image, or neighborhood-based methods, which quantify gray-level differences of neighboring pixels/voxels within a set distance. Given the high dimensionality of radiomics datasets, data dimensionality reduction methods have been proposed in an attempt to optimize model performance in machine learning studies; however, it should be noted that these approaches should only be applied to training data in order to avoid information leakage and model overfitting. While area under the curve of the receiver operating characteristic is perhaps the most commonly reported assessment of model performance, it is prone to overestimation when output classifications are unbalanced. In such cases, confusion matrices may be additionally reported, whereby diagnostic cut points for model predicted probability may hold more clinical significance to clinical colleagues with respect to related forms of diagnostic testing.

When properly implemented and processed, anatomic T1-weighted magnetic resonance imaging (MRI) can be ideal for the noninvasive quantification of white matter (WM) and gray matter (GM) in the living human brain. Although MRI is more suitable for distinguishing GM from WM than computed tomography (CT), the growing clinical use of the latter technique has renewed interest in head CT segmentation. Such interest is particularly strong in settings where MRI is unavailable, logistically unfeasible or prohibitively expensive. Nevertheless, whereas MRI segmentation is a sophisticated and technically-mature research field, the task of automatically classifying soft brain tissues from CT remains largely unexplored. Furthermore, brain segmentation methods for MRI hold considerable potential for adaptation and application to CT image processing. Here we demonstrate this by combining probabilistic, atlas-based classification with topologically-constrained tissue boundary refinement to delineate WM, GM and cerebrospinal fluid (CSF) from head CT images. The feasibility and utility of this approach are revealed by comparison of MRI-only vs. CT-only segmentations in geriatric concussion victims with both MRI and CT scans. Comparison of the two segmentations yields mean Sørensen-Dice coefficients of 85.5 ± 4.6% (WM), 86.7 ± 5.6% (GM) and 91.3 ± 2.8% (CSF), as well as average Hausdorff distances of 3.76 ± 1.85 mm (WM), 3.43 ± 1.53 mm (GM) and 2.46 ± 1.27 mm (CSF). Bootstrapping results suggest that the segmentation approach is sensitive enough to yield WM, GM and CSF volume estimates within ~5%, ~4%, and ~3% of their MRI-based estimates, respectively. To our knowledge, this is the first 3D segmentation approach for CT to undergo rigorous within-subject comparison with high-resolution MRI. Results suggest that (1) standard-quality CT allows WM/GM/CSF segmentation with reasonable accuracy, and that (2) the task of soft brain tissue classification from CT merits further attention from neuroimaging researchers.

The persistent trigeminal artery (PTA) is the largest and most commonly occurring type of remnant fetal arteries, typically originating from the posterior bend or lateral wall of the intracavernous carotid artery. There are no published reports of coexisting PTA and midline epithelial tumors. We describe a coincident case of craniopharyngioma associated with an adjacent PTA traversing through the sella turcica, which are both developmental midline skull base anomalies. The caliber and location of the PTA precluded an endoscopic endonasal operation; the tumor was safely resected via a supraorbital keyhole approach. Anatomic implications pertaining to surgical approach and treatment are also discussed. Surgeons performing endonasal skull base operations should be vigilant for the presence of PTAs and related vascular anomalies on MR imaging. Noninvasive vascular imaging can confirm and assist with preoperative planning.

I Anny H. Xiang, Mayra P. Martinez, Enrique Trigo, Kristina M. Utzschneider, Melanie Cree-Green, Silva A. Arslanian, David A. Ehrmann, Sonia Caprio, Passant H. I. H. Mohamed, Darryl H. Hwang, Namir Katkhouda, Krishna S. Nayak, and Thomas A. Buchanan, for the RISE Consortium i In the above article, Elizabeth Beale's name was missing from the author byline. Liver fat reduction after gastric banding and associations with changes in insulin sensitivity and -cell function. The correct author byline follows: Anny H. Xiang SP 1 sp , Mayra P. Martinez SP 1 sp , Enrique Trigo SP 2 sp , Kristina M. Utzschneider SP 3 sp , Melanie Cree-Green SP 4 sp , Silva A. Arslanian SP 5 sp , David A. Ehrmann SP 6 sp , Sonia Caprio SP 7 sp , Passant H. I. H. Mohamed SP 8 sp , Darryl H. Hwang SP 8 sp , Elizabeth Beale SP 2 sp , Namir Katkhouda SP 9 sp , Krishna S. Nayak SP 10 sp , and Thomas A. Buchanan SP 2 sp , for the RISE Consortium* The authors apologize for this error. [Extracted from the article]

Objectives: To evaluate the performance of machine learning–augmented MRI-based radiomics models for predicting response to neoadjuvant chemotherapy (NAC) in soft tissue sarcomas. Methods: Forty-four subjects were identified retrospectively from patients who received NAC at our institution for pathologically proven soft tissue sarcomas. Only subjects who had both a baseline MRI prior to initiating chemotherapy and a post-treatment scan at least 2 months after initiating chemotherapy and prior to surgical resection were included. 3D ROIs were used to delineate whole-tumor volumes on pre- and post-treatment scans, from which 1708 radiomics features were extracted. Delta-radiomics features were calculated by subtraction of baseline from post-treatment values and used to distinguish treatment response through univariate analyses as well as machine learning–augmented radiomics analyses. Results: Though only 4.74% of variables overall reached significance at p ≤ 0.05 in univariate analyses, Laws Texture Energy (LTE)-derived metrics represented 46.04% of all such features reaching statistical significance. ROC analyses similarly failed to predict NAC response, with AUCs of 0.40 (95% CI 0.22–0.58) and 0.44 (95% CI 0.26–0.62) for RF and AdaBoost, respectively. Conclusion: Overall, while our result was not able to separate NAC responders from non-responders, our analyses did identify a subset of LTE-derived metrics that show promise for further investigations. Future studies will likely benefit from larger sample size constructions so as to avoid the need for data filtering and feature selection techniques, which have the potential to significantly bias the machine learning procedures. [ABSTRACT FROM AUTHOR]

Introduction: This study investigates how quantitative texture analysis can be used to non-invasively identify novel radiogenomic correlations with clear cell renal cell carcinoma (ccRCC) biomarkers. Methods: The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma open-source database was used to identify 190 sets of patient genomic data that had corresponding multiphase contrast-enhanced CT images in The Cancer Imaging Archive. 2,824 radiomic features spanning fifteen texture families were extracted from CT images using a custom-built MATLAB software package. Robust radiomic features with strong inter-scanner reproducibility were selected. Random forest, AdaBoost, and elastic net machine learning (ML) algorithms evaluated the ability of the selected radiomic features to predict the presence of 12 clinically relevant molecular biomarkers identified from the literature. ML analysis was repeated with cases stratified by stage (I/II vs. III/IV) and grade (1/2 vs. 3/4). 10-fold cross validation was used to evaluate model performance. Results: Before stratification by tumor grade and stage, radiomics predicted the presence of several biomarkers with weak discrimination (AUC 0.60–0.68). Once stratified, radiomics predicted KDM5C, SETD2, PBRM1, and mTOR mutation status with acceptable to excellent predictive discrimination (AUC ranges from 0.70 to 0.86). Conclusions: Radiomic texture analysis can potentially identify a variety of clinically relevant biomarkers in patients with ccRCC and may have a prognostic implication. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the utility of CT-based radiomics signatures in discriminating low-grade (grades 1-2) clear cell renal cell carcinomas (ccRCC) from high-grade (grades 3-4) and low TNM stage (stages I-II) ccRCC from high TNM stage (stages III-IV).Methods: A total of 587 subjects (mean age 60.2 years ± 12.2; range 22-88.7 years) with ccRCC were included. A total of 255 tumors were high grade and 153 were high stage. For each subject, one dominant tumor was delineated as the region of interest (ROI). Our institutional radiomics pipeline was then used to extract 2824 radiomics features across 12 texture families from the manually segmented volumes of interest. Separate iterations of the machine learning models using all extracted features (full model) as well as only a subset of previously identified robust metrics (robust model) were developed. Variable of importance (VOI) analysis was performed using the out-of-bag Gini index to identify the top 10 radiomics metrics driving each classifier. Model performance was reported using area under the receiver operating curve (AUC).Results: The highest AUC to distinguish between low- and high-grade ccRCC was 0.70 (95% CI 0.62-0.78) and the highest AUC to distinguish between low- and high-stage ccRCC was 0.80 (95% CI 0.74-0.86). Comparable AUCs of 0.73 (95% CI 0.65-0.8) and 0.77 (95% CI 0.7-0.84) were reported using the robust model for grade and stage classification, respectively. VOI analysis revealed the importance of neighborhood operation-based methods, including GLCM, GLDM, and GLRLM, in driving the performance of the robust models for both grade and stage classification.Conclusion: Post-validation, CT-based radiomics signatures may prove to be useful tools to assess ccRCC grade and stage and could potentially add to current prognostic models. Multiphase CT-based radiomics signatures have potential to serve as a non-invasive stratification schema for distinguishing between low- and high-grade as well as low- and high-stage ccRCC.Key Points: • Radiomics signatures derived from clinical multiphase CT images were able to stratify low- from high-grade ccRCC, with an AUC of 0.70 (95% CI 0.62-0.78). • Radiomics signatures derived from multiphase CT images yielded discriminative power to stratify low from high TNM stage in ccRCC, with an AUC of 0.80 (95% CI 0.74-0.86). • Models created using only robust radiomics features achieved comparable AUCs of 0.73 (95% CI 0.65-0.80) and 0.77 (95% CI 0.70-0.84) to the model with all radiomics features in classifying ccRCC grade and stage, respectively. [ABSTRACT FROM AUTHOR]

The goal of the Enhancing Neuroimaging Genetics through Meta‐Analysis (ENIGMA) Stroke Recovery working group is to understand brain and behavior relationships using well‐powered meta‐ and mega‐analytic approaches. ENIGMA Stroke Recovery has data from over 2,100 stroke patients collected across 39 research studies and 10 countries around the world, comprising the largest multisite retrospective stroke data collaboration to date. This article outlines the efforts taken by the ENIGMA Stroke Recovery working group to develop neuroinformatics protocols and methods to manage multisite stroke brain magnetic resonance imaging, behavioral and demographics data. Specifically, the processes for scalable data intake and preprocessing, multisite data harmonization, and large‐scale stroke lesion analysis are described, and challenges unique to this type of big data collaboration in stroke research are discussed. Finally, future directions and limitations, as well as recommendations for improved data harmonization through prospective data collection and data management, are provided. [ABSTRACT FROM AUTHOR]

Objective: The aim of this study was to examine the relationship between changes in liver fat and changes in insulin sensitivity and β-cell function 2 years after gastric banding surgery.Methods: Data included 23 adults with the surgery who had prediabetes or type 2 diabetes for less than 1 year and BMI 30 to 40 kg/m2 at baseline. Body adiposity measures including liver fat content (LFC), insulin sensitivity (M/I), and β-cell responses (acute, steady-state, and arginine-stimulated maximum C-peptide) were assessed at baseline and 2 years after surgery. Regression models were used to assess associations adjusted for age and sex.Results: Two years after surgery, all measures of body adiposity, LFC, fasting and 2-hour glucose, and hemoglobin A1c significantly decreased; M/I significantly increased; and β-cell responses adjusted for M/I did not change significantly. Among adiposity measures, reduction in LFC had the strongest association with M/I increase (r = -0.61, P = 0.003). Among β-cell measures, change in LFC was associated with change in acute C-peptide response to arginine at maximal glycemic potentiation adjusted for M/I (r = 0.66, P = 0.007). Significant reductions in glycemic measures and increase in M/I were observed in individuals with LFC loss >2.5%.Conclusions: Reduction in LFC after gastric banding surgery appears to be an important factor associated with long-term improvements in insulin sensitivity and glycemic profiles in adults with obesity and prediabetes or early type 2 diabetes. [ABSTRACT FROM AUTHOR]

Objectives: Using a radiomics framework to quantitatively analyze tumor shape and texture features in three dimensions, we tested its ability to objectively and robustly distinguish between benign and malignant renal masses. We assessed the relative contributions of shape and texture metrics separately and together in the prediction model.Materials and Methods: Computed tomography (CT) images of 735 patients with 539 malignant and 196 benign masses were segmented in this retrospective study. Thirty-three shape and 760 texture metrics were calculated per tumor. Tumor classification models using shape, texture, and both metrics were built using random forest and AdaBoost with tenfold cross-validation. Sensitivity analyses on five sub-cohorts with respect to the acquisition phase were conducted. Additional sensitivity analyses after multiple imputation were also conducted. Model performance was assessed using AUC.Results: Random forest classifier showed shape metrics featuring within the top 10% performing metrics regardless of phase, attaining the highest variable importance in the corticomedullary phase. Convex hull perimeter ratio is a consistently high-performing shape feature. Shape metrics alone achieved an AUC ranging 0.64-0.68 across multiple classifiers, compared with 0.67-0.75 and 0.68-0.75 achieved by texture-only and combined models, respectively.Conclusion: Shape metrics alone attain high prediction performance and high variable importance in the combined model, while being independent of the acquisition phase (unlike texture). Shape analysis therefore should not be overlooked in its potential to distinguish benign from malignant tumors, and future radiomics platforms powered by machine learning should harness both shape and texture metrics.Key Points: • Current radiomics research is heavily weighted towards texture analysis, but quantitative shape metrics should not be ignored in their potential to distinguish benign from malignant renal tumors. • Shape metrics alone can attain high prediction performance and demonstrate high variable importance in the combined shape and texture radiomics model. • Any future radiomics platform powered by machine learning should harness both shape and texture metrics, especially since tumor shape (unlike texture) is independent of the acquisition phase and more robust from the imaging variations. [ABSTRACT FROM AUTHOR]

Introduction: Youth with classical congenital adrenal hyperplasia (CAH) have higher prevalence of cardiometabolic risk factors such as obesity, abdominal adiposity, and hypertension. Patients with CAH also exhibit an earlier adiposity rebound (AR) compared to normative populations. However, the predictive relationship between AR and cardiometabolic risk factors needs to be better understood. Methods: We performed a retrospective cohort study at a US tertiary pediatric center in youth with classical CAH due to 21-hydroxylase deficiency. AR was determined by cubic polynomial modeling. A subset of participants had fasting analytes, whole-body dual-energy X-ray absorptiometry, and magnetic resonance imaging as adolescents. Results: In 42 youth with CAH (45.2% female, 54.8% Hispanic, and 90.5% salt-wasting form), the average age at AR was 3.4 ± 1.3 years. AR differed by BMI-z, with youth with obesity having an earlier AR (2.8 ± 1.0 years) compared to lean youth (4.1 ± 1.3 years, p = 0.001). However, AR did not differ by either CAH form or sex. Earlier AR predicted higher BMI-z at 7 and 12 years of age. In addition, earlier AR predicted increased central obesity (as measured by waist circumference, subcutaneous adipose tissue, and trunk fat) and total body fat in adolescence. AR was negatively correlated with bone age, and its relationships with HDL and hypertension were trending towards significance. Conclusions: AR in youth with classical CAH could serve as a useful clinical marker to identify those patients who are at higher risk for developing cardiometabolic risk factors during childhood and adolescence. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of the study was to evaluate the feasibility of using contrast-enhanced computed tomography (CECT)-based texture analysis (CTTA) metrics to differentiate between juxtatumoral perinephric fat (JPF) surrounding low-grade (ISUP 1–2) versus high-grade (ISUP 3–4) clear cell renal cell carcinoma (ccRCC). Methods: In this IRB-approved study, we retrospectively queried the surgical database between June 2009 and April 2016 and identified 83 patients with pathologically confirmed ccRCC (low grade: n = 54, mean age = 61.5 years, 18F/35M; high grade n = 30, mean age = 61.7 years, 8F/22M) who also had pre-operative multiphase CT acquisitions. CT images were transferred to a 3D workstation, and nephrographic phase JPF regions were manually segmented. Using an in-house developed Matlab program, a CTTA panel comprising of texture metrics extracted using six different methods, histogram, 2D- and 3D-Gray-level co-occurrence matrix (GLCM) and Gray-level difference matrix (GLDM), and 2D-Fast Fourier Transform (FFT) analyses, was applied to the segmented images to assess JPF textural heterogeneity in low- versus high-grade ccRCC. Univariate analysis and receiver-operator characteristics (ROC) analysis were used to assess interclass differences in texture metrics and their prediction accuracy, respectively. Results: All methods except GLCM consistently revealed increased heterogeneity in the JPF surrounding high- versus low-grade ccRCC. FFT showed increased complexity index (p < 0.01). Histogram analysis showed increased kurtosis and positive skewness in (p < 0.03), and GLDM analysis showed decreased measure of correlation coefficient (MCC) (p < 0.04). Several of the GLCM metrics showed statistically significant (p < 0.04) textural differences between the two groups, but with no consistent trend. ROC analysis showed that MCC in GLCM analysis had an area under the curve of 0.75. Conclusions: Our study suggests that CTTA of ccRCC shows statistically significant textural differences in JPF surrounding high- versus low-grade ccRCC. [ABSTRACT FROM AUTHOR]

When properly implemented and processed, anatomic T 1-weighted magnetic resonance imaging (MRI) can be ideal for the noninvasive quantification of white matter (WM) and gray matter (GM) in the living human brain. Although MRI is more suitable for distinguishing GM from WM than computed tomography (CT), the growing clinical use of the latter technique has renewed interest in head CT segmentation. Such interest is particularly strong in settings where MRI is unavailable, logistically unfeasible or prohibitively expensive. Nevertheless, whereas MRI segmentation is a sophisticated and technically-mature research field, the task of automatically classifying soft brain tissues from CT remains largely unexplored. Furthermore, brain segmentation methods for MRI hold considerable potential for adaptation and application to CT image processing. Here we demonstrate this by combining probabilistic, atlas-based classification with topologically-constrained tissue boundary refinement to delineate WM, GM and cerebrospinal fluid (CSF) from head CT images. The feasibility and utility of this approach are revealed by comparison of MRI-only vs. CT-only segmentations in geriatric concussion victims with both MRI and CT scans. Comparison of the two segmentations yields mean Sørensen-Dice coefficients of 85.5 ± 4.6% (WM), 86.7 ± 5.6% (GM) and 91.3 ± 2.8% (CSF), as well as average Hausdorff distances of 3.76 ± 1.85 mm (WM), 3.43 ± 1.53 mm (GM) and 2.46 ± 1.27 mm (CSF). Bootstrapping results suggest that the segmentation approach is sensitive enough to yield WM, GM and CSF volume estimates within ~5%, ~4%, and ~3% of their MRI-based estimates, respectively. To our knowledge, this is the first 3D segmentation approach for CT to undergo rigorous within-subject comparison with high-resolution MRI. Results suggest that (1) standard-quality CT allows WM/GM/CSF segmentation with reasonable accuracy, and that (2) the task of soft brain tissue classification from CT merits further attention from neuroimaging researchers. [ABSTRACT FROM AUTHOR]

We investigate the viability of statistical relational machine learning algorithms for the task of identifying malignancy of renal masses using radiomics-based imaging features. Features characterizing the texture, signal intensity, and other relevant metrics of the renal mass were extracted from multiphase contrast-enhanced computed tomography images. The recently developed formalism of relational functional gradient boosting (RFGB) was used to learn human-interpretable models for classification. Experimental results demonstrate that RFGB outperforms many standard machine learning approaches as well as the current diagnostic gold standard of visual qualification by radiologists. [ABSTRACT FROM AUTHOR]

Human pelvic floor muscles have been shown to operate synergistically with a wide variety of muscles, which has been suggested to be an important contributor to continence and pelvic stability during functional tasks. However, the neural mechanism of pelvic floor muscle synergies remains unknown. Here, we test the hypothesis that activation in motor cortical regions associated with pelvic floor activation are part of the neural substrate for such synergies. We first use electromyographic recordings to extend previous findings and demonstrate that pelvic floor muscles activate synergistically during voluntary activation of gluteal muscles, but not during voluntary activation of finger muscles. We then show, using functional magnetic resonance imaging (fMRI), that a region of the medial wall of the precentral gyrus consistently activates during both voluntary pelvic floor muscle activation and voluntary gluteal activation, but not during voluntary finger activation. We finally confirm, using transcranial magnetic stimulation, that the fMRI-identified medial wall region is likely to generate pelvic floor muscle activation. Thus, muscle synergies of the human male pelvic floor appear to involve activation of motor cortical areas associated with pelvic floor control. [ABSTRACT FROM AUTHOR]

The quantitative, multiparametric assessment of brain lesions requires coregistering different parameters derived from MRI sequences. This will be followed by analysis of the voxel values of the ROI within the sequences and calculated parametric maps, and deriving multiparametric models to classify imaging data. There is a need for an intuitive, automated quantitative processing framework that is generalized and adaptable to different clinical and research questions. As such flexible frameworks have not been previously described, we proceeded to construct a quantitative post-processing framework with commonly available software components. Matlab was chosen as the programming/integration environment, and SPM was chosen as the coregistration component. Matlab routines were created to extract and concatenate the coregistration transforms, take the coregistered MRI sequences as inputs to the process, allow specification of the ROI, and store the voxel values to the database for statistical analysis. The functionality of the framework was validated using brain tumor MRI cases. The implementation of this quantitative post-processing framework enables intuitive creation of multiple parameters for each voxel, facilitating near real-time in-depth voxel-wise analysis. Our initial empirical evaluation of the framework is an increased usage of analysis requiring post-processing and increased number of simultaneous research activities by clinicians and researchers with non-technical backgrounds. We show that common software components can be utilized to implement an intuitive real-time quantitative post-processing framework, resulting in improved scalability and increased adoption of post-processing needed to answer important diagnostic questions. [ABSTRACT FROM AUTHOR]