Publications by Year: 2022

Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received significant interest for accelerating magnetic resonance imaging (MRI) acquisition and reconstruction strategies. A number of ideas inspired by deep learning techniques for computer vision and image processing have been successfully applied to nonlinear image reconstruction in the spirit of compressed sensing for accelerated MRI. Given the rapidly growing nature of the field, it is imperative to consolidate and summarize the large number of deep learning methods that have been reported in the literature, to obtain a better understanding of the field in general. This article provides an overview of the recent developments in neural-network based approaches that have been proposed specifically for improving parallel imaging. A general background and introduction to parallel MRI is also given from a classical view of k-space based reconstruction methods. Image domain based techniques that introduce improved regularizers are covered along with k-space based methods which focus on better interpolation strategies using neural networks. While the field is rapidly evolving with plenty of papers published each year, in this review, we attempt to cover broad categories of methods that have shown good performance on publicly available data sets. Limitations and open problems are also discussed and recent efforts for producing open data sets and benchmarks for the community are examined.

Background Stratifying high-risk histopathologic features in endometrial carcinoma is important for treatment planning. Radiomics analysis at preoperative MRI holds potential to identify high-risk phenotypes. Purpose To evaluate the performance of multiparametric MRI three-dimensional radiomics-based machine learning models for differentiating low- from high-risk histopathologic markers-deep myometrial invasion (MI), lymphovascular space invasion (LVSI), and high-grade status-and advanced-stage endometrial carcinoma. Materials and Methods This dual-center retrospective study included women with histologically proven endometrial carcinoma who underwent 1.5-T MRI before hysterectomy between January 2011 and July 2015. Exclusion criteria were tumor diameter less than 1 cm, missing MRI sequences or histopathology reports, neoadjuvant therapy, and malignant neoplasms other than endometrial carcinoma. Three-dimensional radiomics features were extracted after tumor segmentation at MRI (T2-weighted, diffusion-weighted, and dynamic contrast-enhanced MRI). Predictive features were selected in the training set with use of random forest (RF) models for each end point, and trained RF models were applied to the external test set. Five board-certified radiologists conducted MRI-based staging and deep MI assessment in the training set. Areas under the receiver operating characteristic curve (AUCs) were reported with balanced accuracies, and radiologists’ readings were compared with radiomics with use of McNemar tests. Results In total, 157 women were included: 94 at the first institution (training set; mean age, 66 years ± 11 [SD]) and 63 at the second institution (test set; 67 years ± 12). RF models dichotomizing deep MI, LVSI, high grade, and International Federation of Gynecology and Obstetrics (FIGO) stage led to AUCs of 0.81 (95% CI: 0.68, 0.88), 0.80 (95% CI: 0.67, 0.93), 0.74 (95% CI: 0.61, 0.86), and 0.84 (95% CI: 0.72, 0.92), respectively, in the test set. In the training set, radiomics provided increased performance compared with radiologists’ readings for identifying deep MI (balanced accuracy, 86% vs 79%; P = .03), while no evidence of a difference was observed in performance for advanced FIGO stage (80% vs 78%; P = .27). Conclusion Three-dimensional radiomics can stratify patients by using preoperative MRI according to high-risk histopathologic end points in endometrial carcinoma and provide nonsignificantly different or higher performance than radiologists in identifying advanced stage and deep myometrial invasion, respectively. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Kido and Nishio in this issue.

BACKGROUND: While adolescent-onset schizophrenia (ADO-SCZ) and adolescent-onset bipolar disorder with psychosis (psychotic ADO-BPD) present a more severe clinical course than their adult forms, their pathophysiology is poorly understood. Here, we study potentially state- and trait-related white matter diffusion-weighted magnetic resonance imaging (dMRI) abnormalities along the adolescent-onset psychosis continuum to address this need. METHODS: Forty-eight individuals with ADO-SCZ (20 female/28 male), 15 individuals with psychotic ADO-BPD (7 female/8 male), and 35 healthy controls (HCs, 18 female/17 male) underwent dMRI and clinical assessments. Maps of extracellular free-water (FW) and fractional anisotropy of cellular tissue (FAT) were compared between individuals with psychosis and HCs using tract-based spatial statistics and FSL’s Randomise. FAT and FW values were extracted, averaged across all voxels that demonstrated group differences, and then utilized to test for the influence of age, medication, age of onset, duration of illness, symptom severity, and intelligence. RESULTS: Individuals with adolescent-onset psychosis exhibited pronounced FW and FAT abnormalities compared to HCs. FAT reductions were spatially more widespread in ADO-SCZ. FW increases, however, were only present in psychotic ADO-BPD. In HCs, but not in individuals with adolescent-onset psychosis, FAT was positively related to age. CONCLUSIONS: We observe evidence for cellular (FAT) and extracellular (FW) white matter abnormalities in adolescent-onset psychosis. Although cellular white matter abnormalities were more prominent in ADO-SCZ, such alterations may reflect a shared trait, i.e. neurodevelopmental pathology, present across the psychosis spectrum. Extracellular abnormalities were evident in psychotic ADO-BPD, potentially indicating a more dynamic, state-dependent brain reaction to psychosis.

BACKGROUND: Alterations in the peripheral inflammatory profile and white matter (WM) deterioration are frequent in Major Depressive Disorder (MDD). The present study applies free-water imaging to investigate the relationship between altered peripheral inflammation and WM microstructure and their predictive value in determining response to ketamine treatment in MDD. METHODS: Ten individuals with MDD underwent diffusion-weighted magnetic resonance imaging and a blood-draw before and 24 h after ketamine infusion. We utilized MANCOVAs and ANCOVAs to compare tissue-specific fractional anisotropy (FAT) and free-water (FW) of the forceps and cingulum, and the ratio of pro-inflammatory interleukin(IL)-8/anti-inflammatory IL-10 between individuals with MDD and 15 healthy controls at baseline. Next, we compared all baseline measures between ketamine responders (6) and non-responders (4) and analyzed changes in imaging and blood data after ketamine infusion. RESULTS: The MDD group exhibited an increased IL-8/IL-10 ratio compared to controls at baseline (p = .040), which positively correlated with average FW across regions of interest (p = .013). Ketamine responders demonstrated higher baseline FAT in the left cingulum than non-responders (p = .023). Ketamine infusion did not influence WM microstructure but decreased the IL-8/IL-10 ratio (p = .043). LIMITATIONS: The small sample size and short follow-up period limit the conclusion regarding the longer-term effects of ketamine in MDD. CONCLUSIONS: This pilot study provides evidence for the role of inflammation in MDD by illustrating an association between peripheral inflammation and WM microstructure. Additionally, we demonstrate that free-water diffusion-weighted imaging might be a valuable tool to determine which individuals with MDD benefit from the anti-inflammatory mediated effects of ketamine treatment.

Proton MRI can provide detailed morphological images, but it reveals little information about cell homeostasis. On the other hand, sodium MRI can provide metabolic information but cannot resolve fine structures. The complementary nature of proton and sodium MRI raises the prospect of their combined use in a single experiment. In this work, we assessed the repeatability of normalized proton density (PD), T1, T2, and normalized sodium density-weighted quantification measured with simultaneous 3D 1H MRF/23Na MRI in the brain at 7 T, from ten healthy volunteers who were scanned three times each. The coefficients of variation (CV) and the intra-class correlation (ICC) were calculated for the mean and standard deviation (SD) of these 4 parameters in grey matter, white matter, and cerebrospinal fluid. As result, the CVs were lower than 3.3% for the mean values and lower than 6.9% for the SD values. The ICCs were higher than 0.61 in all 24 measurements. We conclude that the measurements of normalized PD, T1, T2, and normalized sodium density-weighted from simultaneous 3D 1H MRF/23Na MRI in the brain at 7 T showed high repeatability. We estimate that changes > 6.6% (> 2 CVs) in mean values of both 1H and 23Na metrics could be detectable with this method.

INTRODUCTION: The presentation, risk factors, and etiologies of white matter hyperintensities (WMH) in people exposed to repetitive head impacts are unknown. We examined the burden and distribution of WMH, and their association with years of play, age of first exposure, and clinical function in former American football players. METHODS: A total of 149 former football players and 53 asymptomatic unexposed participants (all men, 45-74 years) completed fluid-attenuated inversion recovery magnetic resonance imaging, neuropsychological testing, and self-report neuropsychiatric measures. Lesion Segmentation Toolbox estimated WMH. Analyses were performed in the total sample and stratified by age 60. RESULTS: In older but not younger participants, former football players had greater total, frontal, temporal, and parietal log-WMH compared to asymptomatic unexposed men. In older but not younger former football players, greater log-WMH was associated with younger age of first exposure to football and worse executive function. DISCUSSION: In older former football players, WMH may have unique presentations, risk factors, and etiologies. HIGHLIGHTS: Older but not younger former football players had greater total, frontal, temporal, and parietal lobe white matter hyperintensities (WMH) compared to same-age asymptomatic unexposed men. Younger age of first exposure to football was associated with greater WMH in older but not younger former American football players. In former football players, greater WMH was associated with worse executive function and verbal memory.

BACKGROUND: Radiomics, defined as quantitative features extracted from images, provide a non-invasive means of assessing malignant versus benign pulmonary nodules. In this study, we evaluate the consistency with which perinodular radiomics extracted from low-dose computed tomography images serve to identify malignant pulmonary nodules. MATERIALS AND METHODS: Using the National Lung Screening Trial (NLST), we selected individuals with pulmonary nodules between 4mm to 20mm in diameter. Nodules were segmented to generate four distinct datasets; 1) a Tumor dataset containing tumor-specific features, 2) a 10 mm Band dataset containing parenchymal features between the segmented nodule boundary and 10mm out from the boundary, 3) a 15mm Band dataset, and 4) a Tumor Size dataset containing the maximum nodule diameter. Models to predict malignancy were constructed using support-vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) approaches. Ten-fold cross validation with 10 repetitions per fold was used to evaluate the performance of each approach applied to each dataset. RESULTS: With respect to the RF, the Tumor, 10mm Band, and 15mm Band datasets achieved areas under the receiver-operator curve (AUC) of 84.44%, 84.09%, and 81.57%, respectively. Significant differences in performance were observed between the Tumor and 15mm Band datasets (adj. p-value <0.001). However, when combining tumor-specific features with perinodular features, the 10mm Band + Tumor and 15mm Band + Tumor datasets (AUC 87.87% and 86.75%, respectively) performed significantly better than the Tumor Size dataset (66.76%) or the Tumor dataset. Similarly, the AUCs from the SVM and LASSO were 84.71% and 88.91%, respectively, for the 10mm Band + Tumor. CONCLUSIONS: The combined 10mm Band + Tumor dataset improved the differentiation between benign and malignant lung nodules compared to the Tumor datasets across all methodologies. This demonstrates that parenchymal features capture novel diagnostic information beyond that present in the nodule itself. (data agreement: NLST-163).

Objectives: Disrupted auditory networks play an important role in the pathophysiology of psychosis, with abnormalities already observed in individuals at clinical high-risk for psychosis (CHR). Here, we examine structural and functional connectivity of an auditory network in CHR utilising state-of-the-art electroencephalography and diffusion imaging techniques.Methods: Twenty-six CHR subjects and 13 healthy controls (HC) underwent diffusion MRI and electroencephalography while performing an auditory task. We investigated structural connectivity, measured as fractional anisotropy in the Arcuate Fasciculus (AF), Cingulum Bundle, and Superior Longitudinal Fasciculus-II. Gamma-band lagged-phase synchronisation, a functional connectivity measure, was calculated between cortical regions connected by these tracts.Results: CHR subjects showed significantly higher structural connectivity in the right AF than HC (p < .001). Although non-significant, functional connectivity between cortical areas connected by the AF was lower in CHR than HC (p = .078). Structural and functional connectivity were correlated in HC (p = .056) but not in CHR (p = .29).Conclusions: We observe significant differences in structural connectivity of the AF, without a concomitant significant change in functional connectivity in CHR subjects. This may suggest that the CHR state is characterised by a decoupling of structural and functional connectivity, possibly due to abnormal white matter maturation.

Worldwide over 150 million women use oral contraceptives (OCs), which are the most prescribed form of contraception in both the United States and in European countries. Sex hormones, such as estradiol and progesterone, are important endogenous hormones known for shaping the brain across the life span. Synthetic hormones, which are present in OCs, interfere with the natural hormonal balance by reducing the endogenous hormone levels. Little is known how this affects the brain, especially during the most vulnerable times of brain maturation. Here, we review studies that investigate differences in brain gray and white matter in women using OCs in comparison to naturally cycling women. We focus on two neuroimaging methods used to quantify structural gray and white matter changes, namely structural MRI and diffusion MRI. Finally, we discuss the potential of these imaging techniques to advance knowledge about the effects of OCs on the brain and wellbeing in women.

Cognitive deficits are among the best predictors of real-world functioning in schizophrenia. However, our understanding of how cognitive deficits relate to neuropathology and clinical presentation over the disease lifespan is limited. Here, we combine multi-site, harmonized cognitive, imaging, demographic, and clinical data from over 900 individuals to characterize a) cognitive deficits across the schizophrenia lifespan and b) the association between cognitive deficits, clinical presentation, and white matter (WM) microstructure. Multimodal harmonization was accomplished using T-scores for cognitive data, previously reported standardization methods for demographic and clinical data, and an established harmonization method for imaging data. We applied t-tests and correlation analysis to describe cognitive deficits in individuals with schizophrenia. We then calculated whole-brain WM fractional anisotropy (FA) and utilized regression-mediation analyses to model the association between diagnosis, FA, and cognitive deficits. We observed pronounced cognitive deficits in individuals with schizophrenia (p < 0.006), associated with more positive symptoms and medication dosage. Regression-mediation analyses showed that WM microstructure mediated the association between schizophrenia and language/processing speed/working memory/non-verbal memory. In addition, processing speed mediated the influence of diagnosis and WM microstructure on the other cognitive domains. Our study highlights the critical role of cognitive deficits in schizophrenia. We further show that WM is crucial when trying to understand the role of cognitive deficits, given that it explains the association between schizophrenia and cognitive deficits (directly and via processing speed).