Sexual Dimorphism of Radiomic Features in the Brain: An Exploratory Study Using 700 µm MP2RAGE MRI at 7 T.

OBJECTIVES: The aim of this study was to determine whether MRI radiomic features of key cerebral structures differ between women and men, and whether detection of such differences depends on the image resolution. MATERIALS AND METHODS: Ultrahigh resolution (UHR) 3D MP2RAGE (magnetization-prepared 2 rapid acquisition gradient echo) T1-weighted MR images (voxel size, 0.7 × 0.7 × 0.7 mm3) of the brain of 30 subjects (18 women and 12 men; mean age, 39.0 ± 14.8 years) without abnormal findings on MRI were retrospectively included. MRI was performed on a whole-body 7 T MR system. A convolutional neural network was used to segment the following structures: frontal cortex, frontal white matter, thalamus, putamen, globus pallidus, caudate nucleus, and corpus callosum. Eighty-seven radiomic features were extracted respectively: gray-level histogram (n = 18), co-occurrence matrix (n = 24), run-length matrix (n = 16), size-zone matrix (n = 16), and dependence matrix (n = 13). Feature extraction was performed at UHR and, additionally, also after resampling to 1.4 × 1.4 × 1.4 mm3 voxel size (standard clinical resolution). Principal components (PCs) of radiomic features were calculated, and independent samples t tests with Cohen d as effect size measure were used to assess differences in PCs between women and men for the different cerebral structures. RESULTS: At UHR, at least a single PC differed significantly between women and men in 6/7 cerebral structures: frontal cortex (d = -0.79, P = 0.042 and d = -1.01, P = 0.010), frontal white matter (d = -0.81, P = 0.039), thalamus (d = 1.43, P < 0.001), globus pallidus (d = 0.92, P = 0.020), caudate nucleus (d = -0.83, P = 0.039), and corpus callosum (d = -0.97, P = 0.039). At standard clinical resolution, only a single PC extracted from the corpus callosum differed between sexes (d = 1.05, P = 0.009). CONCLUSIONS: Nonnegligible differences in radiomic features of several key structures of the brain exist between women and men, and need to be accounted for. Very high spatial resolution may be required to uncover and further investigate the sexual dimorphism of brain structures on MRI.

Comparison of Dentatorubrothalamic Tractography Methods Based on the Anatomy of the Rubral Wing.

BACKGROUND AND OBJECTIVES: Precise localization of the dentatorubrothalamic (DRT) tract can facilitate anatomic targeting in MRI-guided high-intensity focused ultrasound (HIFU) thalamotomy and thalamic deep brain stimulation for tremor. The anatomic segment of DRT fibers adjacent to the ventral intermediate nucleus of the thalamus (VIM), referred to as the rubral wing (RW), may be directly visualized on the fast gray matter acquisition T1 inversion recovery. We compared reproducibility, lesion overlap, and clinical outcomes when reconstructing the DRT tract using a novel anatomically defined RW region of interest, DRT-RW, to an existing tractography method based on the posterior subthalamic area region of interest (DRT-PSA). METHODS: We reviewed data of 23 patients with either essential tremor (n = 18) or tremor-predominant Parkinson's disease (n = 5) who underwent HIFU thalamotomy, targeting the VIM. DRT tractography, ipsilateral to the lesion, was created based on either DRT-PSA or DRT-RW. Volume sections of each tract were created and dice similarity coefficients were used to measure spatial overlap between the 2 tractographies. Post-HIFU lesion size and location (on postoperative T2 MRI) was correlated with tremor outcomes and side effects for both DRT tractography methods and the RW itself. RESULTS: DRT-PSA passed through the RW and DRT-RW intersected with the ROIs of the DRT-PSA in all 23 cases. A higher percentage of the RW was ablated in patients who achieved tremor control (18.9%, 95% CI 15.1, 22.7) vs those without tremor relief (6.7%, 95% CI% 0, 22.4, P = .017). In patients with tremor control 6 months postoperatively (n = 12), those with side effects (n = 6) had larger percentages of their tracts ablated in comparison with those without side effects in both DRT-PSA (44.8, 95% CI 31.8, 57.8 vs 24.2%, 95% CI 12.4, 36.1, P = .025) and DRT-RW (35.4%, 95% CI 21.5, 49.3 vs 21.7%, 95% CI 12.7, 30.8, P = .030). CONCLUSION: Tractography of the DRT could be reconstructed by direct anatomic visualization of the RW on fast gray matter acquisition T1 inversion recovery-MRI. Anatomic planning is expected to be quicker, more reproducible, and less operator-dependent.

Unconstrained quantitative magnetization transfer imaging: disentangling T1 of the free and semi-solid spin pools.

Since the inception of magnetization transfer (MT) imaging, it has been widely assumed that Henkelman's two spin pools have similar longitudinal relaxation times, which motivated many researchers to constrain them to each other. However, several recent publications reported a T1s of the semi-solid spin pool that is much shorter than T1f of the free pool. While these studies tailored experiments for robust proofs-of-concept, we here aim to quantify the disentangled relaxation processes on a voxel-by-voxel basis in a clinical imaging setting, i.e., with an effective resolution of 1.24mm isotropic and full brain coverage in 12min. To this end, we optimized a hybrid-state pulse sequence for mapping the parameters of an unconstrained MT model. We scanned four people with relapsing-remitting multiple sclerosis (MS) and four healthy controls with this pulse sequence and estimated T1f≈1.84s and T1s≈0.34s in healthy white matter. Our results confirm the reports that T1s≪T1f and we argue that this finding identifies MT as an inherent driver of longitudinal relaxation in brain tissue. Moreover, we estimated a fractional size of the semi-solid spin pool of m0s≈0.212, which is larger than previously assumed. An analysis of T1f in normal-appearing white matter revealed statistically significant differences between individuals with MS and controls.

Rapid quantitative magnetization transfer imaging: Utilizing the hybrid state and the generalized Bloch model.

PURPOSE: To explore efficient encoding schemes for quantitative magnetization transfer (qMT) imaging with few constraints on model parameters. THEORY AND METHODS: We combine two recently proposed models in a Bloch-McConnell equation: the dynamics of the free spin pool are confined to the hybrid state, and the dynamics of the semi-solid spin pool are described by the generalized Bloch model. We numerically optimize the flip angles and durations of a train of radio frequency pulses to enhance the encoding of three qMT parameters while accounting for all eight parameters of the two-pool model. We sparsely sample each time frame along this spin dynamics with a three-dimensional radial koosh-ball trajectory, reconstruct the data with subspace modeling, and fit the qMT model with a neural network for computational efficiency. RESULTS: We extracted qMT parameter maps of the whole brain with an effective resolution of 1.24 mm from a 12.6-min scan. In lesions of multiple sclerosis subjects, we observe a decreased size of the semi-solid spin pool and longer relaxation times, consistent with previous reports. CONCLUSION: The encoding power of the hybrid state, combined with regularized image reconstruction, and the accuracy of the generalized Bloch model provide an excellent basis for efficient quantitative magnetization transfer imaging with few constraints on model parameters.

Improved reconstruction of crossing fibers in the mouse optic pathways with orientation distribution function fingerprinting.

PURPOSE: The accuracy of diffusion MRI tractography reconstruction decreases in the white matter regions with crossing fibers. The optic pathways in rodents provide a challenging structure to test new diffusion tractography approaches because of the small crossing volume within the optic chiasm and the unbalanced 9:1 proportion between the contra- and ipsilateral neural projections from the retina to the lateral geniculate nucleus, respectively. METHODS: Common approaches based on Orientation Distribution Function (ODF) peak finding or statistical inference were compared qualitatively and quantitatively to ODF Fingerprinting (ODF-FP) for reconstruction of crossing fibers within the optic chiasm using in vivo diffusion MRI ( n = 18 $$ n=18 $$ healthy C57BL/6 mice). Manganese-Enhanced MRI (MEMRI) was obtained after intravitreal injection of manganese chloride and used as a reference standard for the optic pathway anatomy. RESULTS: ODF-FP outperformed by over 100% all the tested methods in terms of the ratios between the contra- and ipsilateral segments of the reconstructed optic pathways as well as the spatial overlap between tractography and MEMRI. CONCLUSION: In this challenging model system, ODF-Fingerprinting reduced uncertainty of diffusion tractography for complex structural formations of fiber bundles.

Mapping tissue microstructure of brain white matter in vivo in health and disease using diffusion MRI.

Diffusion magnetic resonance imaging offers unique in vivo sensitivity to tissue microstructure in brain white matter, which undergoes significant changes during development and is compromised in virtually every neurological disorder. Yet, the challenge is to develop biomarkers that are specific to micrometer-scale cellular features in a human MRI scan of a few minutes. Here we quantify the sensitivity and specificity of a multicompartment diffusion modeling framework to the density, orientation and integrity of axons. We demonstrate that using a machine learning based estimator, our biophysical model captures the morphological changes of axons in early development, acute ischemia and multiple sclerosis (total N=821). The methodology of microstructure mapping is widely applicable in clinical settings and in large imaging consortium data to study development, aging and pathology.

Tractography passes the test: Results from the diffusion-simulated connectivity (disco) challenge.

Estimating structural connectivity from diffusion-weighted magnetic resonance imaging is a challenging task, partly due to the presence of false-positive connections and the misestimation of connection weights. Building on previous efforts, the MICCAI-CDMRI Diffusion-Simulated Connectivity (DiSCo) challenge was carried out to evaluate state-of-the-art connectivity methods using novel large-scale numerical phantoms. The diffusion signal for the phantoms was obtained from Monte Carlo simulations. The results of the challenge suggest that methods selected by the 14 teams participating in the challenge can provide high correlations between estimated and ground-truth connectivity weights, in complex numerical environments. Additionally, the methods used by the participating teams were able to accurately identify the binary connectivity of the numerical dataset. However, specific false positive and false negative connections were consistently estimated across all methods. Although the challenge dataset doesn't capture the complexity of a real brain, it provided unique data with known macrostructure and microstructure ground-truth properties to facilitate the development of connectivity estimation methods.

Surgical cytoreduction of deep-seated high-grade glioma through tubular retractor.

OBJECTIVE: Maximal safe resection is the goal of surgical treatment for high-grade glioma (HGG). Deep-seated hemispheric gliomas present a surgical challenge due to safety concerns and previously were often considered inoperable. The authors hypothesized that use of tubular retractors would allow resection of deep-seated gliomas with an acceptable safety profile. The purpose of this study was to describe surgical outcomes and survival data after resection of deep-seated HGG with stereotactically placed tubular retractors, as well as to discuss the technical advances that enable such procedures. METHODS: This is a retrospective review of 20 consecutive patients who underwent 22 resections of deep-seated hemispheric HGG with the Viewsite Brain Access System by a single surgeon. Patient demographics, survival, tumor characteristics, extent of resection (EOR), and neurological outcomes were recorded. Cannulation trajectories and planned resection volumes depended on the relative location of white matter tracts extracted from diffusion tractography. The surgical plans were designed on the Brainlab system and preoperatively visualized on the Surgical Theater virtual reality SNAP platform. Volumetric assessment of EOR was obtained on the Brainlab platform and confirmed by a board-certified neuroradiologist. RESULTS: Twenty adult patients (18 with IDH-wild-type glioblastomas and 2 with IDH-mutant grade IV astrocytomas) and 22 surgeries were included in the study. The cohort included both newly diagnosed (n = 17; 77%) and recurrent (n = 5; 23%) tumors. Most tumors (64%) abutted the ventricular system. The average preoperative and postoperative tumor volumes measured 33.1 ± 5.3 cm3 and 15.2 ± 5.1 cm3, respectively. The median EOR was 93%. Surgical complications included 2 patients (10%) who developed entrapment of the temporal horn, necessitating placement of a ventriculoperitoneal shunt; 1 patient (5%) who suffered a wound infection and pulmonary embolus; and 1 patient (5%) who developed pneumonia. In 2 cases (9%) patients developed new permanent visual field deficits, and in 5 cases (23%) patients experienced worsening of preoperative deficits. Preoperative neurological or cognitive deficits remained the same in 9 cases (41%) and improved in 7 (32%). The median overall survival was 14.4 months in all patients (n = 20) and in the newly diagnosed IDH-wild-type glioblastoma group (n = 16). CONCLUSIONS: Deep-seated HGGs, which are surgically challenging and frequently considered inoperable, are amenable to resection through tubular retractors, with an acceptable safety profile. Such cytoreductive surgery may allow these patients to experience an overall survival comparable to those with more superficial tumors.

MRI-Visible Anatomy of the Basal Ganglia and Thalamus.

Conventional MR imaging does not discriminate basal ganglia and thalamic internal anatomy well. Radiology reports describe anatomic locations but not specific functional structures. Functional neurosurgery uses indirect targeting based on commissural coordinates or atlases that do not fully account for individual variability. We describe innovative MR imaging sequences that improve the visualization of normal anatomy in this complex brain region and may increase our understanding of basal ganglia and thalamic function. Better visualization also may improve treatments for movement disorders and other emerging functional neurosurgery targets. We aim to provide an accessible review of the most clinically-relevant neuroanatomy within the thalamus and basal ganglia.

MRI-Visible Anatomy of the Brainstem.

Human brainstem internal anatomy is intricate, complex, and essential to normal brain function. The brainstem is affected by stroke, multiple sclerosis, and most neurodegenerative diseases-a 1-mm focus of pathologic condition can have profound clinical consequences. Unfortunately, detailed internal brainstem anatomy is difficult to see with conventional MRI sequences. We review normal brainstem anatomy visualized on widely available clinical 3-T MRI scanners using fast gray matter acquisition T1 inversion recovery, probabilistic diffusion tractography, neuromelanin, and susceptibility-weighted imaging. Better anatomic localization using these recent innovations improves our ability to diagnose, localize, and treat brainstem diseases. We aim to provide an accessible review of the most clinically relevant brainstem neuroanatomy.

Performance of orientation distribution function-fingerprinting with a biophysical multicompartment diffusion model.

PURPOSE: Orientation Distribution Function (ODF) peak finding methods typically fail to reconstruct fibers crossing at shallow angles below 40°, leading to errors in tractography. ODF-Fingerprinting (ODF-FP) with the biophysical multicompartment diffusion model allows for breaking this barrier. METHODS: A randomized mechanism to generate a multidimensional ODF-dictionary that covers biologically plausible ranges of intra- and extra-axonal diffusivities and fraction volumes is introduced. This enables ODF-FP to address the high variability of brain tissue. The performance of the proposed approach is evaluated on both numerical simulations and a reconstruction of major fascicles from high- and low-resolution in vivo diffusion images. RESULTS: ODF-FP with the suggested modifications correctly identifies fibers crossing at angles as shallow as 10 degrees in the simulated data. In vivo, our approach reaches 56% of true positives in determining fiber directions, resulting in visibly more accurate reconstruction of pyramidal tracts, arcuate fasciculus, and optic radiations than the state-of-the-art techniques. Moreover, the estimated diffusivity values and fraction volumes in corpus callosum conform with the values reported in the literature. CONCLUSION: The modified ODF-FP outperforms commonly used fiber reconstruction methods at shallow angles, which improves deterministic tractography outcomes of major fascicles. In addition, the proposed approach allows for linearization of the microstructure parameters fitting problem.

mTOR Inhibition with Sirolimus in Multiple System Atrophy: A Randomized, Double-Blind, Placebo-Controlled Futility Trial and 1-Year Biomarker Longitudinal Analysis.

BACKGROUND: Multiple system atrophy (MSA) is a fatal neurodegenerative disease characterized by the aggregation of α-synuclein in glia and neurons. Sirolimus (rapamycin) is an mTOR inhibitor that promotes α-synuclein autophagy and reduces its associated neurotoxicity in preclinical models. OBJECTIVE: To investigate the efficacy and safety of sirolimus in patients with MSA using a futility design. We also analyzed 1-year biomarker trajectories in the trial participants. METHODS: Randomized, double-blind, parallel group, placebo-controlled clinical trial at the New York University of patients with probable MSA randomly assigned (3:1) to sirolimus (2-6 mg daily) for 48 weeks or placebo. Primary endpoint was change in the Unified MSA Rating Scale (UMSARS) total score from baseline to 48 weeks. (ClinicalTrials.gov NCT03589976). RESULTS: The trial was stopped after a pre-planned interim analysis met futility criteria. Between August 15, 2018 and November 15, 2020, 54 participants were screened, and 47 enrolled and randomly assigned (35 sirolimus, 12 placebo). Of those randomized, 34 were included in the intention-to-treat analysis. There was no difference in change from baseline to week 48 between the sirolimus and placebo in UMSARS total score (mean difference, 2.66; 95% CI, -7.35-6.91; P = 0.648). There was no difference in UMSARS-1 and UMSARS-2 scores either. UMSARS scores changes were similar to those reported in natural history studies. Neuroimaging and blood biomarker results were similar in the sirolimus and placebo groups. Adverse events were more frequent with sirolimus. Analysis of 1-year biomarker trajectories in all participants showed that increases in blood neurofilament light chain (NfL) and reductions in whole brain volume correlated best with UMSARS progression. CONCLUSIONS: Sirolimus for 48 weeks was futile to slow the progression of MSA and had no effect on biomarkers compared to placebo. One-year change in blood NfL and whole brain atrophy are promising biomarkers of disease progression for future clinical trials. © 2022 International Parkinson and Movement Disorder Society.

Central Retinal Artery Visualization with Cone-Beam CT Angiography.

Background There are multiple tools available to visualize the retinal and choroidal vasculature of the posterior globe. However, there are currently no reliable in vivo imaging techniques that can visualize the entire retrobulbar course of the retinal and ciliary vessels. Purpose To identify and characterize the central retinal artery (CRA) using cone-beam CT (CBCT) images obtained as part of diagnostic cerebral angiography. Materials and Methods In this retrospective study, patients with catheter DSA performed between October 2019 and October 2020 were included if CBCT angiography included the orbit in the field of view. The CBCT angiography data sets were postprocessed with a small field-of-view volume centered in the posterior globe to a maximum resolution of 0.2 mm. The following were evaluated: CRA origin, CRA course, CRA point of penetration into the optic nerve sheath, bifurcation of the CRA at the papilla, visualization of anatomic variants, and visualization of the central retinal vein. Descriptive statistical analysis was performed. Results Twenty-one patients with 24 visualized orbits were included in the analysis (mean age, 55 years ± 15; 14 women). Indications for angiography were as follows: diagnostic angiography (n = 8), aneurysm treatment (n = 6), or other (n = 7). The CRA was identified in all orbits; the origin, course, point of penetration of the CRA into the optic nerve sheath, and termination in the papilla were visualized in all orbits. The average length of the intraneural segment was 10.6 mm (range, 7-18 mm). The central retinal vein was identified in six of 24 orbits. Conclusion Cone-beam CT, performed during diagnostic angiography, consistently demonstrated the in vivo central retinal artery, demonstrating excellent potential for multiple diagnostic and therapeutic applications. © RSNA, 2021 Online supplemental material is available for this article.

Stepwise Stochastic Dictionary Adaptation Improves Microstructure Reconstruction with Orientation Distribution Function Fingerprinting.

Fitting of the multicompartment biophysical model of white matter is an ill-posed optimization problem. One approach to make it computationally tractable is through Orientation Distribution Function (ODF) Fingerprinting. However, the accuracy of this method relies solely on ODF dictionary generation mechanisms which either sample the microstructure parameters on a multidimensional grid or draw them randomly with a uniform distribution. In this paper, we propose a stepwise stochastic adaptation mechanism to generate ODF dictionaries tailored specifically to the diffusion-weighted images in hand. The results we obtained on a diffusion phantom and in vivo human brain images show that our reconstructed diffusivities are less noisy and the separation of a free water fraction is more pronounced than for the prior (uniform) distribution of ODF dictionaries.

Nanostructure-specific X-ray tomography reveals myelin levels, integrity and axon orientations in mouse and human nervous tissue.

Myelin insulates neuronal axons and enables fast signal transmission, constituting a key component of brain development, aging and disease. Yet, myelin-specific imaging of macroscopic samples remains a challenge. Here, we exploit myelin's nanostructural periodicity, and use small-angle X-ray scattering tensor tomography (SAXS-TT) to simultaneously quantify myelin levels, nanostructural integrity and axon orientations in nervous tissue. Proof-of-principle is demonstrated in whole mouse brain, mouse spinal cord and human white and gray matter samples. Outcomes are validated by 2D/3D histology and compared to MRI measurements sensitive to myelin and axon orientations. Specificity to nanostructure is exemplified by concomitantly imaging different myelin types with distinct periodicities. Finally, we illustrate the method's sensitivity towards myelin-related diseases by quantifying myelin alterations in dysmyelinated mouse brain. This non-destructive, stain-free molecular imaging approach enables quantitative studies of myelination within and across samples during development, aging, disease and treatment, and is applicable to other ordered biomolecules or nanostructures.

Another 'BEE'? - Brain-Eye-Ear (BEE) Disease Secondary to HbSC Disease Masquerading as Multiple Sclerosis.

Recurrent episodes of neurological dysfunction and white matter lesions in a young adult raise suspicion for multiple sclerosis (MS). However, occlusive retinopathy, hearing loss and absence of CSF oligoclonal bands are atypical for MS and should make the clinician consider an alternative diagnosis. We describe a man with hearing loss, visual signs and symptoms, and an accumulating burden of brain lesions, who was treated for a clinical diagnosis of MS for nearly two decades. Genetic testing revealed a unifying diagnosis.

High resolution automated labeling of the hippocampus and amygdala using a 3D convolutional neural network trained on whole brain 700 µm isotropic 7T MP2RAGE MRI.

Image labeling using convolutional neural networks (CNNs) are a template-free alternative to traditional morphometric techniques. We trained a 3D deep CNN to label the hippocampus and amygdala on whole brain 700 µm isotropic 3D MP2RAGE MRI acquired at 7T. Manual labels of the hippocampus and amygdala were used to (i) train the predictive model and (ii) evaluate performance of the model when applied to new scans. Healthy controls and individuals with epilepsy were included in our analyses. Twenty-one healthy controls and sixteen individuals with epilepsy were included in the study. We utilized the recently developed DeepMedic software to train a CNN to label the hippocampus and amygdala based on manual labels. Performance was evaluated by measuring the dice similarity coefficient (DSC) between CNN-based and manual labels. A leave-one-out cross validation scheme was used. CNN-based and manual volume estimates were compared for the left and right hippocampus and amygdala in healthy controls and epilepsy cases. The CNN-based technique successfully labeled the hippocampus and amygdala in all cases. Mean DSC = 0.88 ± 0.03 for the hippocampus and 0.8 ± 0.06 for the amygdala. CNN-based labeling was independent of epilepsy diagnosis in our sample (p = .91). CNN-based volume estimates were highly correlated with manual volume estimates in epilepsy cases and controls. CNNs can label the hippocampus and amygdala on native sub-mm resolution MP2RAGE 7T MRI. Our findings suggest deep learning techniques can advance development of morphometric analysis techniques for high field strength, high spatial resolution brain MRI.

Improved Task-based Functional MRI Language Mapping in Patients with Brain Tumors through Marchenko-Pastur Principal Component Analysis Denoising.

Background Functional MRI improves preoperative planning in patients with brain tumors, but task-correlated signal intensity changes are only 2%-3% above baseline. This makes accurate functional mapping challenging. Marchenko-Pastur principal component analysis (MP-PCA) provides a novel strategy to separate functional MRI signal from noise without requiring user input or prior data representation. Purpose To determine whether MP-PCA denoising improves activation magnitude for task-based functional MRI language mapping in patients with brain tumors. Materials and Methods In this Health Insurance Portability and Accountability Act-compliant study, MP-PCA performance was first evaluated by using simulated functional MRI data with a known ground truth. Right-handed, left-language-dominant patients with brain tumors who successfully performed verb generation, sentence completion, and finger tapping functional MRI tasks were retrospectively identified between January 2017 and August 2018. On the group level, for each task, histograms of z scores for original and MP-PCA denoised data were extracted from relevant regions and contralateral homologs were seeded by a neuroradiologist blinded to functional MRI findings. Z scores were compared with paired two-sided t tests, and distributions were compared with effect size measurements and the Kolmogorov-Smirnov test. The number of voxels with a z score greater than 3 was used to measure task sensitivity relative to task duration. Results Twenty-three patients (mean age ± standard deviation, 43 years ± 18; 13 women) were evaluated. MP-PCA denoising led to a higher median z score of task-based functional MRI voxel activation in left hemisphere cortical regions for verb generation (from 3.8 ± 1.0 to 4.5 ± 1.4; P < .001), sentence completion (from 3.7 ± 1.0 to 4.3 ± 1.4; P < .001), and finger tapping (from 6.9 ± 2.4 to 7.9 ± 2.9; P < .001). Median z scores did not improve in contralateral homolog regions for verb generation (from -2.7 ± 0.54 to -2.5 ± 0.40; P = .90), sentence completion (from -2.3 ± 0.21 to -2.4 ± 0.37; P = .39), or finger tapping (from -2.3 ± 1.20 to -2.7 ± 1.40; P = .07). Individual functional MRI task durations could be truncated by at least 40% after MP-PCA without degradation of clinically relevant correlations between functional cortex and functional MRI tasks. Conclusion Denoising with Marchenko-Pastur principal component analysis led to higher task correlations in relevant cortical regions during functional MRI language mapping in patients with brain tumors. © RSNA, 2020 Online supplemental material is available for this article.

Approximating anatomically-guided PET reconstruction in image space using a convolutional neural network.

In the last two decades, it has been shown that anatomically-guided PET reconstruction can lead to improved bias-noise characteristics in brain PET imaging. However, despite promising results in simulations and first studies, anatomically-guided PET reconstructions are not yet available for use in routine clinical because of several reasons. In light of this, we investigate whether the improvements of anatomically-guided PET reconstruction methods can be achieved entirely in the image domain with a convolutional neural network (CNN). An entirely image-based CNN post-reconstruction approach has the advantage that no access to PET raw data is needed and, moreover, that the prediction times of trained CNNs are extremely fast on state of the art GPUs which will substantially facilitate the evaluation, fine-tuning and application of anatomically-guided PET reconstruction in real-world clinical settings. In this work, we demonstrate that anatomically-guided PET reconstruction using the asymmetric Bowsher prior can be well-approximated by a purely shift-invariant convolutional neural network in image space allowing the generation of anatomically-guided PET images in almost real-time. We show that by applying dedicated data augmentation techniques in the training phase, in which 16 [18F]FDG and 10 [18F]PE2I data sets were used, lead to a CNN that is robust against the used PET tracer, the noise level of the input PET images and the input MRI contrast. A detailed analysis of our CNN in 36 [18F]FDG, 18 [18F]PE2I, and 7 [18F]FET test data sets demonstrates that the image quality of our trained CNN is very close to the one of the target reconstructions in terms of regional mean recovery and regional structural similarity.