Adverse radiation effect versus tumor progression following stereotactic radiosurgery for brain metastases: Implications of radiologic uncertainty.

BACKGROUND: Adverse radiation effect (ARE) following stereotactic radiosurgery (SRS) for brain metastases is challenging to distinguish from tumor progression. This study characterizes the clinical implications of radiologic uncertainty (RU). METHODS: Cases reviewed retrospectively at a single-institutional, multi-disciplinary SRS Tumor Board between 2015-2022 for RU following SRS were identified. Treatment history, diagnostic or therapeutic interventions performed upon RU resolution, and development of neurologic deficits surrounding intervention were obtained from the medical record. Differences in lesion volume and maximum diameter at RU onset versus resolution were compared with paired t-tests. Median time from RU onset to resolution was estimated using the Kaplan-Meier method. Univariate and multivariate associations between clinical characteristics and time to RU resolution were assessed with Cox proportional-hazards regression. RESULTS: Among 128 lesions with RU, 23.5% had undergone ≥ 2 courses of radiation. Median maximum diameter (20 vs. 16 mm, p < 0.001) and volume (2.7 vs. 1.5 cc, p < 0.001) were larger upon RU resolution versus onset. RU resolution took > 6 and > 12 months in 25% and 7% of cases, respectively. Higher total EQD2 prior to RU onset (HR = 0.45, p = 0.03) and use of MR perfusion (HR = 0.56, p = 0.001) correlated with shorter time to resolution; larger volume (HR = 1.05, p = 0.006) portended longer time to resolution. Most lesions (57%) were diagnosed as ARE. Most patients (58%) underwent an intervention upon RU resolution; of these, 38% developed a neurologic deficit surrounding intervention. CONCLUSIONS: RU resolution took > 6 months in > 25% of cases. RU may lead to suboptimal outcomes and symptom burden. Improved characterization of post-SRS RU is needed.

Strategies to Improve Drug Delivery Across the Blood-Brain Barrier for Glioblastoma.

PURPOSE OF REVIEW: Glioblastoma remains resistant to most conventional treatments. Despite scientific advances in the past three decades, there has been a dearth of effective new treatments. New approaches to drug delivery and clinical trial design are needed. RECENT FINDINGS: We discuss how the blood-brain barrier and tumor microenvironment pose challenges for development of effective therapies for glioblastoma. Next, we discuss treatments in development that aim to overcome these barriers, including novel drug designs such as nanoparticles and antibody-drug conjugates, novel methods of drug delivery, including convection-enhanced and intra-arterial delivery, and novel methods to enhance drug penetration, such as blood-brain barrier disruption by focused ultrasound and laser interstitial thermal therapy. Lastly, we address future opportunities, positing combination therapy as the best strategy for effective treatment, neoadjuvant and window-of-opportunity approaches to simultaneously enhance therapeutic effectiveness with interrogation of on-treatment biologic endpoints, and adaptive platform and basket trials as imperative for future trial design. New approaches to GBM treatment should account for the blood-brain barrier and immunosuppression by improving drug delivery, combining treatments, and integrating novel clinical trial designs.

Comparison of quantitative susceptibility mapping methods for iron-sensitive susceptibility imaging at 7T: An evaluation in healthy subjects and patients with Huntington's disease.

Quantitative susceptibility mapping (QSM) is a promising tool for investigating iron dysregulation in neurodegenerative diseases, including Huntington's disease (HD). Many diverse methods have been proposed to generate accurate and robust QSM images. In this study, we evaluated the performance of different dipole inversion algorithms for iron-sensitive susceptibility imaging at 7T on healthy subjects of a large age range and patients with HD. We compared an iterative least-squares-based method (iLSQR), iterative methods that use regularization, single-step approaches, and deep learning-based techniques. Their performance was evaluated by comparing: (1) deviations from a multiple-orientation QSM reference; (2) visual appearance of QSM maps and the presence of artifacts; (3) susceptibility in subcortical brain regions with age; (4) regional brain susceptibility with published postmortem brain iron quantification; and (5) susceptibility in HD-affected basal ganglia regions between HD subjects and healthy controls. We found that single-step QSM methods with either total variation or total generalized variation constraints (SSTV/SSTGV) and the single-step deep learning method iQSM generally provided the best performance in terms of correlation with iron deposition and were better at differentiating between healthy controls and premanifest HD individuals, while deep learning QSM methods trained with multiple-orientation susceptibility data created QSM maps that were most similar to the multiple orientation reference and with the best visual scores.

Hyperpolarized [2-13C]pyruvate MR molecular imaging with whole brain coverage.

Hyperpolarized (HP) 13C Magnetic Resonance Imaging (MRI) was applied for the first time to image and quantify the uptake and metabolism of [2-13C]pyruvate in the human brain to provide new metabolic information on cerebral energy metabolism. HP [2-13C]pyruvate was injected intravenously and imaged in 5 healthy human volunteer exams with whole brain coverage in a 1-minute acquisition using a specialized spectral-spatial multi-slice echoplanar imaging (EPI) pulse sequence to acquire 13C-labeled volumetric and dynamic images of [2-13C]pyruvate and downstream metabolites [5-13C]glutamate and [2-13C]lactate. Metabolic ratios and apparent conversion rates of pyruvate-to-lactate (kPL) and pyruvate-to-glutamate (kPG) were quantified to investigate simultaneously glycolytic and oxidative metabolism in a single injection.

"De novo replication repair deficient glioblastoma, IDH-wildtype" is a distinct glioblastoma subtype in adults that may benefit from immune checkpoint blockade.

Glioblastoma is a clinically and molecularly heterogeneous disease, and new predictive biomarkers are needed to identify those patients most likely to respond to specific treatments. Through prospective genomic profiling of 459 consecutive primary treatment-naïve IDH-wildtype glioblastomas in adults, we identified a unique subgroup (2%, 9/459) defined by somatic hypermutation and DNA replication repair deficiency due to biallelic inactivation of a canonical mismatch repair gene. The deleterious mutations in mismatch repair genes were often present in the germline in the heterozygous state with somatic inactivation of the remaining allele, consistent with glioblastomas arising due to underlying Lynch syndrome. A subset of tumors had accompanying proofreading domain mutations in the DNA polymerase POLE and resultant "ultrahypermutation". The median age at diagnosis was 50 years (range 27-78), compared with 63 years for the other 450 patients with conventional glioblastoma (p < 0.01). All tumors had histologic features of the giant cell variant of glioblastoma. They lacked EGFR amplification, lacked combined trisomy of chromosome 7 plus monosomy of chromosome 10, and only rarely had TERT promoter mutation or CDKN2A homozygous deletion, which are hallmarks of conventional IDH-wildtype glioblastoma. Instead, they harbored frequent inactivating mutations in TP53, NF1, PTEN, ATRX, and SETD2 and recurrent activating mutations in PDGFRA. DNA methylation profiling revealed they did not align with known reference adult glioblastoma methylation classes, but instead had unique globally hypomethylated epigenomes and mostly classified as "Diffuse pediatric-type high grade glioma, RTK1 subtype, subclass A". Five patients were treated with immune checkpoint blockade, four of whom survived greater than 3 years. The median overall survival was 36.8 months, compared to 15.5 months for the other 450 patients (p < 0.001). We conclude that "De novo replication repair deficient glioblastoma, IDH-wildtype" represents a biologically distinct subtype in the adult population that may benefit from prospective identification and treatment with immune checkpoint blockade.

DeepSWI: Using Deep Learning to Enhance Susceptibility Contrast on T2*-Weighted MRI.

BACKGROUND: Although susceptibility-weighted imaging (SWI) is the gold standard for visualizing cerebral microbleeds (CMBs) in the brain, the required phase data are not always available clinically. Having a postprocessing tool for generating SWI contrast from T2*-weighted magnitude images is therefore advantageous. PURPOSE: To create synthetic SWI images from clinical T2*-weighted magnitude images using deep learning and evaluate the resulting images in terms of similarity to conventional SWI images and ability to detect radiation-associated CMBs. STUDY TYPE: Retrospective. POPULATION: A total of 145 adults (87 males/58 females; 43.9 years old) with radiation-associated CMBs were used to train (16,093 patches/121 patients), validate (484 patches/4 patients), and test (2420 patches/20 patients) our networks. FIELD STRENGTH/SEQUENCE: 3D T2*-weighted, gradient-echo acquired at 3 T. ASSESSMENT: Structural similarity index (SSIM), peak signal-to-noise-ratio (PSNR), normalized mean-squared-error (nMSE), CMB counts, and line profiles were compared among magnitude, original SWI, and synthetic SWI images. Three blinded raters (J.E.V.M., M.A.M., B.B. with 8-, 6-, and 4-years of experience, respectively) independently rated and classified test-set images. STATISTICAL TESTS: Kruskall-Wallis and Wilcoxon signed-rank tests were used to compare SSIM, PSNR, nMSE, and CMB counts among magnitude, original SWI, and predicted synthetic SWI images. Intraclass correlation assessed interrater variability. P values <0.005 were considered statistically significant. RESULTS: SSIM values of the predicted vs. original SWI (0.972, 0.995, 0.9864) were statistically significantly higher than that of the magnitude vs. original SWI (0.970, 0.994, 0.9861) for whole brain, vascular structures, and brain tissue regions, respectively; 67% (19/28) CMBs detected on original SWI images were also detected on the predicted SWI, whereas only 10 (36%) were detected on magnitude images. Overall image quality was similar between the synthetic and original SWI images, with less artifacts on the former. CONCLUSIONS: This study demonstrated that deep learning can increase the susceptibility contrast present in neurovasculature and CMBs on T2*-weighted magnitude images, without residual susceptibility-induced artifacts. This may be useful for more accurately estimating CMB burden from magnitude images alone. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Technology and Tool Development for BACPAC: Qualitative and Quantitative Analysis of Accelerated Lumbar Spine MRI with Deep-Learning Based Image Reconstruction at 3T.

OBJECTIVES: To evaluate whether combining fast acquisitions with deep-learning reconstruction can provide diagnostically useful images and quantitative assessment comparable to standard-of-care acquisitions for lumbar spine magnetic resonance imaging (MRI). METHODS: Eighteen patients were imaged with both standard protocol and fast protocol using reduced signal averages, each protocol including sagittal fat-suppressed T2-weighted, sagittal T1-weighted, and axial T2-weighted 2D fast spin-echo sequences. Fast-acquisition data was additionally reconstructed using vendor-supplied deep-learning reconstruction with three different noise reduction factors. For qualitative analysis, standard images as well as fast images with and without deep-learning reconstruction were graded by three radiologists on five different categories. For quantitative analysis, convolutional neural networks were applied to sagittal T1-weighted images to segment intervertebral discs and vertebral bodies, and disc heights and vertebral body volumes were derived. RESULTS: Based on noninferiority testing on qualitative scores, fast images without deep-learning reconstruction were inferior to standard images for most categories. However, deep-learning reconstruction improved the average scores, and noninferiority was observed over 24 out of 45 comparisons (all with sagittal T2-weighted images while 4/5 comparisons with sagittal T1-weighted and axial T2-weighted images). Interobserver variability increased with 50 and 75% noise reduction factors. Deep-learning reconstructed fast images with 50% and 75% noise reduction factors had comparable disc heights and vertebral body volumes to standard images (r2≥ 0.86 for disc heights and r2≥ 0.98 for vertebral body volumes). CONCLUSIONS: This study demonstrated that deep-learning-reconstructed fast-acquisition images have the potential to provide noninferior image quality and comparable quantitative assessment to standard clinical images.

Kinetic analysis of multi-resolution hyperpolarized 13 C human brain MRI to study cerebral metabolism.

PURPOSE: To investigate multi-resolution hyperpolarized (HP) 13 C pyruvate MRI for measuring kinetic conversion rates in the human brain. METHODS: HP [1-13 C]pyruvate MRI was acquired in 6 subjects with a multi-resolution EPI sequence at 7.5 × 7.5 mm2 resolution for pyruvate and 15 × 15 mm2 resolution for lactate and bicarbonate. With the same lactate data, 2 quantitative maps of pyruvate-to-lactate conversion (kPL ) maps were generated: 1 using 7.5 × 7.5 mm2 resolution pyruvate data and the other using synthetic 15 × 15 mm2 resolution pyruvate data to simulate a standard constant resolution acquisition. To examine local kPL values, 4 voxels were manually selected in each study representing brain tissue near arteries, brain tissue near veins, white matter, and gray matter. RESULTS: High resolution 7.5 × 7.5 mm2 pyruvate images increased the spatial delineation of brain structures and decreased partial volume effects compared to coarser resolution 15 × 15 mm2 pyruvate images. Voxels near arteries, veins and in white matter exhibited higher calculated kPL for multi-resolution images. CONCLUSION: Acquiring HP 13 C pyruvate metabolic data with a multi-resolution approach minimized partial volume effects from vascular pyruvate signals while maintaining the SNR of downstream metabolites. Higher resolution pyruvate images for kinetic fitting resulted in increased kinetic rate values, particularly around the superior sagittal sinus and cerebral arteries, by reducing extracellular pyruvate signal contributions from adjacent blood vessels. This HP 13 C study showed that acquiring pyruvate with finer resolution improved the quantification of kinetic rates throughout the human brain.

Imaging joint infections using D-methyl-11C-methionine PET/MRI: initial experience in humans.

PURPOSE: Non-invasive imaging is a key clinical tool for detection and treatment monitoring of infections. Existing clinical imaging techniques are frequently unable to distinguish infection from tumors or sterile inflammation. This challenge is well-illustrated by prosthetic joint infections that often complicate joint replacements. D-methyl-11C-methionine (D-11C-Met) is a new bacteria-specific PET radiotracer, based on an amino acid D-enantiomer, that is rapidly incorporated into the bacterial cell wall. In this manuscript, we describe the biodistribution, radiation dosimetry, and initial human experience using D-11C-Met in patients with suspected prosthetic joint infections. METHODS: 614.5 ± 100.2 MBq of D-11C-Met was synthesized using an automated in-loop radiosynthesis method and administered to six healthy volunteers and five patients with suspected prosthetic joint infection, who were studied by PET/MRI. Time-activity curves were used to calculate residence times for each source organ. Absorbed doses to each organ and body effective doses were calculated using OLINDA/EXM 1.1 with both ICRP 60 and ICRP 103 tissue weighting factors. SUVmax and SUVpeak were calculated for volumes of interest (VOIs) in joints with suspected infection, the unaffected contralateral joint, blood pool, and soft tissue background. A two-tissue compartment model was used for kinetic modeling. RESULTS: D-11C-Met was well tolerated in all subjects. The tracer showed clearance from both urinary (rapid) and hepatobiliary (slow) pathways as well as low effective doses. Moreover, minimal background was observed in both organs with resident micro-flora and target organs, such as the spine and musculoskeletal system. Additionally, D-11C-Met showed increased focal uptake in areas of suspected infection, demonstrated by a significantly higher SUVmax and SUVpeak calculated from VOIs of joints with suspected infections compared to the contralateral joints, blood pool, and background (P < 0.01). Furthermore, higher distribution volume and binding potential were observed in suspected infections compared to the unaffected joints. CONCLUSION: D-11C-Met has a favorable radiation profile, minimal background uptake, and fast urinary extraction. Furthermore, D-11C-Met showed increased uptake in areas of suspected infection, making this a promising approach. Validation in larger clinical trials with a rigorous gold standard is still required.

Brain herniation (encephalocele) into arachnoid granulations: prevalence and association with pulsatile tinnitus and idiopathic intracranial hypertension.

PURPOSE: Brain herniation into arachnoid granulations (BHAG) of the dural venous sinuses is a recently described finding of uncertain etiology. The purpose of this study was to investigate the prevalence of BHAG in a cohort of patients with pulsatile tinnitus (PT) and to clarify the physiologic and clinical implications of these lesions. METHODS: The imaging and charts of consecutive PT patients were retrospectively reviewed. All patients were examined with MRI including pre- and post-contrast T1- and T2-weighted sequences. Images were reviewed separately by three blinded neuroradiologists to identify the presence of BHAG. Their location, signal intensity, size, presence of arachnoid granulation, and associated dural venous sinus stenosis were documented. Clinical records were further reviewed for idiopathic intracranial hypertension, history of prior lumbar puncture, and opening pressure. RESULTS: Two hundred sixty-two consecutive PT patients over a 4-year period met inclusion criteria. PT patients with BHAG were significantly more likely to have idiopathic intracranial hypertension than PT patients without BHAG (OR 4.2, CI 1.5-12, p = 0.006). Sixteen out of 262 (6%) patients were found to have 18 BHAG. Eleven out of 16 (69%) patients had unilateral temporal or occipital lobe herniations located in the transverse sinus or the transverse-sigmoid junction. Three out of 16 (19%) patients had unilateral cerebellar herniations and 2/16 (13%) patients had bilateral BHAG. CONCLUSION: In patients with PT, BHAG is a prevalent MRI finding that is strongly associated with the clinical diagnosis of IIH. The pathogenesis of BHAG remains uncertain, but recognition should prompt comprehensive evaluation for IIH.

Simultaneous multi-slice spin- and gradient-echo dynamic susceptibility-contrast perfusion-weighted MRI of gliomas.

Although combined spin- and gradient-echo (SAGE) dynamic susceptibility-contrast (DSC) MRI can provide perfusion quantification that is sensitive to both macrovessels and microvessels while correcting for T1 -shortening effects, spatial coverage is often limited in order to maintain a high temporal resolution for DSC quantification. In this work, we combined a SAGE echo-planar imaging (EPI) sequence with simultaneous multi-slice (SMS) excitation and blipped controlled aliasing in parallel imaging (blipped CAIPI) at 3 T to achieve both high temporal resolution and whole brain coverage. Two protocols using this sequence with multi-band (MB) acceleration factors of 2 and 3 were evaluated in 20 patients with treated gliomas to determine the optimal scan parameters for clinical use. ΔR2 *(t) and ΔR2 (t) curves were derived to calculate dynamic signal-to-noise ratio (dSNR), ΔR2 *- and ΔR2 -based relative cerebral blood volume (rCBV), and mean vessel diameter (mVD) for each voxel. The resulting SAGE DSC images acquired using MB acceleration of 3 versus 2 appeared visually similar in terms of image distortion and contrast. The difference in the mean dSNR from normal-appearing white matter (NAWM) and that in the mean dSNR between NAWM and normal-appearing gray matter were not statistically significant between the two protocols. ΔR2 *- and ΔR2 -rCBV maps and mVD maps provided unique contrast and spatial heterogeneity within tumors.

A variable resolution approach for improved acquisition of hyperpolarized 13 C metabolic MRI.

PURPOSE: To ameliorate tradeoffs between a fixed spatial resolution and signal-to-noise ratio (SNR) for hyperpolarized 13 C MRI. METHODS: In MRI, SNR is proportional to voxel volume but retrospective downsampling or voxel averaging only improves SNR by the square root of voxel size. This can be exploited with a metabolite-selective imaging approach that independently encodes each compound, yielding high-resolution images for the injected substrate and coarser resolution images for downstream metabolites, while maintaining adequate SNR for each. To assess the efficacy of this approach, hyperpolarized [1-13 C]pyruvate data were acquired in healthy Sprague-Dawley rats (n = 4) and in two healthy human subjects. RESULTS: Compared with a constant resolution acquisition, variable-resolution data sets showed improved detectability of metabolites in pre-clinical renal studies with a 3.5-fold, 8.7-fold, and 6.0-fold increase in SNR for lactate, alanine, and bicarbonate data, respectively. Variable-resolution data sets from healthy human subjects showed cardiac structure and neuro-vasculature in the higher resolution pyruvate images (6.0 × 6.0 mm2 for cardiac and 7.5 × 7.5 mm2 for brain) that would otherwise be missed due to partial-volume effects and illustrates the level of detail that can be achieved with hyperpolarized substrates in a clinical setting. CONCLUSION: We developed a variable-resolution strategy for hyperpolarized 13 C MRI using metabolite-selective imaging and demonstrated that it mitigates tradeoffs between a fixed spatial resolution and SNR for hyperpolarized substrates, providing both high resolution pyruvate and coarse resolution metabolite data sets in a single exam. This technique shows promise to improve future studies by maximizing metabolite SNR while minimizing partial-volume effects from the injected substrate.

Pediatric bithalamic gliomas have a distinct epigenetic signature and frequent EGFR exon 20 insertions resulting in potential sensitivity to targeted kinase inhibition.

Brain tumors are the most common solid tumors of childhood, and the genetic drivers and optimal therapeutic strategies for many of the different subtypes remain unknown. Here, we identify that bithalamic gliomas harbor frequent mutations in the EGFR oncogene, only rare histone H3 mutation (in contrast to their unilateral counterparts), and a distinct genome-wide DNA methylation profile compared to all other glioma subtypes studied to date. These EGFR mutations are either small in-frame insertions within exon 20 (intracellular tyrosine kinase domain) or missense mutations within exon 7 (extracellular ligand-binding domain) that occur in the absence of accompanying gene amplification. We find these EGFR mutations are oncogenic in primary astrocyte models and confer sensitivity to specific tyrosine kinase inhibitors dependent on location within the kinase domain or extracellular domain. We initiated treatment with targeted kinase inhibitors in four children whose tumors harbor EGFR mutations with encouraging results. This study identifies a promising genomically-tailored therapeutic strategy for bithalamic gliomas, a lethal and genetically distinct brain tumor of childhood.

Treatment-induced lesions in newly diagnosed glioblastoma patients undergoing chemoradiotherapy and heat-shock protein vaccine therapy.

OBJECTIVES: Treatment-induced lesions represent a great challenge in neuro-oncology. The aims of this study were (i) to characterize treatment induced lesions in glioblastoma patients treated with chemoradiotherapy and heat-shock protein (HSP) vaccine and (ii) to evaluate the diagnostic accuracy of diffusion weighted imaging for differentiation between treatment-induced lesions and tumor progression. METHODS: Twenty-seven patients with newly diagnosed glioblastoma treated with HSP vaccine and chemoradiotherapy were included. Serial magnetic resonance imaging evaluation was performed to detect treatment-induced lesions and assess their growth. Quantitative analysis of the apparent diffusion coefficient (ADC) was performed to discriminate treatment-induced lesions from tumor progression. Mann-Whitney U-test and receiver operating characteristic (ROC) curves were used for analysis. RESULTS: Thirty-three percent of patients developed treatment-induced lesions. Five treatment-related lesions appeared between end of radiotherapy and the first vaccine administration; 4 lesions within the first 4 months from vaccine initiation and 1 at 3.5 years. Three patients with pathology proven treatment-induced lesions showed a biphasic growth pattern progressed shortly after. ADC ratio between the peripheral enhancing rim and central necrosis showed an accuracy of 0.84 (95% CI 0.63-1) for differentiation between progression and treatment-induced lesions. CONCLUSION: Our findings do not support the iRANO recommendation of a 6-month time window in which progressive disease should not be declared after immunotherapy initiation. A biphasic growth pattern of pathologically proven treatment-induced lesions was associated with a dismal prognosis. The presence of lower ADC values in the central necrotic portion of the lesions compared to the enhancing rim shows high specificity for detection of treatment-induced lesions.

Hyperpolarized 13C MRI: State of the Art and Future Directions.

Hyperpolarized (HP) carbon 13 (13C) MRI is an emerging molecular imaging method that allows rapid, noninvasive, and pathway-specific investigation of dynamic metabolic and physiologic processes that were previously inaccessible to imaging. This technique has enabled real-time in vivo investigations of metabolism that are central to a variety of diseases, including cancer, cardiovascular disease, and metabolic diseases of the liver and kidney. This review provides an overview of the methods of hyperpolarization and 13C probes investigated to date in preclinical models of disease. The article then discusses the progress that has been made in translating this technology for clinical investigation. In particular, the potential roles and emerging clinical applications of HP [1-13C]pyruvate MRI will be highlighted. The future directions to enable the adoption of this technology to advance the basic understanding of metabolism, to improve disease diagnosis, and to accelerate treatment assessment are also detailed.

Machine Learning in Neurooncology Imaging: From Study Request to Diagnosis and Treatment.

OBJECTIVE: Machine learning has potential to play a key role across a variety of medical imaging applications. This review seeks to elucidate the ways in which machine learning can aid and enhance diagnosis, treatment, and follow-up in neurooncology. CONCLUSION: Given the rapid pace of development in machine learning over the past several years, a basic proficiency of the key tenets and use cases in the field is critical to assessing potential opportunities and challenges of this exciting new technology.

Correction to: Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network.

This paper was published inadvertently as open access. It has been corrected online.

Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network.

Cerebral microbleeds, which are small focal hemorrhages in the brain that are prevalent in many diseases, are gaining increasing attention due to their potential as surrogate markers of disease burden, clinical outcomes, and delayed effects of therapy. Manual detection is laborious and automatic detection and labeling of these lesions is challenging using traditional algorithms. Inspired by recent successes of deep convolutional neural networks in computer vision, we developed a 3D deep residual network that can distinguish true microbleeds from false positive mimics of a previously developed technique based on traditional algorithms. A dataset of 73 patients with radiation-induced cerebral microbleeds scanned at 7 T with susceptibility-weighted imaging was used to train and evaluate our model. With the resulting network, we maintained 95% of the true microbleeds in 12 test patients and the average number of false positives was reduced by 89%, achieving a detection precision of 71.9%, higher than existing published methods. The likelihood score predicted by the network was also evaluated by comparing to a neuroradiologist's rating, and good correlation was observed.

MRI Features and IDH Mutational Status of Grade II Diffuse Gliomas: Impact on Diagnosis and Prognosis.

OBJECTIVE: Grade II diffuse gliomas (DGs) with isocitrate dehydrogenase (IDH) mutations are associated with better prognosis than their IDH wild-type counterparts. We sought to determine the MRI characteristics associated with IDH mutational status and ascertain whether MRI considered in combination with IDH mutational status can better predict the clinical outcomes of grade II DGs. MATERIALS AND METHODS: Preoperative MRI examinations were retrospectively studied for qualitative tumor characteristics, including location, extent, cortical involvement, margin sharpness, cystic component, mineralization or hemorrhage, and contrast enhancement. Quantitative diffusion and perfusion metrics were also assessed. Logistic regression and ROC analyses were used to evaluate the relationship between MRI features and IDH mutational status. The association between IDH mutational status, 1p19q codeletion, MRI features, extent of resection, and clinical outcomes was assessed by Kaplan-Meier and Cox proportional hazards models. RESULTS: Of 100 grade II DGs, 78 were IDH mutant and 22 were IDH wild type. IDH wild-type tumors were associated with older age, multifocality, brainstem involvement, lack of cystic change, and a lower apparent diffusion coefficient (ADC). Multivariable regression showed that age older than 45 years as well as low minimum ADC (ADCmin), mean ADC, and maximum ADC values were independently associated with IDH mutational status. Of these, an ADCmin threshold of 0.9 × 10-3 mm2/s or less provided the greatest sensitivity and specificity (91% and 76%, respectively) in defining IDH wild-type grade II DGs. Combining low ADCmin with IDH wild-type status conferred worse outcomes than did IDH wild-type status alone. CONCLUSION: IDH wild-type grade II DGs are associated with a lower ADC and poor clinical outcomes. Combining IDH mutational status and ADC may allow more accurate prediction of clinical outcomes for patients with grade II DGs.