Increasing discrepancy of MR imaging and CSF study in patients with leptomeningeal seeding from lung adenocarcinoma after targeted therapy using a tyrosine kinase inhibitor.

PURPOSE: To evaluate the correlation between contrast-enhanced (CE) MRI and cerebrospinal fluid (CSF) cytology for the evaluation of leptomeningeal metastasis (LM) on MRI after targeted therapy with tyrosine kinase inhibitors. METHODS: We retrospectively reviewed the data of nonsmall cell lung cancer patients registered with NCT03257124 from May 2017 to December 2018, with progressive disease despite targeted therapy. Twenty-nine patients whose MRI scans exhibited LM at the time of registration were enrolled. During the targeted therapy with osimertinib, MRI scans, and subsequent CSF examinations were performed in every 2 months. In total, 113 MRI scans and CSF cytology data after treatment were collected. For each CE MRI scan, LM positivity was evaluated on 3D T1-weighted image (T1WI) and 2D FLAIR. The correlation between MRI and CSF cytology results and the diagnostic performance of MRI with CSF cytology as a reference standard were evaluated. RESULTS: After treatment, MRI revealed positivity for LM in 81 and negativity in 32. CSF results were positive in 69 examinations and negative in 44. The diagnostic accuracy of CE 3D T1WI and 2D FLAIR was 0.52 and 0.46, respectively. After targeted therapy, discrepancy in the CSF and MRI results tended to increase over time. The proportions of concordant MRI and CSF cytology results after targeted therapy were 66%, 58%, 62%, and 47% at the first, second, third, and fourth follow-up, respectively. CONCLUSION: The discrepancy of MRI in evaluation of LM and CSF cytology increases over time after targeted therapy with osimertinib. LM positivity on MRI could be a surrogate imaging marker in the pre- and immediate posttargeted-treatment with Osimertinib but not after sessions of osimertinib.

Detecting Low-Variant Allele Frequency Mosaic Pathogenic Variants of NF1, TSC2, and AKT3 Genes from Blood in Patients with Neurodevelopmental Disorders.

Growing evidence indicates that early and late postzygotic mosaicism can cause neurodevelopmental disorders (NDDs), but detection of low variant allele frequency (VAF) mosaic variants from blood remains a challenge. Data of 2162 patients with NDDs who underwent conventional genetic tests were reviewed and a deep sequencing was performed using a specifically designed mosaic next-generation sequencing (NGS) panel in the patients with negative genetic test results. Forty-four patents with neurocutaneous syndrome, malformation of cortical development, or nonlesional epileptic encephalopathies were included. In total, mosaic variants were detected from blood in 1.2% (25/2162) of the patients. Using conventional NGS panels, 22 mosaic variants (VAF, 8.8% to 29.8%) were identified in 18 different genes. Using a specifically designed mosaicism NGS panel, three mosaic variants of the NF1, TSC2, and AKT3 genes were identified (VAF, 2.0% to 11.2%). Mosaic variants were found frequently in the patients who had neurocutaneous syndrome (2/7, 28.6%), whereas only one or no mosaic variant was detected for patients who had malformations of cortical development (1/20, 5%) or nonlesional epileptic encephalopathies (0%, 0/17). In summary, mosaic variants that contribute to the spectrum of NDDs can be detected from blood via conventional NGS and specifically designed mosaicism NGS panels, and detection of mosaic variants using blood will increase diagnostic yield.

Vessel Wall Changes on Serial High-Resolution MRI and the Use of Cilostazol in Patients With Adult-Onset Moyamoya Disease.

BACKGROUND AND PURPOSE: The natural course of adult-onset moyamoya disease (MMD) is unknown, and there is no medical treatment that halts its progression. We hypothesized that progressive shrinkage of large intracranial arteries occurs in adult-onset MMD, and that cilostazol inhibits this process. METHODS: Serial high-resolution magnetic resonance imaging (HR-MRI) was performed on 66 patients with MMD: 30 patients received cilostazol, 21 received other antiplatelets, and 15 received no antiplatelets or had poor compliance to them. Serial HR-MRI was performed (interval between MRI scans: 29.67±18.02 months, mean±SD), and changes in outer diameter, luminal stenosis, and vascular enhancement were measured. Factors affecting HR-MRI changes were evaluated, including vascular risk factors and the ring finger protein 213 gene variant. RESULTS: The progression of stenosis to occlusion, recurrent ischemic stroke, and the development of new stenotic segments were observed in seven, seven, and three patients, respectively. Serial HR-MRI indicated that the degree of stenosis increased with negative remodeling (outer diameter shrinkage). Patients who received cilostazol presented significantly larger outer diameters and lower degrees of stenosis compared with other groups (p=0.005 and p=0.031, respectively). After adjusting for clinical and genetic factors, only cilostazol use was independently associated with negative remodeling (odds ratio=0.29, 95% confidence interval=0.10-0.84, p=0.023). While vascular enhancement was observed in most patients (61 patients), the progression of enhancement or the occurrence of new vascular enhancement was rarely observed on follow-up HR-MRI (6 and 1 patients, respectively). CONCLUSIONS: Adult-onset MMD induces progressive shrinkage of large intracranial arteries, which cilostazol treatment may prevent. Further randomized clinical trials are warranted. TRIAL REGISTRATION: ClinicalTrials.gov identifier NCT02074111.

High-Resolution Intracranial Vessel Wall MRI Findings Among Different Middle Cerebral Artery Territory Infarction Types.

OBJECTIVE: Intracranial atherosclerotic stroke occurs through various mechanisms, mainly by artery-to-artery embolism (AA) or branch occlusive disease (BOD). This study evaluated the spatial relationship between middle cerebral artery (MCA) plaques and perforating arteries among different MCA territory infarction types using vessel wall magnetic resonance imaging (VW-MRI). MATERIALS AND METHODS: We retrospectively enrolled patients with acute MCA infarction who underwent VW-MRI. Thirty-four patients were divided into three groups according to infarction pattern: 1) BOD, 2) both BOD and AA (BOD-AA), and 3) AA. To determine the factors related to BOD, the BOD and BOD-AA groups were combined into one group (with striatocapsular infarction [BOD+]) and compared with the AA group. To determine the factors related to AA, the BOD-AA and AA groups were combined into another group (with cortical infarction [AA+]) and compared with the BOD group. Plaque morphology and the spatial relationship between the perforating artery orifice and plaque were evaluated both quantitatively and qualitatively. RESULTS: The plaque margin in the BOD+ group was closer to the perforating artery orifice than that in the AA group (p = 0.011), with less enhancing plaque (p = 0.030). In the BOD group, plaques were mainly located on the dorsal (41.2%) and superior (41.2%) sides where the perforating arteries mainly arose. No patient in the AA group had overlapping plaques with perforating arteries at the cross-section where the perforator arose. Perforating arteries associated with culprit plaques were most frequently located in the middle two-thirds of the M1 segment (41.4%). The AA+ group had more stenosis (%) than the BOD group (39.73 ± 24.52 vs. 14.42 ± 20.96; p = 0.003). CONCLUSION: The spatial relationship between the perforating artery orifice and plaque varied among different types of MCA territory infarctions. In patients with BOD, the plaque margin was closer and blocked the perforating artery orifice, and stenosis degree and enhancement were less than those in patients with AA.

A Deep Learning Model with High Standalone Performance for Diagnosis of Unruptured Intracranial Aneurysm.

PURPOSE: This study aimed to investigate whether a deep learning model for automated detection of unruptured intracranial aneurysms on time-of-flight (TOF) magnetic resonance angiography (MRA) can achieve a target diagnostic performance comparable to that of human radiologists for approval from the Korean Ministry of Food and Drug Safety as an artificial intelligence-applied software. MATERIALS AND METHODS: In this single-center, retrospective, confirmatory clinical trial, the diagnostic performance of the model was evaluated in a predetermined test set. After sample size estimation, the test set consisted of 135 aneurysm-containing examinations with 168 intracranial aneurysms and 197 aneurysm-free examinations. The target sensitivity and specificity were set as 87% and 92%, respectively. The patient-wise sensitivity and specificity of the model were analyzed. Moreover, the lesion-wise sensitivity and false-positive detection rate per case were also investigated. RESULTS: The sensitivity and specificity of the model were 91.11% [95% confidence interval (CI): 84.99, 95.32] and 93.91% (95% CI: 89.60, 96.81), respectively, which met the target performance values. The lesion-wise sensitivity was 92.26%. The overall false-positive detection rate per case was 0.123. Of the 168 aneurysms, 13 aneurysms from 12 examinations were missed by the model. CONCLUSION: The present deep learning model for automated detection of unruptured intracranial aneurysms on TOF MRA achieved the target diagnostic performance comparable to that of human radiologists. With high standalone performance, this model may be useful for accurate and efficient diagnosis of intracranial aneurysm.

Eif2b3 mutants recapitulate phenotypes of vanishing white matter disease and validate novel disease alleles in zebrafish.

Leukodystrophy with vanishing white matter (VWM), also called Childhood Ataxia with Central Nervous System Hypomyelination, is caused by mutations in the subunits of the eukaryotic translation initiation factor, EIF2B1, EIF2B2, EIF2B3, EIF2B4 or EIF2B5. However, little is known regarding the underlying pathogenetic mechanisms, and there is no curative treatment for VWM. In this study, we established the first EIF2B3 animal model for VWM disease in vertebrates by CRISPR mutagenesis of the highly conserved zebrafish ortholog eif2b3. Using CRISPR, we generated two mutant alleles in zebrafish eif2b3, 10- and 16-bp deletions, respectively. The eif2b3 mutants showed defects in myelin development and glial cell differentiation, and increased expression of genes in the induced stress response pathway. Interestingly, we also found ectopic angiogenesis and increased VEGF expression. Ectopic angiogenesis in the eif2b3 mutants was reduced by the administration of VEGF receptor inhibitor SU5416. Using the eif2b3 mutant zebrafish model together with in silico protein modeling analysis, we demonstrated the pathogenicity of 18 reported mutations in EIF2B3, as well as of a novel variant identified in a 19-month-old female patient: c.503 T > C (p.Leu168Pro). In summary, our zebrafish mutant model of eif2b3 provides novel insights into VWM pathogenesis and offers rapid functional analysis of human EIF2B3 gene variants.

Contrast-Enhanced High-Resolution Intracranial Vessel Wall MRI with Compressed Sensing: Comparison with Conventional T1 Volumetric Isotropic Turbo Spin Echo Acquisition Sequence.

OBJECTIVE: Compressed sensing (CS) has gained wide interest since it accelerates MRI acquisition. We aimed to compare the 3D post-contrast T1-weighted volumetric isotropic turbo spin echo acquisition (VISTA) with CS (VISTA-CS) and without CS (VISTA-nonCS) in intracranial vessel wall MRIs (VW-MRI). MATERIALS AND METHODS: From April 2017 to July 2018, 72 patients who underwent VW-MRI, including both VISTA-CS and VISTA-nonCS, were retrospectively enrolled. Wall and lumen volumes, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured from normal and lesion sites. Two neuroradiologists independently evaluated overall image quality and degree of normal and lesion wall delineation with a four-point scale (scores ≥ 3 defined as acceptable). RESULTS: Scan coverage was increased in VISTA-CS to cover both anterior and posterior circulations with a slightly shorter scan time compared to VISTA-nonCS (approximately 7 minutes vs. 8 minutes). Wall and lumen volumes were not significantly different with VISTA-CS or VISTA-nonCS (interclass correlation coefficient = 0.964-0.997). SNR was or trended towards significantly higher values in VISTA-CS than in VISTA-nonCS. At normal sites, CNR was not significantly different between two sequences (p = 0.907), whereas VISTA-CS provided lower CNR in lesion sites compared with VISTA-nonCS (p = 0.003). Subjective wall delineation was superior with VISTA-nonCS than with VISTA-CS (p = 0.019), although overall image quality did not differ (p = 0.297). The proportions of images with acceptable quality were not significantly different between VISTA-CS (83.3-97.8%) and VISTA-nonCS (75-100%). CONCLUSION: CS may be useful for intracranial VW-MRI as it allows for larger scan coverage with slightly shorter scan time without compromising image quality.

Factors for Enhancement of Intracranial Atherosclerosis in High Resolution Vessel Wall MRI in Ischemic Stroke Patients.

Introduction: High resolution vessel wall MRI (VW-MRI) has enabled to characterize intracranial atherosclerosis (ICAS). We studied to identify the factors for enhancement of ICAS in VW-MRI in patients with acute ischemic stroke. Methods: Consecutive patients with acute ischemic stroke or TIA who underwent VW-MRI between January 2017 and December 2017 were included. Enhancement on VW-MRI was defined as an increase in intensity on contrast-enhanced T1-weighted sequence. We compared the clinical and the radiologic findings between patients with wall enhancement and those without wall enhancement. Results: Of the 48 patients with ICAS, 28 patients revealed enhancement on VW-MRI. Patients with enhancement were more likely to have severe stenotic lesions and higher levels of total cholesterol, triglycerides, low-density cholesterol, Apo (b), and Apo (b)/Apo (a) lipoprotein ratio (p < 0.05). Multivariable analysis demonstrated that total cholesterol (OR: 5.378, 95% CI, 1.779-16.263), triglycerides (OR: 3.362, 95% CI, 1.008-11.209), low density lipoprotein cholesterol (OR: 4.226, 95% CI, 1.264-14.126), Apo (b) lipoprotein (OR: 3639.641, 95% CI, 17.854-741954.943) levels, and Apo (b)/Apo (a) lipoprotein ratio (OR, 65.514; 95% CI, 1.131-3680.239) were independently associated with enhancement of ICAS. High-density lipoprotein cholesterol and Apo (a) lipoprotein levels were not significantly different between the patients with wall enhancement and those without wall enhancement. Conclusions: The presence and severity of enhancement of ICAS was significantly associated with dyslipidemic conditions. These results suggest that strict lipid modification should be achieved for the management of ICAS.

Temporal Profile of Blood-Brain Barrier Breakdown in Reversible Cerebral Vasoconstriction Syndrome.

Background and Purpose- Reversible cerebral vasoconstriction syndrome (RCVS) has a unique temporal course of vasoconstriction. Blood-brain barrier (BBB) breakdown is part of the pathophysiology of RCVS, but its temporal course is unknown. We aimed to investigate the temporal profile of BBB breakdown and relevant clinical profiles in a large sample size. Methods- In this prospective observatory bicenter study, patients who underwent contrast-enhanced fluid-attenuated inversion recovery magnetic resonance imaging within 2 months from onset were included. The presence and extent of BBB breakdown were evaluated using contrast-enhanced fluid-attenuated inversion recovery magnetic resonance imaging. Contrast-enhanced fluid-attenuated inversion recovery magnetic resonance imaging data were analyzed using a semiautomated segmentation technique to quantitatively measure the area of Gadolinium leakage into cerebrospinal fluid space. The univariable and multivariable linear regressions were performed to investigate the independent effect of time from onset with adjustment for other covariates. Results- In the 186 patients with angiogram-proven RCVS included in this analysis, BBB breakdown was observed in 52.6%, 56.8%, 30.3%, 40.0%, and 23.8% in the first, second, third, fourth, and ≥fifth week after onset. The extent of BBB breakdown peaked at first and second week, whereas the peak of vasoconstriction was observed at the third week after onset. Multivariable analysis showed the second week from onset (ß, 3.35 [95% CI, 0.07-6.64]; P=0.046) and blood pressure surge (ß, 3.84 [95% CI, 1.75-5.92]; P<0.001) were independently associated with a greater extent of BBB breakdown. A synergistic effect of time from onset and blood pressure surge was found (P for interaction=0.006). Conclusions- Frequency and extent of BBB breakdown are more prominent during the early stage in patients with RCVS, with an earlier peak than that of vasoconstriction. The temporal course of BBB breakdown may provide a pathophysiologic background of the temporal course of neurological complications of RCVS.

Two-step deep neural network for segmentation of deep white matter hyperintensities in migraineurs.

BACKGROUND AND OBJECTIVE: Patients with migraine show an increased presence of white matter hyperintensities (WMHs), especially deep WMHs. Segmentation of small, deep WMHs is a critical issue in managing migraine care. Here, we aim to develop a novel approach to segmenting deep WMHs using deep neural networks based on the U-Net. METHODS: 148 non-elderly subjects with migraine were recruited for this study. Our model consists of two networks: the first identifies potential deep WMH candidates, and the second reduces the false positives within the candidates. The first network for initial segmentation includes four down-sampling layers and four up-sampling layers to sort the candidates. The second network for false positive reduction uses a smaller field-of-view and depth than the first network to increase utilization of local information. RESULTS: Our proposed model segments deep WMHs with a high true positive rate of 0.88, a low false discovery rate of 0.13, and F1 score of 0.88 tested with ten-fold cross-validation. Our model was automatic and performed better than existing models based on conventional machine learning. CONCLUSION: We developed a novel segmentation framework tailored for deep WMHs using U-Net. Our algorithm is open-access to promote future research in quantifying deep WMHs and might contribute to the effective management of WMHs in migraineurs.

Usefulness of high-resolution three-dimensional proton density-weighted turbo spin-echo MRI in distinguishing a junctional dilatation from an intracranial aneurysm of the posterior communicating artery: a pilot study.

BACKGROUND: Discriminating a junctional dilatation from a true saccular aneurysm is clinically important. PURPOSE: To evaluate the usefulness of high-resolution three-dimensional proton density-weighted turbo spin-echo magnetic resonance imaging (PD MRI) in distinguishing a junctional dilatation from an aneurysm of the posterior communicating artery (PcomA). METHODS: Eighty-two consecutive patients with 83 PcomA lesions, which were evaluated by time-of-flight (TOF) MR angiography (MRA), PD MRI, and digital subtraction angiography (DSA), were enrolled. These radiologic data were retrospectively and independently reviewed by two neurosurgeons, and each diagnosis based on TOF MRA, PD MRI, and DSA was compared. The diagnostic efficacy (interobserver agreement, intermodality agreement, and diagnostic performance) of PD MRI was compared with that of TOF MRA. RESULTS: PD MRI showed higher AC1 (Gwet's agreement coefficient, PD MRI: 0.8942, 95% CI 0.8204 to 0.968; TOF MRA: 0.7185, 95% CI 0.5753 to 0.8617) and prevalence-adjusted bias-adjusted kappa coefficient (PABAK) (PD MRI: 0.8554, TOF MRA: 0.5904) than TOF MRA for interobserver agreement. For intermodality agreement, PD MRI also showed higher AC1 (PD MRI: 0.9069, 95% CI 0.8374 to 0.9764; TOF MRA: 0.7983, 95% CI 0.6969 to 0.8996) and PABAK (PD MRI: 0.8735, TOF MRA: 0.7289) than TOF MRA. The diagnostic performance of PD MRI was statistically superior to that of TOF MRA in sensitivity, specificity, positive predictive value, and negative predictive value. CONCLUSIONS: PD MRI could provide excellent diagnostic accuracy and better information in distinguishing a junctional dilatation from a true saccular aneurysm of the PcomA compared with TOF MRA.

Intensive Statin Treatment in Acute Ischaemic Stroke Patients with Intracranial Atherosclerosis: a High-Resolution Magnetic Resonance Imaging study (STAMINA-MRI Study).

OBJECTIVE: Intracranial atherosclerosis is a major cause of ischaemic stroke worldwide. A number of studies have shown the effects of statin treatment on coronary and carotid artery plaques, but there is little evidence on the effects of statin treatment on intracranial atherosclerotic plaques. METHODS: The Intensive Statin Treatment in Acute Ischaemic Stroke Patients with Intracranial Atherosclerosis - High-Resolution Magnetic Resonance Imaging (STAMINA-MRI) Trial is a single-arm, prospective, observational study monitoring imaging and clinical outcomes of high-dose statin treatment among statin-naive patients with acute ischaemic stroke caused by symptomatic intracranial atherosclerosis. The primary outcome was the change in vascular remodelling and plaque characteristics before and after 6 months (median: 179 days, IQR 163-189 days) of statin treatment measured by high-resolution MRI (HR-MRI). RESULTS: A total of 77 patients (mean age: 62.6±13.7 years, 61.0% women) were included in this study. Low-density lipoprotein cholesterol (LDL-C) levels (mg/dL) at initial and follow-up assessments were 125.81±35.69 and 60.95±19.28, respectively. Overall, statin treatment significantly decreased enhancement of plaque volume (mm3, 32.07±39.15 vs 17.06±34.53, p=0.013), the wall area index (7.50±4.28 vs 5.86±4.05, p=0.016) and stenosis degree (%, 76.47±20.23 vs 64.05±21.29, p<0.001), but not the remodelling index (p=0.195). However, 35% patients showed no change or increased enhancement volume and stenosis degree after statin treatment. Higher reduction of LDL-C and longer duration of statin treatment were associated with decreased enhancement volume after statin treatment. CONCLUSIONS: High-dose statin treatment effectively stabilised symptomatic intracranial atherosclerotic plaques as documented by HR-MRI. Further study is needed to determine laboratory and genetic factors associated with poor response to statins and alternative therapeutic options, such as proprotein convertase subtilisin-kexin type 9 inhibitors, for these patients. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov NCT02458755.

Differentiation of postoperative changes and residual tumors in dynamic contrast-enhanced sella MRI after transsphenoidal resection of pituitary adenoma.

To establish magnetic resonance imaging (MRI) features that differentiate residual tumors from postoperative surgical changes following the transsphenoidal approach of a pituitary adenoma.We analyzed residual enhancements at the tumor bed in 52 patients who underwent dynamic contrast-enhanced sella MRI within 48 hours after surgery and at 6 to 28 months. Patients were divided into 2 groups defined by either peripheral or nodular enhancement patterns. For each group, we measured the maximum thickness of the residual enhancing portion and compared differences in the residual tumor and postoperative changes.Among the tumors examined in the 52 patients, 19 residual tumors showed nodular (n = 16) and peripheral (n = 3) enhancement patterns, and 33 postoperative changes showed nodular (n = 3) and peripheral (n = 30) enhancement patterns. The mean residual tumor thickness was 7.1 mm (range, 2.9-16.8 mm) and 1.9 mm (range, 1.0-7.4 mm) in the postoperative change. Receiver operating characteristic curve analysis revealed that a 3.9-mm thickness was associated with 89% sensitivity, 97% specificity, and 94% accuracy for diagnosis of residual tumor.On immediate postoperative MRI, residual enhancement with greater than 3.9-mm thickness and nodular pattern suggest residual pituitary adenoma tumor.

Basal cell adenoma and myoepithelioma of the parotid gland: patterns of enhancement at two-phase CT in comparison with Warthin tumor.

PURPOSE: Early enhancement and a washout pattern are reported to be the characteristic imaging features of Warthin tumor (WT). The purpose of this study was to evaluate the enhancement patterns of basal cell adenoma (BCA) and myoepithelioma (ME) of the parotid gland on two-phase computed tomography (CT), compared with WT. METHODS: We retrospectively evaluated two-phase CT examinations of histologically proven 19 BCAs, 12 MEs, and 23 WTs of the parotid gland. In all patients, CT scans were obtained at early and delayed phases with scanning delays of 40 and 180 s, respectively. We measured the attenuation values on each phase of CT scans and calculated washout attenuation and relative percentage enhancement washout ratio. From the data acquired, we statistically compared the enhancing characteristics among three tumor groups. RESULTS: Based on the results of washout attenuation and relative percentage enhancement washout ratio, 15 (79%) of 19 BCAs, 9 (75%) of 12 MEs, and 23 (100%) of 23 WTs demonstrated a washout pattern of enhancement on two-phase CT scans. Despite variations of the individual tumors, both parameters revealed no significant difference among three tumor groups. CONCLUSION: BCAs and MEs of the parotid gland frequently show early enhancement and a washout pattern on two-phase CT, which can be indistinguishable from WTs in the majority of cases.

Characterization of clot composition in acute cerebral infarct using machine learning techniques.

OBJECTIVE: Clot characteristics can provide information on the cause of cerebral artery occlusion and may guide acute revascularization and secondary prevention strategies. We developed a rapid automated clot analysis system using machine learning (ML) and validated its accuracy in patients undergoing endovascular treatment. METHODS: Pre-endovascular treatment gradient echo (GRE) images from consecutive patients with middle cerebral artery occlusion were utilized to develop and validate an ML system to predict whether atrial fibrillation (AF) was the underlying cause of ischemic stroke. The accuracy of the ML algorithm was compared with that of visual inspection by neuroimaging specialists for the presence of blooming artifact. Endovascular procedures and outcomes were compared in patients with and without AF. RESULTS: Of 67 patients, 29 (43.3%) had AF. Of these, 13 had known AF and 16 were newly diagnosed with cardiac monitoring. By visual inspection, interrater correlation for blooming artifact was 0.73 and sensitivity and specificity for AF were 0.79 and 0.63, respectively. For AF classification, the ML algorithms yielded an average accuracy of > 75.4% in fivefold cross-validation with clot signal profiles obtained from 52 patients and an area under the curve >0.87 for the average AF probability from five signal profiles in external validation (n = 15). Analysis with an in-house interface took approximately 3 min per patient. Absence of AF was associated with increased number of passes by stentriever, high reocclusion frequency, and additional use of rescue stenting and/or glycogen IIb/IIIa blocker for recanalization. INTERPRETATION: ML-based rapid clot analysis is feasible and can identify AF with high accuracy, enabling selection of endovascular treatment strategy.

Data-driven synthetic MRI FLAIR artifact correction via deep neural network.

BACKGROUND: FLAIR (fluid attenuated inversion recovery) imaging via synthetic MRI methods leads to artifacts in the brain, which can cause diagnostic limitations. The main sources of the artifacts are attributed to the partial volume effect and flow, which are difficult to correct by analytical modeling. In this study, a deep learning (DL)-based synthetic FLAIR method was developed, which does not require analytical modeling of the signal. PURPOSE: To correct artifacts in synthetic FLAIR using a DL method. STUDY TYPE: Retrospective. SUBJECTS: A total of 80 subjects with clinical indications (60.6 ± 16.7 years, 38 males, 42 females) were divided into three groups: a training set (56 subjects, 62.1 ± 14.8 years, 25 males, 31 females), a validation set (1 subject, 62 years, male), and the testing set (23 subjects, 57.3 ± 20.4 years, 13 males, 10 females). FIELD STRENGTH/SEQUENCE: 3 T MRI using a multiple-dynamic multiple-echo acquisition (MDME) sequence for synthetic MRI and a conventional FLAIR sequence. ASSESSMENT: Normalized root mean square (NRMSE) and structural similarity (SSIM) were computed for uncorrected synthetic FLAIR and DL-corrected FLAIR. In addition, three neuroradiologists scored the three FLAIR datasets blindly, evaluating image quality and artifacts for sulci/periventricular and intraventricular/cistern space regions. STATISTICAL TESTS: Pairwise Student's t-tests and a Wilcoxon test were performed. RESULTS: For quantitative assessment, NRMSE improved from 4.2% to 2.9% (P < 0.0001) and SSIM improved from 0.85 to 0.93 (P < 0.0001). Additionally, NRMSE values significantly improved from 1.58% to 1.26% (P < 0.001), 3.1% to 1.5% (P < 0.0001), and 2.7% to 1.4% (P < 0.0001) in white matter, gray matter, and cerebral spinal fluid (CSF) regions, respectively, when using DL-corrected FLAIR. For qualitative assessment, DL correction achieved improved overall quality, fewer artifacts in sulci and periventricular regions, and in intraventricular and cistern space regions. DATA CONCLUSION: The DL approach provides a promising method to correct artifacts in synthetic FLAIR. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1413-1423.

Visualization of basilar artery atherosclerotic plaques by conventional T2-weighted magnetic resonance imaging: A case-control study.

OBJECTIVE: In vivo visualization of intracranial atherosclerotic plaque has been performed only with high-resolution magnetic resonance imaging (HRMR). We investigated whether atherosclerotic plaque of the basilar artery (BA) can be identified in conventional magnetic resonance imaging (MRI). METHODS: Patients with acute ischemic stroke who had BA stenosis ("symptomatic BAA") were retrospectively recruited using the prospective stroke registry. In the HRMR databank, subjects without BA stenosis were recruited and classified as those with silent plaque ("silent BAA") and without any plaque ("normal controls"). Outer diameter of the BA and T2 plaque sign (an eccentric or complete obscuration of normal flow-void) within the BA were assessed by two blinded raters using conventional T2 MRI. RESULTS: Seventy-five patients with symptomatic BAA, 40 with asymptomatic BAA, and 36 normal controls were included in the study. Maximal BA diameter was significantly larger in symptomatic BAA patients with <30%, 30-50%, 50-70%, and >70% stenosis (all p<0.01 in each subgroup) and silent BAA subjects (p = 0.018) than controls. T2 plaque signs were present in 46 (61.3%) patients with symptomatic BAA and 6 (14.6%) subjects with asymptomatic BAA, while none in normal controls (p <0.001 and 0.057, respectively). Detection rates were increased with an increase in stenosis degree (25.0% in <30% stenosis, 57.9% in 30-50% stenosis, 38.5% in 50-70% stenosis, 92.3% in 70-99% stenosis, and 100.0% in occlusion). CONCLUSIONS: Our data suggest that BA atherosclerosis can be detected by conventional MRI. When the use of HRMR is limited, conventional MR imaging may give additive information to clinicians.

A case report of isolated orbital vasculitis mimicking retinal migraine: A potential cause of recurrent transient monocular blindness and ipsilateral headache.

BACKGROUND: Retinal migraine is an important differential diagnosis of recurrent transient monocular blindness accompanied by headache when other etiologies are excluded. Here, we report a case of orbital vasculitis which initially mimicked retinal migraine. CASE REPORT: A 47-year-old woman had recurrent episodes of fully reversible transient monocular blindness accompanied by ipsilateral headache for 15 months. The patient's neuroimaging and cardiac and ophthalmologic evaluations were normal. With a diagnosis of retinal migraine, her symptoms remitted in response to prophylactic treatment with topiramate and propranolol for 8 months. Three months after discontinuation of medications, transient monocular blindness recurred. High-resolution vessel wall magnetic resonance imaging revealed enhancement of the ipsilateral orbital vessels. Isolated orbital vasculitis was diagnosed. Complete remission of transient monocular blindness was achieved after steroid pulse therapy. DISCUSSION: Isolated orbital vasculitis should be considered in differential diagnosis of recurrent transient monocular blindness and ipsilateral headache. High-resolution vessel wall magnetic resonance imaging can be helpful for the diagnosis.

Outcomes after ischemic stroke caused by intracranial atherosclerosis vs dissection.

OBJECTIVE: To compare the outcomes between patients with nontraumatic intracranial arterial dissection (ICAD) and intracranial atherosclerotic stenosis (ICAS) using high-resolution MRI (HR-MRI). METHODS: We conducted a prospective study using HR-MRI in patients with acute symptomatic cerebrovascular disease due to intracranial occlusive disease and no dissection on luminal images. Patients were followed-up for 27.9 ± 19.3 months. We compared the functional outcome, recurrence, and changes in vascular status between patients with ICAD (dissection and no plaque on HR-MRI) and ICAS (atherosclerosis plaque on HR-MRI). RESULTS: We included 312 patients (mean age, 59.0 ± 14.2 years; men, 58.3%), of whom 113 had ICAD and 199 had ICAS. The functional outcome (as measured by modified Rankin Scale score) on the 90th day after symptom onset was not different between the groups, after adjusted for other factors (p = 0.095). However, recurrent ischemic cerebrovascular disease on the relevant vascular territory was lower in the ICAD group (7 patients, 6.2%) than in the ICAS group (37 patients, 18.6%). ICAD was a significant independent determinant of disease recurrence (hazard ratio, 0.43; 95% confidence interval, 0.19-0.98). Improvement in vascular stenosis on follow-up vascular studies was more frequently observed in ICAD (50.7%) than in ICAS (11.6%). ICAD was an independent determinant of vascular improvement (odds ratio, 7.94; 95% confidence interval, 3.32-19.01). CONCLUSION: Considering the high prevalence of ICAD in the patients with presumed ICAS and the differential outcomes between ICAD and ICAS, HR-MRI may be a useful diagnostic tool in this population.