Deep Learning-Based Tract Classification of Preoperative DWI Tractography Advances the Prediction of Short-term Postoperative Language Improvement in Children with Drug-resistant Epilepsy.

OBJECTIVE: To develop an innovative deep convolutional neural network (DCNN)-based tract classification to enhance the prediction of short-term postoperative language improvement using axonal connectivity markers derived from specific language modular networks (LMNs) within the preoperative whole-brain diffusion-weighted imaging connectome (wDWIC). METHODS: We employed a three-step approach. First, our previous DCNN-based tract classification to detect true-positive eloquent tracts was extended using an open-source database of high-quality wDWIC to facilitate the accurate classification of truepositive tracts within the preoperative backbone wDWIC of individual patients. Next, we applied psychometry-driven DWIC analysis to the resulting DCNN-based backbone wDWIC in order to create core, expressive, and receptive LMNs. Finally, graph and circuit theory-based connectivity markers were assessed within the three LMNs and compared using a series of machine learning algorithms to predict the presence of postoperative language improvement from a given LMN. RESULTS: The results showed that the extended DCNN tract classification significantly improved the reproducibility of connectivity markers by up to 35.5% of F-statistics across different LMNs. The prediction accuracy increased by up to 40% across different machine learning algorithms. Notably, the best algorithm achieved the accuracy of 96%/94%/96% to predict the presence of language improvement about two months after surgery in core/expressive/receptive domain of an independent validation cohort. CONCLUSION: These domains hold great potential to assist physicians in identifying candidates whose language skills stand to benefit from early surgery. SIGNIFICANCE: DCNN tract classification may be an effective tool to improve predicting short-term postoperative language improvement in pediatric epilepsy surgery.

Feasibility and Potential Diagnostic Value of Noncontrast Brain MRI in Nonsedated Children With Sturge-Weber Syndrome and Healthy Siblings.

BACKGROUND: Postcontrast magnetic resonance imaging (MRI), obtained under anesthesia, is often used to evaluate brain parenchymal and vascular abnormalities in young children, including those with Sturge-Weber syndrome. However, anesthesia and contrast administration may carry risks. We explored the feasibility and potential diagnostic value of a noncontrast, nonsedate MRI acquisition in Sturge-Weber syndrome children and their siblings with a wide range of cognitive and behavioral functioning. METHODS: Twenty children (10 with Sturge-Weber syndrome and 10 healthy siblings; age: 0.7-13.5 years) underwent nonsedate 3-tesla (T) brain MRI acquisition with noncontrast sequences (including susceptibility-weighted imaging) prospectively along with neuropsychology assessment. All images were evaluated for quality, and MRI abnormalities identified in the Sturge-Weber syndrome group were compared to those identified on previous clinical pre- and postcontrast MRI. RESULTS: Nineteen participants (95%) completed the MRI with good (n = 18) or adequate (n = 1) quality, including all children with Sturge-Weber syndrome and all 5 children ≤5 years of age. The Sturge-Weber syndrome group had lower cognitive functions than the controls, and both groups had several children with behavioral issues, without an apparent effect on the success and quality of the MR images. Susceptibility-weighted imaging detected key venous vascular abnormalities and calcifications and, along with the other noncontrast sequences, provided diagnostic information comparable to previous clinical MRI performed with contrast administration under anesthesia. CONCLUSION: This study demonstrates the feasibility and the potential diagnostic value of a nonsedate, noncontrast MRI acquisition protocol in young children including those with cognitive impairment and/or behavioral concerns. This approach can facilitate clinical trials in children where safe serial MRI is warranted.

Quantification of enlarged deep medullary vein volumes in Sturge-Weber syndrome.

Background: Enlarged deep medullary veins (EDMVs) in patients with Sturge-Weber syndrome (SWS) may channel venous blood from the surface to the deep vein system in brain regions affected by the leptomeningeal venous malformation. Thus, the quantification of EDMV volume may provide an objective imaging marker for this vascular compensatory process. The present study proposes a novel analytical method to quantify enlarged EDMV volumes in the affected hemisphere of patients with unilateral SWS. Methods: Twenty young subjects, including 10 patients with unilateral SWS and 10 healthy siblings (age 14.5±6.7 and 16.0±7.0 years, respectively) underwent 3T brain MRI scanning using susceptibility-weighted imaging (SWI) and volumetric T1-weighted sequences. The proposed image analytic steps segmented EDMVs in white matter regions, defined on the volumetric T1-weighted images, by statistically associating the likelihood of intensity, location, and tubular shape on SWI. The volumes of the segmented EDMVs, calculated in each hemisphere, were compared between affected and unaffected hemispheres. EDMV volumes were also correlated with visually assessed EDMV scores, hemispheric white matter volumes, and cortical surface areas. Parametric tests including Pearson's correlation, unpaired and paired t-tests, were used. A P value <0.05 was considered statistically significant. Results: It was found that EDMVs were identified well in SWS-affected hemispheres while calcified regions were excluded. Mean EDMV volumes in the SWS-affected hemispheres were 10-12-fold greater than in the unaffected or healthy control hemispheres; while white matter volumes and cortical surface areas were lower. EDMV volumes in the SWS-affected hemispheres showed a strong positive correlation with the visual EDMV scores (r=0.88, P=0.001) and an inverse correlation with cortical surface area ratios (r=-0.65, P=0.04) but no correlation with white matter volume ratios. Conclusions: EDMVs were detected in the SWS-affected atrophic hemispheres reliably while avoiding calcified regions. The approach can be used to quantify enlarged deep cerebral veins in the human brain, which may provide a potential marker of cerebral venous remodeling.

The First Human Application of an F-18-Labeled Tryptophan Analog for PET Imaging of Cancer.

PURPOSE: Preclinical studies showed the tryptophan analog PET radiotracer 1-(2-18F-fluoroethyl)-L-tryptophan (18F-FETrp) to accumulate in various tumors, including gliomas, and being metabolized via the immunosuppressive kynurenine pathway. In this first-in-human study, we tested the use 18F-FETrp-PET in patients with neuroendocrine and brain tumors. PROCEDURES: We applied dynamic brain imaging in patients with gliomas (n = 2) and multi-pass 3D whole-body PET scans in patients with neuroendocrine tumors (n =4). Semiquantitative analysis of organ and tumor tracer uptake was performed using standardized uptake values (SUVs). In addition, organ dosimetry was performed based on extracted time-activity curves and the OLINDA software. RESULTS: Neuroendocrine tumors showed an early peak (10-min post-injection) followed by washout. Both gliomas showed prolonged 18F-FETrp accumulation plateauing around 40 min and showing heterogeneous uptake including non-enhancing tumor regions. Biodistribution showed moderate liver uptake and fast clearance of radioactivity into the urinary bladder; the estimated effective doses were similar to other 18F-labeled radioligands. CONCLUSIONS: The study provides proof-of-principle data for the safety and potential clinical value of 18F-FETrp-PET for molecular imaging of human gliomas.

Automated radiosynthesis of 1-(2-[18 F]fluoroethyl)-L-tryptophan ([18 F]FETrp) for positron emission tomography (PET) imaging of cancer in humans.

The radiotracer 1-(2-[18 F]fluoroethyl)-L-tryptophan (L-[18 F]FETrp or [18 F]FETrp) is a substrate of indoleamine 2,3-dioxygenase, the initial and key enzyme of the kynurenine pathway associated with tumoral immune resistance. In preclinical positron emission tomography studies, [18 F]FETrp is highly accumulated in a wide range of primary and metastatic cancers, such as lung cancer, prostate cancer, and gliomas. However, the clinical translation of this radiotracer into the first-in-human trial has not been reported, partially due to its racemization during radiofluorination which renders the purification of the final product challenging. However, efficient purification is essential for human studies in order to assure radiochemical and enantiomeric purity. In this work, we report a fully automated radiosynthesis of [18 F]FETrp on a Synthra RNPlus research module, including a one-pot two steps radiosynthesis, dual independent chiral and reverse-phase semipreparative high-performance liquid chromatography purifications, and solid-phase extraction-assisted formulation. The presented approach has led to its Investigational New Drug application and approval that allows the testing of this tracer in humans.

Deep Venous Remodeling in Unilateral Sturge-Weber Syndrome: Robust Hemispheric Differences and Clinical Correlates.

BACKGROUND: Enlarged deep medullary veins (EDMVs) in patients with Sturge-Weber syndrome (SWS) may provide compensatory venous drainage for brain regions affected by the leptomeningeal venous malformation (LVM). We evaluated the prevalence, extent, hemispheric differences, and clinical correlates of EDMVs in SWS. METHODS: Fifty children (median age: 4.5 years) with unilateral SWS underwent brain magnetic resonance imaging prospectively including susceptibility-weighted imaging (SWI); children aged 2.5 years or older also had a formal neurocognitive evaluation. The extent of EDMVs was assessed on SWI by using an EDMV hemispheric score, which was compared between patients with right and left SWS and correlated with clinical variables. RESULTS: EDMVs were present in 89% (24 of 27) of right and 78% (18 of 23) of left SWS brains. Extensive EDMVs (score >6) were more frequent in right (33%) than in left SWS (9%; P = 0.046) and commonly occurred in young children with right SWS. Patients with EDMV scores >4 had rare (less than monthly) seizures, whereas 35% (11 of 31) of patients with EDMV scores ≤4 had monthly or more frequent seizures (P = 0.003). In patients with right SWS and at least two LVM-affected lobes, higher EDMV scores were associated with higher intelligence quotient (P < 0.05). CONCLUSIONS: Enlarged deep medullary veins are common in unilateral SWS, but extensive EDMVs appear to develop more commonly and earlier in right hemispheric SWS. Deep venous remodeling may be a compensatory mechanism contributing to better clinical outcomes in some patients with SWS.

Multi-Scale Deep Learning of Clinically Acquired Multi-Modal MRI Improves the Localization of Seizure Onset Zone in Children With Drug-Resistant Epilepsy.

The present study investigates the effectiveness of a deep learning neural network for non-invasively localizing the seizure onset zone (SOZ) using multi-modal MRI data that are clinically acquired from children with drug-resistant epilepsy. A cortical parcellation was applied to localize the SOZ in cortical nodes of the epileptogenic hemisphere. At each node, the laminar surface analysis was followed to sample 1) the relative intensity of gray matter and white matter in multi-modal MRI and 2) the neighboring white matter connectivity using diffusion tractography edge strengths. A cross-validation was employed to train and test all layers of a multi-scale residual neural network (msResNet) that can classify SOZ node in an end-to-end fashion. A prediction probability of a given node belonging to the SOZ class was proposed as a non-invasive MRI marker of seizure onset likelihood. In an independent validation cohort, the proposed MRI marker provided a very large effect size of Cohen's d = 1.21 between SOZ and non-SOZ, and classified SOZ with a balanced accuracy of 0.75 in lesional and 0.67 in non-lesional MRI groups. The subsequent multi-variate logistic regression found the incorporation of the proposed MRI marker into interictal intracranial EEG (iEEG) markers further improves the differentiation between the epileptogenic focus (defined as SOZ resected during surgery) and non-epileptogenic sites (i.e., non-SOZ sites preserved during surgery) up to 15 % in non-lesional MRI group, suggesting that the proposed MRI marker could improve the localization of epileptogenic foci for successful pediatric epilepsy surgery.

Prostate-Specific Membrane Antigen as Target for Neuroimaging of Central Nervous System Tumors.

Introduction: Positron emission tomography (PET) imaging with prostate-specific membrane antigen- (PSMA-) binding tracers has been found incidentally to demonstrate uptake in CNS tumors. Following the encouraging findings of several such case reports, there is a growing interest in the potential application of PSMA-targeted PET imaging for diagnostics, theranostics, and monitoring of CNS tumors. This is a systematic literature review on PSMA-binding tracers in CNS tumors. Methods: A PubMed search was conducted, including preclinical and clinical reports. One hundred and twelve records were identified, and after screening, 56 were included in the final report. Results: Tissue studies demonstrated PSMA expression in tumor vascular endothelial cells, without expression in normal brain tissue, though the extent and intensity of staining varied by anti-PSMA antibody and methodology. Most included studies reported on gliomas, which showed strong PSMA ligand uptake and more favorable tumor to background ratios than other PET tracers. There are also case reports demonstrating PSMA ligand uptake in prostate cancer brain metastases, nonprostate cancer brain metastases, and meningiomas. We also review the properties of the various PSMA-binding radiotracers available. Therapeutic and theranostic applications of PSMA-binding tracers have been studied, including labeled alpha- and beta-ray emitting isotopes, as well as PSMA targeting in directing MRI-guided focused ultrasound. Conclusions: There is a potential application for PSMA-targeted PET in neuro-oncology as a combination of diagnostic and therapeutic use, as a theranostic modality for managing CNS tumors. Further research is needed regarding the mechanism(s) of PSMA expression in CNS tumors and its differential performance by tumor type.

Diffusion tractography predicts propagated high-frequency activity during epileptic spasms.

OBJECTIVE: To determine the structural networks that constrain propagation of ictal oscillations during epileptic spasm events, and compare the observed propagation patterns across patients with successful or unsuccessful surgical outcomes. METHODS: Subdural electrode recordings of 18 young patients (age 1-11 years) were analyzed during epileptic spasm events to determine ictal networks and quantify the amplitude and onset time of ictal oscillations across the cortical surface. Corresponding structural networks were generated with diffusion magnetic resonance imaging (MRI) tractography by seeding the cortical region associated with the earliest average oscillation onset time, and white matter pathways connecting active electrode regions within the ictal network were isolated. Properties of this structural network were used to predict oscillation onset times and amplitudes, and this relationship was compared across patients who did and did not achieve seizure freedom following resective surgery. RESULTS: Onset propagation patterns were relatively consistent across each patient's spasm events. An electrode's average ictal oscillation onset latency was most significantly associated with the length of direct corticocortical tracts connecting to the area with the earliest average oscillation onset (p < .001, model R2  = .54). Moreover, patients demonstrating a faster propagation of ictal oscillation signals within the corticocortical network were more likely to have seizure recurrence following resective surgery (p = .039). In addition, ictal oscillation amplitude was associated with connecting tractography length and weighted fractional anisotropy (FA) measures along these pathways (p = .002/.030, model R2  = .31/.25). Characteristics of analogous corticothalamic pathways did not show significant associations with ictal oscillation onset latency or amplitude. SIGNIFICANCE: Spatiotemporal propagation patterns of high-frequency activity in epileptic spasms align with length and FA measures from onset-originating corticocortical pathways. Considering the data in this individualized framework may help inform surgical decision-making and expectations of surgical outcomes.

Comparison of Amino Acid PET to Advanced and Emerging MRI Techniques for Neurooncology Imaging: A Systematic Review of the Recent Studies.

Introduction: Standard neuroimaging protocols for brain tumors have well-known limitations. The clinical use of additional modalities including amino acid PET (aaPET) and advanced MRI (aMRI) techniques (including DWI, PWI, and MRS) is emerging in response to the need for more accurate detection of brain tumors. In this systematic review of the past 2 years of the literature, we discuss the most recent studies that directly compare or combine aaPET and aMRI for brain tumor imaging. Methods: A PubMed search was conducted for human studies incorporating both aaPET and aMRI and published between July 2018 and August 2020. Results: A total of 22 studies were found in the study period. Recent studies of aaPET with DWI showed a superiority of MET, FET, FDOPA, and AMT PET for detecting tumor, predicting recurrence, diagnosing progression, and predicting survival. Combining modalities further improved performance. Comparisons of aaPET with PWI showed mixed results about spatial correlation. However, both modalities were able to detect high-grade tumors, identify tumor recurrence, differentiate recurrence from treatment effects, and predict survival. aaPET performed better on these measures than PWI, but when combined, they had the strongest results. Studies of aaPET with MRS demonstrated that both modalities have diagnostic potential but MET PET and FDOPA PET performed better than MRS. MRS suffered from some data quality issues that limited analysis in two studies, and, in one study that combined modalities, overall performance actually decreased. Four recent studies compared aaPET with emerging MRI approaches (such as CEST imaging, MR fingerprinting, and SISTINA), but the initial results remain inconclusive. Conclusions: aaPET outperformed the aMRI imaging techniques in most recent studies. DWI and PWI added meaningful complementary data, and the combination of aaPET with aMRI yielded the best results in most studies.

Consensus Statement for the Management and Treatment of Sturge-Weber Syndrome: Neurology, Neuroimaging, and Ophthalmology Recommendations.

BACKGROUND: Sturge-Weber syndrome (SWS) is a sporadic, neurocutaneous syndrome involving the skin, brain, and eyes. Because of the variability of the clinical manifestations and the lack of prospective studies, consensus recommendations for management and treatment of SWS have not been published. OBJECTIVE: This article consolidates the current literature with expert opinion to make recommendations to guide the neuroimaging evaluation and the management of the neurological and ophthalmologic features of SWS. METHODS: Thirteen national peer-recognized experts in neurology, radiology, and ophthalmology with experience treating patients with SWS were assembled. Key topics and questions were formulated for each group and included (1) risk stratification, (2) indications for referral, and (3) optimum treatment strategies. An extensive PubMed search was performed of English language articles published in 2008 to 2018, as well as recent studies identified by the expert panel. The panel made clinical practice recommendations. CONCLUSIONS: Children with a high-risk facial port-wine birthmark (PWB) should be referred to a pediatric neurologist and a pediatric ophthalmologist for baseline evaluation and periodic follow-up. In newborns and infants with a high-risk PWB and no history of seizures or neurological symptoms, routine screening for brain involvement is not recommended, but brain imaging can be performed in select cases. Routine follow-up neuroimaging is not recommended in children with SWS and stable neurocognitive symptoms. The treatment of ophthalmologic complications, such as glaucoma, differs based on the age and clinical presentation of the patient. These recommendations will help facilitate coordinated care for patients with SWS and may improve patient outcomes.

Multicenter Research Data of Epilepsy Management in Patients With Sturge-Weber Syndrome.

BACKGROUND: Epilepsy in typical Sturge-Weber syndrome (SWS) is common, and many questions remain regarding the treatment outcomes. We analyzed a large multicenter database with focus on neurological drug treatment in different demographic and SWS characteristic groups. METHODS: A total of 268 patients with brain involvement and a history of seizures were selected from a research data registry generated from a multicenter cross-sectional questionnaire. We examined associations between medication use and binary variables such as sex, ethnicity, and brain, skin, and eye involvement laterality. We analyzed group differences in mean number of antiseizure medications and age at diagnosis, enrollment, and seizure onset and examined differences in median SWS neurological scores in groups of interest. RESULTS: The most frequently used medications were levetiracetam (48.1%), low-dose aspirin (44.8%), oxcarbazepine (39.9%), and phenobarbital (14.9%). Lamotrigine was more frequently used in adults than in children (P = 0.001). History of neurosurgery was associated with no current antiseizure medication use (P = 0.001), whereas bilateral brain involvement and family history of seizures were associated with using a higher number of antiseizure medications (P = 0.002, P = 0.027, respectively). Subjects with bilateral brain involvement and early seizure onset were associated with using a higher number of antiseizure medications (P = 0.002) and phenobarbital use (0.003). CONCLUSIONS: Levetiracetam, low-dose aspirin, and oxcarbazepine were the most frequently used medications. More severely affected patients were frequently on a greater number of antiseizure medications. Surgery for epilepsy was associated with the ability to discontinue antiseizure medication. Longitudinal studies are needed to further investigate medication use in patients with SWS.

Depression and tryptophan metabolism in patients with primary brain tumors: Clinical and molecular imaging correlates.

Patients with brain tumors have an increased risk for depression, whose underlying pathomechanism may involve dysregulated tryptophan/kynurenine metabolism. In this study, we analyzed the relation of depressive symptoms to clinical and tumor characteristics as well as cerebral and systemic tryptophan metabolism in patients with primary brain tumors. Sixty patients with newly-diagnosed or recurrent primary brain tumor underwent testing with the Beck Depression Inventory-II (BDI-II), and 34 patients also had positron emission tomography (PET) imaging with alpha-[11C]methyl-L-tryptophan (AMT). BDI-II scores were correlated with clinical and tumor-related variables, cerebral regional AMT metabolism measured in the non-tumoral hemisphere, and plasma tryptophan metabolite levels. Sixteen patients (27%) had BDI-II scores indicating depression, including 6 with moderate/severe depression. High BDI-II scores were independent of clinical and tumor-related variables except lower Karnofsky Performance Status scores. In patients with recurrent malignant gliomas, depression was associated with shorter survival (hazard ratio: 3.7; p = 0.048). High BDI-II total and somatic subscale scores were associated with higher frontal cortical and thalamic AMT metabolic values measured on PET. In contrast, plasma tryptophan and kynurenine metabolite levels did not correlate with the BDI-II scores. In conclusion, our results confirm previous data that depression affects more than » of patients with primary brain tumors, it is largely independent of tumor characteristics and is associated with shorter survival in patients with recurrent malignant gliomas. On PET imaging, higher tryptophan metabolism in the frontal cortex and thalamus was found in those with brain tumor-associated depression and supports the role of dysregulated tryptophan/kynurenine metabolism in this condition.

Deep Relational Reasoning for the Prediction of Language Impairment and Postoperative Seizure Outcome Using Preoperative DWI Connectome Data of Children With Focal Epilepsy.

Prolonged seizures in children with focal epilepsy (FE) may impair language functions and often reoccur after surgical intervention. This study is aimed at developing a novel deep relational reasoning network to investigate whether conventional diffusion-weighted imaging connectome analysis can be improved when predicting expressive and receptive scores of preoperative language impairments and classifying postoperative seizure outcomes (seizure freedom or recurrence) in individual FE children. To deeply reason the dependencies of axonal connections that are sparsely distributed in the whole brain, this study proposes the "dilated CNN + RN", a dilated convolutional neural network (CNN) combined with a relation network (RN). The performance of the dilated CNN + RN was evaluated using whole brain connectome data from 51 FE children. It was found that when compared with other state-of-the-art algorithms, the dilated CNN + RN led to an average improvement of 90.2% and 97.3% in predicting expressive and receptive language scores, and 2.2% and 4% improvement in classifying seizure freedom and seizure recurrence, respectively. These improvements were independent of the prefixed connectome densities. Also, the dilated CNN + RN could provide an explainable artificial intelligence (AI) model by computing gradient-based regression/classification activation maps. This mapping analysis revealed left superior-medial frontal cortex, bilateral hippocampi, and cerebellum as crucial hubs, facilitating important connections that were most predictive of language function and seizure refractoriness after surgery.

Molecular Imaging of Brain Tumor-Associated Epilepsy.

Epilepsy is a common clinical manifestation and a source of significant morbidity in patients with brain tumors. Neuroimaging has a pivotal role in neuro-oncology practice, including tumor detection, differentiation, grading, treatment guidance, and posttreatment monitoring. In this review, we highlight studies demonstrating that imaging can also provide information about brain tumor-associated epileptogenicity and assist delineation of the peritumoral epileptic cortex to optimize postsurgical seizure outcome. Most studies focused on gliomas and glioneuronal tumors where positron emission tomography (PET) and advanced magnetic resonance imaging (MRI) techniques can detect metabolic and biochemical changes associated with altered amino acid transport and metabolism, neuroinflammation, and neurotransmitter abnormalities in and around epileptogenic tumors. PET imaging of amino acid uptake and metabolism as well as activated microglia can detect interictal or peri-ictal cortical increased uptake (as compared to non-epileptic cortex) associated with tumor-associated epilepsy. Metabolic tumor volumes may predict seizure outcome based on objective treatment response during glioma chemotherapy. Advanced MRI, especially glutamate imaging, can detect neurotransmitter changes around epileptogenic brain tumors. Recently, developed PET radiotracers targeting specific glutamate receptor types may also identify therapeutic targets for pharmacologic seizure control. Further studies with advanced multimodal imaging approaches may facilitate development of precision treatment strategies to control brain tumor-associated epilepsy.

Multimodal neuroimaging of gliomatosis cerebri: a case series of four patients.

In the latest World Health Organization classification of brain tumors, gliomatosis cerebri has been redefined to varying subsets of diffuse gliomas; however, the term is still used to describe gliomas with infiltrative growth into three or more cerebral lobes. These tumors are frequently misdiagnosed and difficult to treat due to their atypical presentation using structural imaging modalities including computed tomography and T1/T2-weighted magnetic resonance imaging (MRI). In this retrospective case series, we compared clinical MRI to amino acid positron emission tomography (PET) to assess the potential value of PET in the assessment of the extent of tumor involvement and in monitoring disease progression. We report the clinical course and serial multimodal imaging findings of four patients. Each patient presented at varying points in disease progression with widespread glioma brain involvement and was evaluated at least once by amino acid PET using alpha-[11C]methyl-L-tryptophan ([11C]-AMT). Increased uptake of [11C]-AMT was detected in a subset of non-enhancing brain lesions and detected tumor invasion before MRI signs of tumor in some regions. Increased uptake of [11C]-AMT was also detected in tumorous regions not detected by perfusion MRI or MR spectroscopy. Metabolic response to treatment was also observed in two patients. Overall, these data are consistent with and expand upon previous reports using other amino acid PET tracers in gliomatosis and show the potential added value of this imaging modality to clinical MRI in the detection and monitoring of these diffusely infiltrative tumors.

Decreased Expression of ZNF554 in Gliomas is Associated with the Activation of Tumor Pathways and Shorter Patient Survival.

Zinc finger protein 554 (ZNF554), a member of the Krüppel-associated box domain zinc finger protein subfamily, is predominantly expressed in the brain and placenta in humans. Recently, we unveiled that ZNF554 regulates trophoblast invasion during placentation and its decreased expression leads to the early pathogenesis of preeclampsia. Since ZNF proteins are immensely implicated in the development of several tumors including malignant tumors of the brain, here we explored the pathological role of ZNF554 in gliomas. We examined the expression of ZNF554 at mRNA and protein levels in normal brain and gliomas, and then we searched for genome-wide transcriptomic changes in U87 glioblastoma cells transiently overexpressing ZNF554. Immunohistochemistry of brain tissues in our cohort (n = 62) and analysis of large TCGA RNA-Seq data (n = 687) of control, oligodendroglioma, and astrocytoma tissues both revealed decreased expression of ZNF554 towards higher glioma grades. Furthermore, low ZNF554 expression was associated with shorter survival of grade III and IV astrocytoma patients. Overexpression of ZNF554 in U87 cells resulted in differential expression, mostly downregulation of 899 genes. The "PI3K-Akt signaling pathway", known to be activated during glioma development, was the most impacted among 116 dysregulated pathways. Most affected pathways were cancer-related and/or immune-related. Congruently, cell proliferation was decreased and cell cycle was arrested in ZNF554-transfected glioma cells. These data collectively suggest that ZNF554 is a potential tumor suppressor and its decreased expression may lead to the loss of oncogene suppression, activation of tumor pathways, and shorter survival of patients with malignant glioma.

Novel Deep Learning Network Analysis of Electrical Stimulation Mapping-Driven Diffusion MRI Tractography to Improve Preoperative Evaluation of Pediatric Epilepsy.

OBJECTIVE: To investigate the clinical utility of deep convolutional neural network (DCNN) tract classification as a new imaging tool in the preoperative evaluation of children with focal epilepsy (FE). METHODS: A DCNN tract classification deeply learned spatial trajectories of DWI white matter pathways linking electrical stimulation mapping (ESM) findings from 89 children with FE, and then automatically identified white matter pathways associated with eloquent functions (i.e., primary motor, language, and vision). Clinical utility was examined by 1) measuring the nearest distance between DCNN-determined pathways and ESM, 2) evaluating the effectiveness of DCNN-determined pathways to optimize surgical margins via Kalman filter analysis, and 3) evaluating how accurately changes in DCNN-determined language pathway volume can predict changes in language ability via canonical correlation analysis. RESULTS: DCNN tract classification outperformed other existing methods, achieving an excellent accuracy of 98 % while non-invasively detecting eloquent areas within the spatial resolution of ESM (i.e., 1 cm). The Kalman filter analysis found that the preservation of brain areas within a surgical margin determined by DCNN tract classification predicted lack of postoperative deficit with a high accuracy of 92 %. Postoperative change of DCNN-determined language pathway volume showed a significant correlation with postoperative changes in language ability (R = 0.7, p   0.001). CONCLUSION: Our findings demonstrate that postoperative functional deficits substantially differ according to the extent of resected white matter, and that DCNN tract classification may offer key translational information by identifying these pathways in pediatric epilepsy surgery. SIGNIFICANCE: DCNN tract classification may be an effective tool to improve surgical outcome of children with FE.