Automated identification and quantification of metastatic brain tumors and perilesional edema based on a deep learning neural network.

PURPOSE: This paper presents a deep learning model for use in the automated segmentation of metastatic brain tumors and associated perilesional edema. METHODS: The model was trained using Gamma Knife surgical data (90 MRI sets from 46 patients), including the initial treatment plan and follow-up images (T1-weighted contrast-enhanced (T1cWI) and T2-weighted images (T2WI)) manually annotated by neurosurgeons to indicate the target tumor and edema regions. A mask region-based convolutional neural network was used to extract brain parenchyma, after which the DeepMedic 3D convolutional neural network was in the segmentation of tumors and edemas. RESULTS: Five-fold cross-validation demonstrated the efficacy of the brain parenchyma extraction model, achieving a Dice similarity coefficient of 96.4%. The segmentation models used for metastatic tumors and brain edema achieved Dice similarity coefficients of 71.6% and 85.1%, respectively. This study also presents an intuitive graphical user interface to facilitate the use of these models in clinical analysis. CONCLUSION: This paper introduces a deep learning model for the automated segmentation and quantification of brain metastatic tumors and perilesional edema trained using only T1cWI and T2WI. This technique could facilitate further research on metastatic tumors and perilesional edema as well as other intracranial lesions.

Application of artificial intelligence to stereotactic radiosurgery for intracranial lesions: detection, segmentation, and outcome prediction.

BACKGROUND: Rapid evolution of artificial intelligence (AI) prompted its wide application in healthcare systems. Stereotactic radiosurgery served as a good candidate for AI model development and achieved encouraging result in recent years. This article aimed at demonstrating current AI application in radiosurgery. METHODS: Literatures published in PubMed during 2010-2022, discussing AI application in stereotactic radiosurgery were reviewed. RESULTS: AI algorithms, especially machine learning/deep learning models, have been administered to different aspect of stereotactic radiosurgery. Spontaneous tumor detection and automated lesion delineation or segmentation were two of the promising application, which could be further extended to longitudinal treatment follow-up. Outcome prediction utilized machine learning algorithms with radiomic-based analysis was another well-established application. CONCLUSIONS: Stereotactic radiosurgery has taken a lead role in AI development. Current achievement, limitation, and further investigation was summarized in this article.

Functional connectivity analysis on electroencephalography signals reveals potential biomarkers for treatment response in major depression.

BACKGROUND: The treatment efficacy varies across individual patients with major depressive disorder (MDD). It lacks robust electroencephalography (EEG) markers for an antidepressant-responsive phenotype. METHOD: This is an observational study enrolling 28 patients with MDD and 33 healthy controls (mean age of 40.7 years, and 71.4% were women). Patients underwent EEG exams at baseline (week0) and week1, while controls' EEG recordings were acquired only at week0. A resting eye-closing EEG segment was analyzed for functional connectivity (FC). Four parameters were used in FC analysis: (1) node strength (NS), (2) global efficiency (GE), (3) clustering coefficient (CC), and (4) betweenness centrality (BC). RESULTS: We found that controls had higher values in delta wave in the indices of NS, GE, BC, and CC than MDD patients at baseline. After treatment with antidepressants, patients' FC indices improved significantly, including GE, mean CC, and mean NS in the delta wave. The FC in the alpha and beta bands of the responders were higher than those of the non-responders. CONCLUSIONS: The FC of the MDD patients at baseline without treatment was worse than that of controls. After treatment, the FC improved and was close to the values of controls. Responders showed better FC in the high-frequency bands than non-responders, and this feature exists in both pre-treatment and post-treatment EEG.

Pilot study of focused ultrasound for drug-resistant epilepsy.

OBJECTIVE: The neuromodulatory effects of focused ultrasound (FUS) have been demonstrated in animal epilepsy models; however, the safety and efficacy of FUS in humans with epilepsy have not been well established. Patients with drug-resistant epilepsy (DRE) undergoing stereo-electroencephalography (SEEG) provide an opportunity to investigate the neuromodulatory effects of FUS in humans. METHODS: Patients with DRE undergoing SEEG for localization of the seizure onset zone (SOZ) were prospectively enrolled. FUS was delivered to the SOZ using a neuronavigation-guided FUS system (ceiling spatial-peak temporal-average intensity level = 2.8 W/cm2 , duty cycle = 30%, modulating duration = 10 min). Simultaneous SEEG recordings were obtained during sonication and for 3 days after treatment. Seizures, interictal epileptiform discharges, and adverse events after FUS were monitored. RESULTS: Six patients met the eligibility criteria and completed FUS treatment. A decrease in seizure frequency was observed in two patients within the 3-day follow-up; however, one patient presented an increase in the frequency of subclinical seizures. Posttreatment magnetic resonance imaging revealed neither lesion nor brain edema. Significant changes in spectral power of SEEG were noted at the targeted electrodes during FUS treatment. One patient reported subjective scalp heating during FUS, and one patient developed transient naming and memory impairment that resolved within 3 weeks after FUS. SIGNIFICANCE: FUS can be safely delivered to the SOZ of patients with DRE, resulting in significant changes in spectral power of SEEG. A larger sample cohort and pursuing optimal sonication parameters will be required to elucidate the neuromodulatory effects of FUS when used for seizure control.

Clinical characteristics and long-term outcome of cerebral cavernous malformations-related epilepsy.

OBJECTIVE: Cerebral cavernous malformations (CCMs) present variably, and epileptic seizures are the most common symptom. The factors contributing to cavernoma-related epilepsy (CRE) and drug resistance remain inconclusive. The outcomes of CRE after different treatment modalities have not yet been fully addressed. This study aimed to characterize the clinical features of patients with CRE and the long-term seizure outcomes of medical and surgical treatment strategies. METHODS: This was a retrospective cohort of 135 patients with CCM who were diagnosed in 2007-2011 and followed up for 93.6 months on average. The patients were divided into drug-resistant epilepsy (DRE; n = 29), non-DRE (n = 45), and no epilepsy (NE; n = 61). RESULTS: Temporal CCM was the factor most strongly associated with the development of both CRE and DRE. The majority of patients with single temporal CCMs had CRE (86.8%, n = 33), and 50% had DRE, whereas only 14.7% (n = 5) with a nontemporal supratentorial CCM had DRE (p < .05). The most common lesion site in the DRE group was the mesiotemporal lobe (50%). Multiple CCMs were more frequently observed in the CRE (29.2%) than the NE (11.5%) group (p < .05). In patients with CRE, multiple lesions were associated with a higher rebleeding rate (odds ratio = 11.1), particularly in those with DRE (odds ratio = 15.4). The majority of patients who underwent resective surgery for DRE (76.5%, n = 13) achieved International League Against Epilepsy Class I and II seizure outcomes even after a long disease course. SIGNIFICANCE: Temporal CCM not only predisposes to CRE but also is a major risk factor for drug resistance. The mesiotemporal lobe is the most epileptogenic zone. Multiple CCMs are another risk factor for CRE and increase the rebleeding risk in these patients. Surgical resection could provide beneficial long-term seizure outcomes in patients with DRE.

Does the Diffuseness of the Nidus Affect the Outcome of Stereotactic Radiosurgery in Patients with Unruptured Cerebral Arteriovenous Malformations?

BACKGROUND: We proposed an algorithm to automate the components within the identification of components within the nidus of cerebral arteriovenous malformations (AVMs) which may be used to analyze the relationship between its diffuseness and treatment outcomes following stereotactic radiosurgery (SRS). OBJECTIVES: to determine the impact of the diffuseness of the AVM nidus on SRS outcomes. METHODS: This study conducted regular follow-ups of 209 patients with unruptured AVMs who underwent SRS. The diffuseness of the AVM nidus was estimated by quantifying the proportions of vascular nidal component, brain parenchyma, and cerebrospinal fluid in T2-weighted MRIs. We used Cox regression analysis to characterize the association between nidal diffuseness and treatment outcomes in terms of obliteration rate and radiation-induced change (RICs) rate following SRS. RESULTS: The median AVM volume was 20.7 cm3. The median duration of imaging follow-up was 51 months after SRS. The overall AVM obliteration rate was 68.4%. RICs were identified in 156 of the 209 patients (74.6%). The median proportions of the nidus of AVM and brain parenchyma components within the prescription isodose range were 30.2 and 52.2%, respectively. Cox regression multivariate analysis revealed that the only factor associated with AVM obliteration rate after SRS was AVM volume. However, a larger AVM volume (>20 mL) and a larger proportion of brain parenchyma (>50%) within the prescription isodose range were both correlated with a higher RIC rate following SRS. CONCLUSIONS: The diffuseness of the nidus indeed appears to affect the RIC rate following SRS in patients with unruptured AVMs.

Quantitative analysis of intraoperative electrocorticography mirrors histopathology and seizure outcome after epileptic surgery in children.

BACKGROUND: Epileptic surgery is the potentially curative treatment for children with refractory seizures. The study aimed to quantify and analyze high frequency oscillation (HFO) ripples and interictal epileptiform discharges (EDs) in intraoperative electrocorticography (ECoG) between malformation of cortical dysplasia (MCD) and non-MCD children with MRI-lesional focal epilepsy, and evaluate of seizure outcomes after epileptic surgery. METHODS: The intraoperative ECoG was performed before and after lesionectomy. Quantifications of HFO ripples and interictal EDs of ECoG by frequency, amplitude, and foci of intraoperative ECoG were performed based on electrode location, and the characteristics of ECoG recordings were analyzed in each patient based on their histopathology. Seizure outcome after surgery according to their quantitative ECoG findings was analyzed. RESULTS: Frequency of EDs and HFO ripple rates in preresection ECoG were significantly higher in children with MCD compared with non-MCD (p = 0.018 and p = 0.002, respectively). Higher frequencies of EDs and ripple rates in preresection ECoG were observed in residual seizures than in seizure-free children (p = 0.045 and p = 0.005, respectively). Clinically, children with residual seizures after surgery were significantly younger at the onset, had a trend of higher seizure frequency and higher spike frequency of presurgical videoEEG. CONCLUSION: Our results suggested that quantification of intraoperative ECoG predicted seizure outcomes and reflected different ED pattern and frequencies between MCD and non-dysplastic histopathology among children who underwent resective epileptic surgery. The results of our study were encouraging and indicated that intraoperative ECoG improved the outcomes of surgery in children with epilepsy.

Radiomics as prognostic factor in brain metastases treated with Gamma Knife radiosurgery.

PURPOSE: Gamma Knife radiosurgery (GKRS) is a non-invasive procedure for the treatment of brain metastases. This study sought to determine whether radiomic features of brain metastases derived from pre-GKRS magnetic resonance imaging (MRI) could be used in conjunction with clinical variables to predict the effectiveness of GKRS in achieving local tumor control. METHODS: We retrospectively analyzed 161 patients with non-small cell lung cancer (576 brain metastases) who underwent GKRS for brain metastases. The database included clinical data and pre-GKRS MRI. Brain metastases were demarcated by experienced neurosurgeons, and radiomic features of each brain metastasis were extracted. Consensus clustering was used for feature selection. Cox proportional hazards models and cause-specific proportional hazards models were used to correlate clinical variables and radiomic features with local control of brain metastases after GKRS. RESULTS: Multivariate Cox proportional hazards model revealed that higher zone percentage (hazard ratio, HR 0.712; P = .022) was independently associated with superior local tumor control. Similarly, multivariate cause-specific proportional hazards model revealed that higher zone percentage (HR 0.699; P = .014) was independently associated with superior local tumor control. CONCLUSIONS: The zone percentage of brain metastases, a radiomic feature derived from pre-GKRS contrast-enhanced T1-weighted MRIs, was found to be an independent prognostic factor of local tumor control following GKRS in patients with non-small cell lung cancer and brain metastases. Radiomic features indicate the biological basis and characteristics of tumors and could potentially be used as surrogate biomarkers for predicting tumor prognosis following GKRS.

Cingulate gyrus epilepsy: semiology, invasive EEG, and surgical approaches.

OBJECTIVE: The semiology of cingulate gyrus epilepsy is varied and may involve the paracentral area, the adjacent limbic system, and/or the orbitofrontal gyrus. Invasive electroencephalography (iEEG) recording is usually required for patients with deeply located epileptogenic foci. This paper reports on the authors' experiences in the diagnosis and surgical treatment of patients with focal epilepsy originating in the cingulate gyrus. METHODS: Eighteen patients (median age 24 years, range 5-53 years) with a mean seizure history of 23 years (range 2-32 years) were analyzed retrospectively. The results of presurgical evaluation, surgical strategy, and postoperative pathology are reported, as well as follow-up concerning functional morbidity and seizures (median follow-up 7 years, range 2-12 years). RESULTS: Patients with cingulate gyrus epilepsy presented with a variety of semiologies and scalp EEG patterns. Prior to ictal onset, 11 (61%) of the patients presented with aura. Initial ictal symptoms included limb posturing in 12 (67%), vocalization in 5, and hypermotor movement in 4. In most patients (n = 16, 89%), ictal EEG presented as widespread patterns with bilateral hemispheric origin, as well as muscle artifacts obscuring the onset of EEG during the ictal period in 11 patients. Among the 18 patients who underwent resection, the pathology revealed mild malformation of cortical development in 2, focal cortical dysplasia (FCD) Ib in 4, FCD IIa in 4, FCD IIb in 4, astrocytoma in 1, ganglioglioma in 1, and gliosis in 2. The seizure outcome after surgery was satisfactory: Engel class IA in 12 patients, IIB in 3, IIIA in 1, IIIB in 1, and IVB in 1 at the 2-year follow-up. CONCLUSIONS: In this study, the authors exploited the improved access to the cingulate epileptogenic network made possible by the use of 3D electrodes implanted using stereoelectroencephalography methodology. Under iEEG recording and intraoperative neuromonitoring, epilepsy surgery on lesions in the cingulate gyrus can result in good outcomes in terms of seizure recurrence and the incidence of postoperative permanent deficits.

Early recovery of interhemispheric functional connectivity after corpus callosotomy.

OBJECTIVE: To investigate whether interhemispheric functional connectivity (FC) recovers in the first year after total callosotomy. METHODS: Eight epilepsy patients undergoing total callosotomy were recruited. Resting-state functional magnetic resonance imaging was acquired before and after surgery. The precallosotomy and postcallosotomy interhemispheric and intrahemispheric FC was analyzed by using graph theory and voxel-mirrored homotopic connectivity (VMHC). The seizure outcome was scored using the Engel surgical outcome scale. RESULTS: After callosotomy (mean postoperative interval = 4 months), the network density, average node degree, characteristic path length, and global efficiency of the whole interhemispheric networks were significantly decreased, compared to those in the precallosotomy networks. However, postcallosotomy interhemispheric FC and homotopic VMHC were not significantly reduced in bilateral frontal and temporal lobes. The network density and average node degree of the intrahemispheric networks were significantly increased. The characteristic path length and global efficiency of intrahemispheric networks were unchanged. SIGNIFICANCE: The interhemispheric FC may be preserved or recover early within the first postoperative year after total callosotomy, particularly in the frontal and anterior temporal lobes.

Ictal-Interictal Comparison of FDG-PET Findings in Sporadic Hemiplegic Migraine.

PURPOSE: Sporadic hemiplegic migraine (SHM) is characterized by a prolonged motor aura that accompanies a migraine attack, and its underlying pathophysiology remains unclear. Functional image during the event can help to explore the mechanism. CASE REPORT: We report a finding of 18-fluorodeoxyglucose positron emission tomography (FDG-PET) in a 15-year-old female with SHM. She presented with recurrent right arm weakness and pain with migrainous headache. A video electroencephalogram showed no evidence of epilepsy during the events. Subtraction of ictal-interictal FDG-PET coregistered to magnetic resonance imaging was performed for the image analysis. In comparison with the interictal state, the FDG-PET image showed decreased glucose metabolism in the bilateral dorsal lateral frontal cortices and bilateral occipital cortices, whereas increased metabolism in the left precentral motor cortex and right premotor cortex. CONCLUSION: These findings reveal an increase in metabolism in the motor cortex during general cortical dysfunction in the frontal and occipital cortices in SHM. Key words: FDG-PET, hemiplegic migraine, migraine, positron emission tomography, SISCOM.

Evaluation of subcortical grey matter abnormalities in patients with MRI-negative cortical epilepsy determined through structural and tensor magnetic resonance imaging.

BACKGROUND: Although many studies have found abnormalities in subcortical grey matter (GM) in patients with temporal lobe epilepsy or generalised epilepsies, few studies have examined subcortical GM in focal neocortical seizures. Using structural and tensor magnetic resonance imaging (MRI), we evaluated subcortical GM from patients with extratemporal lobe epilepsy without visible lesion on MRI. Our aims were to determine whether there are structural abnormalities in these patients and to correlate the extent of any observed structural changes with clinical characteristics of disease in these patients. METHODS: Twenty-four people with epilepsy and 29 age-matched normal subjects were imaged with high-resolution structural and diffusion tensor MR scans. The patients were characterised clinically by normal brain MRI scans and seizures that originated in the neocortex and evolved to secondarily generalised convulsions. We first used whole brain voxel-based morphometry (VBM) to detect density changes in subcortical GM. Volumetric data, values of mean diffusivity (MD) and fractional anisotropy (FA) for seven subcortical GM structures (hippocampus, caudate nucleus, putamen, globus pallidus, nucleus accumbens, thalamus and amygdala) were obtained using a model-based segmentation and registration tool. Differences in the volumes and diffusion parameters between patients and controls and correlations with the early onset and progression of epilepsy were estimated. RESULTS: Reduced volumes and altered diffusion parameters of subcortical GM were universally observed in patients in the subcortical regions studied. In the patient-control group comparison of VBM, the right putamen, bilateral nucleus accumbens and right caudate nucleus of epileptic patients exhibited a significantly decreased density Segregated volumetry and diffusion assessment of subcortical GM showed apparent atrophy of the left caudate nucleus, left amygdala and right putamen; reduced FA values for the bilateral nucleus accumbens; and elevated MD values for the left thalamus, right hippocampus and right globus pallidus A decreased volume of the nucleus accumbens consistently related to an early onset of disease. The duration of disease contributed to the shrinkage of the left thalamus. CONCLUSIONS: Patients with neocortical seizures and secondary generalisation had smaller volumes and microstructural anomalies in subcortical GM regions. Subcortical GM atrophy is relevant to the early onset and progression of epilepsy.

Investigation of Subcortical Gray Matter in Patients with Non-lesional Neocortical Focal Epilepsy.

PURPOSE: To investigate whether there is any change in the subcortical gray matter of patients with neocortical focal epilepsy without visible magnetic resonance imaging (MRI) abnormalities. METHODS: MRI morphometric parameter data from 24 patients and 29 neurologically normal controls were analyzed. All of the MRI scans were reported to have no any anomaly. Differences were evaluated by vertex-wise shape analysis. RESULTS: A shape analysis showed significant surface reductions at the anterior-ventral and the posteriordorsal aspects of the bilateral thalami, the global left caudate nucleus, part of the bilateral dorsal putamen and the left hippocampus. CONCLUSION: Patients with focal seizures and secondary generalization had smaller volumes and microstructural anomalies in subcortical gray matter regions.

Glucose Metabolism of Hippocampal Subfields in Medial Temporal Lobe Epilepsy.

PURPOSE: Reduced glucose metabolism in the hippocampus is commonly observed in cases of medial temporal lobe epilepsy (MTLE) with hippocampal sclerosis (HS). Glucose metabolism among the various hippocampal subfields has not been thoroughly investigated. PATIENTS AND METHODS: This study examined 29 patients (18 females; 15-58 years) diagnosed with HS who underwent surgery for drug-resistant epilepsy. FreeSurfer 7.1.1 was used in the processing of MRI data and 18 F-FDG PET scans to derive volumetric data and the FDG SUVr in the whole hippocampus and hippocampal subfields, including the CA1, CA2-4, granule cell and molecular layer of the dentate gyrus (GC-ML-DG), and subiculum. Asymmetries in the volume and SUVr between the 2 sides from the subfields of the hippocampus were defined in terms of an asymmetry index. Comparisons of the asymmetry index among these regions were performed. The correlations between asymmetry index values and postoperative outcomes and presurgical neuropsychological test results were also evaluated. RESULT: The CA1, CA2-4, subiculum, GC-ML-DG, and whole hippocampus presented reductions in volume and hypometabolism ipsilateral to MTLE. Asymmetries in volume and SUVr were significantly less pronounced in the CA1 and subiculum than in the CA2-4 or GC-ML-DG. Postoperative seizure outcomes were not correlated with the asymmetry index for volume or SUVr in any hippocampal subfield. In cases of left MTLE, scores of immediate logical memory and delayed logical memory were positively correlated with the asymmetry index for SUVr in the following subfields: CA1 ( R = 0.829, P = 0.021; R = 0.770, P = 0.043), CA2-4 ( R = 0.825, P = 0.022; R = 0.894, P = 0.007), subiculum ( R = 0.882, P = 0.009; R = 0.853, P = 0.015), GC-ML-DG ( R = 0.850, P = 0.015; R = 0.796, P = 0.032), and whole hippocampus ( R = 0.841, P = 0.018; R = 0.822, P = 0.023). In cases of right MTLE, the scores for delayed face memory were positively correlated with the asymmetry index for SUVr in the subiculum ( R = 0.935, P = 0.006). CONCLUSIONS: In cases of HS, changes in glucose metabolism levels varied among the hippocampal subfields. Asymmetries in glucose metabolism among the CA-1, CA2-4, subiculum, and GC-ML-DG subregions were correlated with scores for verbal memory among patients with left MTLE. Asymmetric glucose metabolism in the subiculum was also correlated with visual memory scores among patients with right MTLE.

Antiseizure Medications Normalize Electroencephalographic Functional Connectivity and Power in Children With Benign Epilepsy With Centrotemporal Spikes.

BACKGROUND: The decision to treat children with benign epilepsy with centrotemporal spikes (BECTS) using antiseizure medications (ASM) is controversial. Our goal is to compare the effect of ASM treatment on the alteration of electroencephalographic (EEG) functional connectivity and power across four frequency bands in children with BECTS. METHODS: Children with BECTS with two-year follow-up were retrospectively divided into ASM versus non-ASM groups. The network properties of the EEGs as based on network-based statistic and graph theory were evaluated by the following indices: global efficiency, clustering coefficient, betweenness centrality, and nodal strength in four frequency bands (delta, theta, alpha, and beta). EEG power including absolute power (AP) and relative power (RP) was analyzed in four frequency bands. RESULTS: In children with BECTS with ASM treatment, there was no significant change in EEG connectivity across all bands before and after two years of ASM. In children with BECTS without ASM treatment, there was a significant increase of global efficiency, clustering coefficient, and nodal strength but not the betweenness centrality in the delta band after two years of follow-up. A decrease in AP in the delta and theta bands and a decrease in RP in the theta band were found in the ASM group after two years of treatment. CONCLUSIONS: Our results suggest that ASM may play a role in modulating the development of increasing overall brain connectivity and in downregulating overt synaptic activity, but not intrinsic focal connectivity, in the early years of BECTS. The changes in the EEG power indicate that ASM significantly normalized slow-wave band power.

Vascular compactness of unruptured brain arteriovenous malformation predicts risk of hemorrhage after stereotactic radiosurgery.

The aim of the study was to investigate whether morphology (i.e. compact/diffuse) of brain arteriovenous malformations (bAVMs) correlates with the incidence of hemorrhagic events in patients receiving Stereotactic Radiosurgery (SRS) for unruptured bAVMs. This retrospective study included 262 adult patients with unruptured bAVMs who underwent upfront SRS. Hemorrhagic events were defined as evidence of blood on CT or MRI. The morphology of bAVMs was evaluated using automated segmentation which calculated the proportion of vessel, brain tissue, and cerebrospinal fluid in bAVMs on T2-weighted MRI. Compactness index, defined as the ratio of vessel to brain tissue, categorized bAVMs into compact and diffuse types based on the optimal cutoff. Cox proportional hazard model was used to identify the independent factors for post-SRS hemorrhage. The median clinical follow-ups was 62.1 months. Post-SRS hemorrhage occurred in 13 (5.0%) patients and one of them had two bleeds, resulting in an annual bleeding rate of 0.8%. Multivariable analysis revealed bAVM morphology (compact versus diffuse), bAVM volume, and prescribed margin dose were significant predictors. The post-SRS hemorrhage rate increased with larger bAVM volume only among the diffuse nidi (1.7 versus 14.9 versus 30.6 hemorrhage per 1000 person-years in bAVM volume < 20 cm3 versus 20-40 cm3 versus > 40 cm3; p = 0.022). The significantly higher post-SRS hemorrhage rate of Spetzler-Martin grade IV-V compared with grade I-III bAVMs (20.0 versus 3.3 hemorrhages per 1000 person-years; p = 0.001) mainly originated from the diffuse bAVMs rather than the compact subgroup (30.9 versus 4.8 hemorrhages per 1000 person-years; p = 0.035). Compact and smaller bAVMs, with higher prescribed margin dose harbor lower risks of post-SRS hemorrhage. The post-SRS hemorrhage rate exceeded 2.2% annually within the diffuse and large (> 40 cm3) bAVMs and the diffuse Spetzler-Martin IV-V bAVMs. These findings may help guide patient selection of SRS for the unruptured bAVMs.

Connectome-based predictive modeling for functional recovery of acute ischemic stroke.

Patients of acute ischemic stroke possess considerable chance of recovery of various levels in the first several weeks after stroke onset. Prognosis of functional recovery is important for decision-making in poststroke patient care and placement. Poststroke functional recovery has conventionally been based on demographic and clinical variables such as age, gender, and severity of stroke impairment. On the other hand, the concept of connectome has become a basis of interpreting the functional impairment and recovery of stroke patients. In this research, the connectome-based predictive modeling was used to provide predictive models for prognosing poststroke functional recovery. Predictive models were developed to use the brain connectivity at stroke onset to predict functional assessment scores at one or three months later, or to use the brain connectivity one-month poststroke to predict functional assessment scores at three months after stroke onset. The brain connectivity was computed from the resting-state fMRI signals. The functional assessment scores used in this research included modified Rankin Scale (mRS) and Barthel Index (BI). This research found significant models that used the brain connectivity at onset to predict the mRS one-month poststroke and to predict the BI three-month poststroke for patients with supratentorial infarction, as well as predictive models that used the brain connectivity one-month poststroke to predict the mRS three-month poststroke for patients with supratentorial infarction in the right hemisphere. The connectome-based predictive modeling could provide clinical value in prognosis of acute ischemic stroke.

Identification of tophi in ultrasound imaging based on transfer learning and clinical practice.

Gout is a common metabolic disorder characterized by deposits of monosodium urate monohydrate crystals (tophi) in soft tissue, triggering intense and acute arthritis with intolerable pain as well as articular and periarticular inflammation. Tophi can also promote chronic inflammatory and erosive arthritis. 2015 ACR/EULAR Gout Classification criteria include clinical, laboratory, and imaging findings, where cases of gout are indicated by a threshold score of ≥ 8. Some imaging-related findings, such as a double contour sign in ultrasound, urate in dual-energy computed tomography, or radiographic gout-related erosion, generate a score of up to 4. Clearly, the diagnosis of gout is largely assisted by imaging findings; however, dual-energy computed tomography is expensive and exposes the patient to high levels of radiation. Although musculoskeletal ultrasound is non-invasive and inexpensive, the reliability of the results depends on expert experience. In the current study, we applied transfer learning to train a convolutional neural network for the identification of tophi in ultrasound images. The accuracy of predictions varied with the convolutional neural network model, as follows: InceptionV3 (0.871 ± 0.020), ResNet101 (0.913 ± 0.015), and VGG19 (0.918 ± 0.020). The sensitivity was as follows: InceptionV3 (0.507 ± 0.060), ResNet101 (0.680 ± 0.056), and VGG19 (0.747 ± 0.056). The precision was as follows: InceptionV3 (0.767 ± 0.091), ResNet101 (0.863 ± 0.098), and VGG19 (0.825 ± 0.062). Our results demonstrate that it is possible to retrain deep convolutional neural networks to identify the patterns of tophi in ultrasound images with a high degree of accuracy.

Morphological and metabolic asymmetries of the thalamic subregions in temporal lobe epilepsy predict cognitive functions.

Both morphological and metabolic imaging were used to determine how asymmetrical changes of thalamic subregions are involved in cognition in temporal lobe epilepsy (TLE). We retrospectively recruited 24 left-TLE and 15 right-TLE patients. Six thalamic subnuclei were segmented by magnetic resonance imaging, and then co-registered onto Positron emission tomography images. We calculated the asymmetrical indexes of the volumes and normalized standard uptake value ratio (SUVR) of the entire and individual thalamic subnuclei. The SUVR of ipsilateral subnuclei were extensively and prominently decreased compared with the volume loss. The posterior and medial subnuclei had persistently lower SUVR in both TLE cases. Processing speed is the cognitive function most related to the metabolic asymmetry. It negatively correlated with the metabolic asymmetrical indexes of subregions in left-TLE, while positively correlated with the subnuclei volume asymmetrical indexes in right-TLE. Epilepsy duration negatively correlated with the volume asymmetry of most thalamic subregions in left-TLE and the SUVR asymmetry of ventral and intralaminar subnuclei in right-TLE. Preserved metabolic activity of contralateral thalamic subregions is the key to maintain the processing speed in both TLEs. R-TLE had relatively preserved volume of the ipsilateral thalamic volume, while L-TLE had relatively decline of volume and metabolism in posterior subnucleus.

Compactness index: a radiosurgery outcome predictor for patients with unruptured brain arteriovenous malformations.

OBJECTIVE: The goal of the study was to define and quantify brain arteriovenous malformation (bAVM) compactness and to assess its effect on outcomes after Gamma Knife radiosurgery (GKRS) for unruptured bAVMs. METHODS: Unsupervised machine learning with fuzzy c-means clustering was used to differentiate the tissue constituents of bAVMs on T2-weighted MR images. The percentages of vessel, brain, and CSF were quantified. The proposed compactness index, defined as the ratio of vasculature tissue to brain tissue, categorized bAVM morphology into compact, intermediate, and diffuse types according to the tertiles of this index. The outcomes of interest were complete obliteration and radiation-induced changes (RICs). RESULTS: A total of 209 unruptured bAVMs treated with GKRS were retrospectively included. The median imaging and clinical follow-up periods were 49.2 and 72.3 months, respectively. One hundred seventy-three bAVMs (82.8%) achieved complete obliteration after a median latency period of 43.3 months. The rates of RIC and permanent RIC were 76.1% and 3.8%, respectively. Post-GKRS hemorrhage occurred in 14 patients (6.7%), resulting in an annual bleeding risk of 1.0%. Compact bAVM, smaller bAVM volume, and exclusively superficial venous drainage were independent predictors of complete obliteration. Diffuse bAVM morphology, larger bAVM volume, and higher margin dose were independently associated with RICs. CONCLUSIONS: The compactness index quantitatively describes the compactness of unruptured bAVMs. Moreover, compact bAVMs may have a higher obliteration rate and a smaller risk of RICs than diffuse bAVMs. This finding could help guide decision-making regarding GKRS treatment for patients with unruptured bAVMs.