scholarly journals Deep Learning provides exceptional accuracy to ECoG-based Functional Language Mapping for epilepsy surgery

2018 ◽  
Author(s):  
Harish RaviPrakash ◽  
Milena Korostenskaja ◽  
Eduardo M. Castillo ◽  
Ki H. Lee ◽  
Christine M. Salinas ◽  
...  
Keyword(s):  
Deep Learning ◽  
Epilepsy Surgery ◽  
Brain Regions ◽  
Language Mapping ◽  
Surgical Morbidity ◽  
Brain Surface ◽  
Alternative Approach ◽  
Increased Risk ◽  
Eloquent Cortex ◽  
Cortical Stimulation Mapping

AbstractThe success of surgical resection in epilepsy patients depends on preserving functionally critical brain regions, while removing pathological tissues. Being the gold standard, electro-cortical stimulation mapping (ESM) helps surgeons in localizing the function of eloquent cortex through electrical stimulation of electrodes placed directly on the cortical brain surface. Due to the potential hazards of ESM, including increased risk of provoked seizures, electrocorticography based functional mapping (ECOG-FM) was introduced as a safer alternative approach. However, ECoG-FM has a low success rate when compared to the ESM. In this study, we address this critical limitation by developing a new algorithm based on deep learning for ECoG-FM and thereby we achieve an accuracy comparable to ESM in identifying eloquent language cortex. In our experiments, with 11 epilepsy patients who underwent presurgical evaluation (through deep learning-based signal analysis on 637 electrodes), our proposed algorithm made an exceptional 23% improvement with respect to the conventional ECoG-FM analysis (∼60%). We obtained the state-of-the-art accuracy of 83.05% in identifying language regions, which has never been achieved before. Our findings have demonstrated, for the first time, that deep learning powered ECoG-FM can serve as a stand-alone modality and avoid likely hazards of the ESM in epilepsy surgery. Hence, reducing the potential for developing post-surgical morbidity in the language function.

scholarly journals Deep Learning Provides Exceptional Accuracy to ECoG-Based Functional Language Mapping for Epilepsy Surgery

2020 ◽  
Vol 14 ◽  
Author(s):  
Harish RaviPrakash ◽  
Milena Korostenskaja ◽  
Eduardo M. Castillo ◽  
Ki H. Lee ◽  
Christine M. Salinas ◽  
...  
Keyword(s):  
Deep Learning ◽  
Epilepsy Surgery ◽  
Functional Language ◽  
Language Mapping

Stereotactic radiosurgery for metastatic brain tumors: a comprehensive review of complications

2009 ◽  
Vol 111 (3) ◽  
pp. 439-448 ◽  
Author(s):  
Brian J. Williams ◽  
Dima Suki ◽  
Benjamin D. Fox ◽  
Christopher E. Pelloski ◽  
Marcos V. C. Maldaun ◽  
...  
Keyword(s):  
Multivariate Analysis ◽  
Brain Metastases ◽  
Stereotactic Radiosurgery ◽  
Neurological Complications ◽  
Brain Regions ◽  
Tumor Location ◽  
Cancer Center ◽  
Primary Cancer ◽  
Increased Risk ◽  
Eloquent Cortex

Object Stereotactic radiosurgery (SRS) is commonly used to treat brain metastases. Complications associated with this treatment are underreported. The authors reviewed a large series of patients who underwent SRS for brain metastases to identify complications and factors predicting their occurrence. Methods Prospectively collected clinical data from 273 patients undergoing SRS for 1 or 2 brain metastases at The University of Texas M. D. Anderson Cancer Center between June 1993 and December 2004 were reviewed. Patients who had received prior treatment for their tumor, including whole-brain radiation, SRS, or surgery, were excluded from the study. Data on adverse neurological and nonneurological outcomes following treatment were collected. Results Three hundred sixteen lesions were treated. Complications were associated with 127 (40%) of 316 treated lesions. New neurological complications were associated with 101 (32%) of 316 lesions. The onset of seizure was the most common complication, occurring in 41 (13%) of 316 SRS cases. On multivariate analysis, progressing primary cancer (hazard ratio [HR] = 2.4, 95% CI 1.6–3.6, p < 0.001), tumor location in eloquent cortex (HR = 2.3, 95% CI 1.6–3.4, p < 0.001), and lower (< 15 Gy) SRS dose (HR = 2.1, 95% CI 1.1–4.2, p = 0.04) were significantly associated with new complications. On multivariate analysis, a tumor location in the eloquent cortex (HR = 2.5, 95% CI 1.6–3.8, p < 0.001) and progressing primary cancer (HR = 1.6, 95% CI 1.1–2.5, p = 0.03) were significantly associated with new neurological complications. Conclusions The authors showed that new neurological and nonneurological complications were associated with 40% of SRS treatments for brain metastases. Patients with lesions in functional brain regions have a significantly increased risk of treatment-related complications.

scholarly journals Exploring the Relationship between Biologics and Postoperative Surgical Morbidity in Ulcerative Colitis: A Review

2021 ◽  
Vol 10 (4) ◽  
pp. 710
Author(s):  
Abel Botelho Quaresma ◽  
Fernanda da Silva Barbosa Baraúna ◽  
Fábio Vieira Teixeira ◽  
Rogério Saad-Hossne ◽  
Paulo Gustavo Kotze
Keyword(s):  
Ulcerative Colitis ◽  
Postoperative Complications ◽  
Meta Analysis ◽  
Qualitative Evaluation ◽  
Complication Rates ◽  
Surgical Morbidity ◽  
Randomized Studies ◽  
Pubmed Database ◽  
Increased Risk ◽  
The Impact

Background: With the paradigm shift related to the overspread use of biological agents in the treatment of inflammatory bowel diseases (IBD), several questions emerged from the surgical perspective. Whether the use of biologicals would be associated with higher rates of postoperative complications in ulcerative colitis (UC) patients still remains controversial. Aims: We aimed to analyze the literature, searching for studies that correlated postoperative complications and preoperative exposure to biologics in UC patients, and synthesize these data qualitatively in order to check the possible impact of biologics on postoperative surgical morbidity in this population. Methods: Included studies were identified by electronic search in the PUBMED database according to the PRISMA (Preferred Items of Reports for Systematic Reviews and Meta-Analysis) guidelines. The quality and bias assessments were performed by MINORS (methodological index for non-randomized studies) criteria for non-randomized studies. Results: 608 studies were initially identified, 22 of which were selected for qualitative evaluation. From those, 19 studies (17 retrospective and two prospective) included preoperative anti-TNF. Seven described an increased risk of postoperative complications, and 12 showed no significant increase postoperative morbidity. Only three studies included surgical UC patients with previous use of vedolizumab, two retrospective and one prospective, all with no significant correlation between the drug and an increase in postoperative complication rates. Conclusions: Despite conflicting results, most studies have not shown increased complication rates after abdominal surgical procedures in patients with UC with preoperative exposure to biologics. Further prospective studies are needed to better establish the impact of preoperative biologics and surgical complications in UC.

scholarly journals MUC5B variant is associated with visually and quantitatively detected preclinical pulmonary fibrosis

Thorax ◽  
2019 ◽  
Vol 74 (12) ◽  
pp. 1131-1139 ◽  
Author(s):  
Susan K Mathai ◽  
Stephen Humphries ◽  
Jonathan A Kropski ◽  
Timothy S Blackwell ◽  
Julia Powers ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pulmonary Fibrosis ◽  
Learning Algorithm ◽  
Quantitative Ct ◽  
First Degree Relatives ◽  
Deep Learning Algorithm ◽  
Increased Risk ◽  
Ct Evaluation ◽  
Ct Analysis ◽  
Quantitative Ct Analysis

BackgroundRelatives of patients with familial interstitial pneumonia (FIP) are at increased risk for pulmonary fibrosis. We assessed the prevalence and risk factors for preclinical pulmonary fibrosis (PrePF) in first-degree relatives of patients with FIP and determined the utility of deep learning in detecting PrePF on CT.MethodsFirst-degree relatives of patients with FIP over 40 years of age who believed themselves to be unaffected by pulmonary fibrosis underwent CT scans of the chest. Images were visually reviewed, and a deep learning algorithm was used to quantify lung fibrosis. Genotyping for common idiopathic pulmonary fibrosis risk variants in MUC5B and TERT was performed.FindingsIn 494 relatives of patients with FIP from 263 families of patients with FIP, the prevalence of PrePF on visual CT evaluation was 15.6% (95% CI 12.6 to 19.0). Compared with visual CT evaluation, deep learning quantitative CT analysis had 84% sensitivity (95% CI 0.72 to 0.89) and 86% sensitivity (95% CI 0.83 to 0.89) for discriminating subjects with visual PrePF diagnosis. Subjects with PrePF were older (65.9, SD 10.1 years) than subjects without fibrosis (55.8 SD 8.7 years), more likely to be male (49% vs 37%), more likely to have smoked (44% vs 27%) and more likely to have the MUC5B promoter variant rs35705950 (minor allele frequency 0.29 vs 0.21). MUC5B variant carriers had higher quantitative CT fibrosis scores (mean difference of 0.36%), a difference that remains significant when controlling for age and sex.InterpretationPrePF is common in relatives of patients with FIP. Its prevalence increases with age and the presence of a common MUC5B promoter variant. Quantitative CT analysis can detect these imaging abnormalities.

Abstract 15219: Fully Automated Calcification Segmentation in Intravascular Optical Coherence Tomography Images Using a Two-step Deep Learning Approach

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Juhwan Lee ◽  
Yazan Gharaibeh ◽  
Vladislav N Zimin ◽  
Luis A Dallan ◽  
Hiram G Bezerra ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Learning Approach ◽  
Optical Coherence ◽  
Stent Deployment ◽  
Automated Method ◽  
Increased Risk ◽  
Maximum Angle ◽  
Intravascular Optical Coherence Tomography ◽  
Sensitivity Specificity

Introduction: Major calcifications are of great concern when performing percutaneous coronary intervention as they hinder stent deployment. Calcifications can lead to under-expansion and strut malapposition, with increased risk of thrombosis and in-stent restenosis. Therefore, accurate identification, visualization, and quantification of calcifications are important. Objective: In this study, we developed a 2-step deep learning approach to enable segmentation of major calcifications in a typical 500+ frame intravascular optical coherence tomography (IVOCT) images. Methods: The dataset consisted of a total of 12,551 IVOCT frames across 68 patients with 68 pullbacks. We applied a series of pre-processing steps including guidewire/shadow removal, lumen detection, pixel shifting, and Gaussian filtering. To detect the major calcifications in step 1, we implemented the 3D convolutional neural network consisting of 5 convolutional, 5 max-pooling, and 2 fully-connected layers. In step-2, SegNet deep learning model was used to segment calcified plaques. In both steps, classification errors were reduced using conditional random field. Results: Step-1 reliably identified major calcifications (sensitivity/specificity: 97.7%/87.7%). Semantic segmentation of calcifications following step-2 was typically visually quite good (Fig. 1) with (sensitivity/specificity: 86.2%/96.7%). Our method was superior to a single step approach and showed excellent reproducibility on repetitive IVOCT pullbacks, with very small differences of clinically relevant attributes (maximum angle, maximum thickness, and length) and the exact same IVOCT calcium scores for assessment of stent deployment. Conclusions: We developed the fully-automated method for identifying calcifications in IVOCT images based on a 2-step deep learning approach. Extensive analyses indicate that our method is very informative for both live-time treatment planning and research purposes.

scholarly journals Multimodality Word-Finding Distinctions in Cortical Stimulation Mapping

Neurosurgery ◽  
2013 ◽  
Vol 73 (1) ◽  
pp. 36-47 ◽  
Author(s):  
Sandra Serafini ◽  
Merlise Clyde ◽  
Matt Tolson ◽  
Michael M. Haglund
Keyword(s):  
Cortical Stimulation ◽  
Sentence Completion ◽  
Resection Margins ◽  
Dominant Hemisphere ◽  
Language Mapping ◽  
Hierarchical Logistic Regression ◽  
Word Finding ◽  
Cortical Stimulation Mapping ◽  
Multimodality Approach ◽  
Patients With Epilepsy

Abstract BACKGROUND: Cortical stimulation mapping (CSM) commonly uses visual naming to determine resection margins in the dominant hemisphere of patients with epilepsy. Visual naming alone may not identify all language sites in resection-prone areas, prompting additional tasks for comprehensive language mapping. OBJECTIVE: To demonstrate word-finding distinctions between visual, auditory, and reading modalities during CSM and the percentage of modality-specific language sites within dominant hemisphere subregions. METHODS: Twenty-eight patients with epilepsy underwent CSM by the use of visual, auditory, and sentence-completion tasks. Hierarchical logistic regression analyzed errors to identify language sites and provide modality-specific percentages within subregions. RESULTS: The percentage of sites classified as language sites based on auditory naming was twice as high in anterior temporal regions compared with visual naming, marginally higher in posterior temporal areas, and comparable in parietal regions. Sentence completion was comparable to visual and auditory naming in parietal regions and lower in most temporal areas. Of 470 sites tested with both visual and auditory naming, 95 sites were distinctly auditory, whereas 48 sites were distinctly visual. The remaining sites overlapped. CONCLUSION: Distinct cortical areas were found for distinct input modalities, with language sites in anterior tip regions found most often by using auditory naming. The vulnerability of anterior temporal tip regions to resection in this population and distinct sites for each modality suggest that a multimodality approach may be needed to spare crucial language sites, if sparing those sites can be shown to significantly reduce the rate of postoperative language deficits without sacrificing seizure control.

scholarly journals A pH-eQTL interaction at the RIT2-SYT4 Parkinson's disease risk locus in the substantia nigra

2020 ◽  
Author(s):  
Sejal Patel ◽  
Derek Howard ◽  
Leon French
Keyword(s):  
Gene Expression ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Substantia Nigra ◽  
Human Brain ◽  
Disease Risk ◽  
Brain Regions ◽  
Dopamine Neurons ◽  
Postmortem Human Brain ◽  
Increased Risk

BACKGROUND: Parkinson's disease (PD) causes severe motor and cognitive disabilities that result from the progressive loss of dopamine neurons in the substantia nigra. The rs12456492 variant in the RIT2 gene has been repeatedly associated with increased risk for Parkinson's disease. From a transcriptomic perspective, a meta-analysis found that RIT2 gene expression is correlated with pH in the human brain. OBJECTIVE: To assess pH associations at the RIT2-SYT4 locus. METHODS: Linear models to examine two datasets that assayed rs12456492, gene expression, and pH in the postmortem human brain. RESULTS: Using the BrainEAC dataset, we replicate the positive correlation between RIT2 gene expression and pH in the human brain. Furthermore, we found that the relationship between expression and pH is influenced by rs12456492. When tested across ten brain regions, this interaction is specifically found in the substantia nigra. A similar association was found for the co-localized SYT4 gene. In addition, SYT4 associations are stronger in a combined model with both genes, and the SYT4 interaction appears to be specific to males. In the GTEx dataset, the pH associations involving rs12456492 and expression of either SYT4 and RIT2 was not seen. This null finding may be due to the short postmortem intervals (PMI) of the GTEx tissue samples. In the BrainEAC data, we tested the effect of PMI and only observed the interactions in the longer PMI samples. CONCLUSIONS: These previously unknown associations suggest novel mechanistic roles for rs12456492, RIT2, and SYT4 in the regulation of pH in the substantia nigra.

scholarly journals Optogenetic spatial and temporal control of cortical circuits on a columnar scale

2016 ◽  
Vol 115 (2) ◽  
pp. 1043-1062 ◽  
Author(s):  
Arani Roy ◽  
Jason J. Osik ◽  
Neil J. Ritter ◽  
Shen Wang ◽  
James T. Shaw ◽  
...  
Keyword(s):  
Visual Stimulation ◽  
Liquid Crystal Display ◽  
Brain Regions ◽  
Cortical Activation ◽  
Mammalian Brain ◽  
Optogenetic Stimulation ◽  
Brain Surface ◽  
Stimulation System ◽  
Circuit Function ◽  
Stimulation Of

Many circuits in the mammalian brain are organized in a topographic or columnar manner. These circuits could be activated—in ways that reveal circuit function or restore function after disease—by an artificial stimulation system that is capable of independently driving local groups of neurons. Here we present a simple custom microscope called ProjectorScope 1 that incorporates off-the-shelf parts and a liquid crystal display (LCD) projector to stimulate surface brain regions that express channelrhodopsin-2 (ChR2). In principle, local optogenetic stimulation of the brain surface with optical projection systems might not produce local activation of a highly interconnected network like the cortex, because of potential stimulation of axons of passage or extended dendritic trees. However, here we demonstrate that the combination of virally mediated ChR2 expression levels and the light intensity of ProjectorScope 1 is capable of producing local spatial activation with a resolution of ∼200–300 μm. We use the system to examine the role of cortical activity in the experience-dependent emergence of motion selectivity in immature ferret visual cortex. We find that optogenetic cortical activation alone—without visual stimulation—is sufficient to produce increases in motion selectivity, suggesting the presence of a sharpening mechanism that does not require precise spatiotemporal activation of the visual system. These results demonstrate that optogenetic stimulation can sculpt the developing brain.

scholarly journals Epilepsy surgery near or in eloquent cortex in children-Practice patterns and recommendations for minimizing and reporting deficits

Epilepsia ◽  
2018 ◽  
Vol 59 (8) ◽  
pp. 1484-1491 ◽  
Author(s):  
Prasanna Jayakar ◽  
Anuj Jayakar ◽  
Mark Libenson ◽  
Alexis Arzimanoglou ◽  
Bertil Rydenhag ◽  
...  
Keyword(s):  
Epilepsy Surgery ◽  
Practice Patterns ◽  
Eloquent Cortex
Sign in / Sign up

Export Citation Format

Share Document