Introduction
Malignant cerebral edema develops in a small subset of patients with hemispheric strokes, precipitating deterioration and death if decompressive hemicraniectomy (DHC) is not performed in ...a timely manner. Predicting which stroke patients will develop malignant edema is imprecise based on clinical data alone. Head computed tomography (CT) imaging is often performed at baseline and 24-h. We determined the incremental value of incorporating imaging-derived features from serial CTs to enhance prediction of malignant edema.
Methods
We identified hemispheric stroke patients at three sites with NIHSS ≥ 7 who had baseline as well as 24-h clinical and CT imaging data. We extracted quantitative imaging features from baseline and follow-up CTs, including CSF volume, intracranial reserve (CSF/cranial volume), as well as midline shift (MLS) and infarct-related hypodensity volume. Potentially lethal malignant edema was defined as requiring DHC or dying with MLS over 5-mm. We built machine-learning models using logistic regression first with baseline data and then adding 24-h data including reduction in CSF volume (ΔCSF). Model performance was evaluated with cross-validation using metrics of recall (sensitivity), precision (predictive value), as well as area under receiver-operating-characteristic and precision-recall curves (AUROC, AUPRC).
Results
Twenty of 361 patients (6%) died or underwent DHC. Baseline clinical variables alone had recall of 60% with low precision (7%), AUROC 0.59, AUPRC 0.15. Adding baseline intracranial reserve improved recall to 80% and AUROC to 0.82 but precision remained only 16% (AUPRC 0.28). Incorporating ΔCSF improved AUPRC to 0.53 (AUROC 0.91) while all imaging features further improved prediction (recall 90%, precision 38%, AUROC 0.96, AUPRC 0.66).
Conclusion
Incorporating quantitative CT-based imaging features from baseline and 24-h CT enhances identification of patients with malignant edema needing DHC. Further refinements and external validation of such imaging-based machine-learning models are required.
Background
Malignant cerebral edema is a devastating complication of stroke, resulting in deterioration and death if hemicraniectomy is not performed prior to herniation. Current approaches for ...predicting this relatively rare complication often require advanced imaging and still suffer from suboptimal performance. We performed a pilot study to evaluate whether neural networks incorporating data extracted from routine computed tomography (CT) imaging could enhance prediction of edema in a large diverse stroke cohort.
Methods
An automated imaging pipeline retrospectively extracted volumetric data, including cerebrospinal fluid (CSF) volumes and the hemispheric CSF volume ratio, from baseline and 24 h CT scans performed in participants of an international stroke cohort study. Fully connected and long short-term memory (LSTM) neural networks were trained using serial clinical and imaging data to predict those who would require hemicraniectomy or die with midline shift. The performance of these models was tested, in comparison with regression models and the Enhanced Detection of Edema in Malignant Anterior Circulation Stroke (EDEMA) score, using cross-validation to construct precision-recall curves.
Results
Twenty of 598 patients developed malignant edema (12 required surgery, 8 died). The regression model provided 95% recall but only 32% precision (area under the precision-recall curve AUPRC 0.74), similar to the EDEMA score (precision 28%, AUPRC 0.66). The fully connected network did not perform better (precision 33%, AUPRC 0.71), but the LSTM model provided 100% recall and 87% precision (AUPRC 0.97) in the overall cohort and the subgroup with a National Institutes of Health Stroke Scale (NIHSS) score ≥ 8 (
p
= 0.0001 vs. regression and fully connected models). Features providing the most predictive importance were the hemispheric CSF ratio and NIHSS score measured at 24 h.
Conclusions
An LSTM neural network incorporating volumetric data extracted from routine CT scans identified all cases of malignant cerebral edema by 24 h after stroke, with significantly fewer false positives than a fully connected neural network, regression model, and the validated EDEMA score. This preliminary work requires prospective validation but provides proof of principle that a deep learning framework could assist in selecting patients for surgery prior to deterioration.
Atezolizumab anti-programmed death-ligand 1 (PD-L1) selectively targets PD-L1 to block its interaction with receptors programmed death 1 and B7.1, thereby reinvigorating antitumor T-cell activity. We ...evaluated the long-term safety and activity of atezolizumab, along with biological correlates of clinical activity endpoints, in a cohort of patients with melanoma in an ongoing phase Ia study (NCT01375842).
Patients with unresectable or metastatic melanoma were enrolled to receive atezolizumab 0.1 to 20 mg/kg or ≥10 mg/kg every 3 weeks. Primary study objectives were safety and tolerability. Secondary objectives included investigator-assessed efficacy measures; pharmacodynamic and predictive biomarkers of antitumor activity were explored.
Forty-five patients were enrolled and were evaluable for safety. Most treatment-related adverse events (AE) were grade 1/2 (60%). Fatigue (44%), pruritus (20%), pyrexia (18%), and rash (18%) were the most common treatment-related AEs of any grade. No treatment-related deaths occurred. Overall response rate was 30% among 43 efficacy- evaluable patients, with a median duration of response of 62 months 95% CI, 35-not estimable (NE). Clinically meaningful long-term survival was observed, with a median overall survival of 23 months (95% CI, 9-66). Baseline biomarkers of tumor immunity PD-L1 expression on immune cells, T effector (Teff), and antigen presentation gene signatures) and tumor mutational burden (TMB) were associated with improved response, progression-free survival, and overall survival.
Atezolizumab was well tolerated, with durable responses and survival in patients with melanoma. PD-L1 expression, TMB, and Teff signatures may indicate improved benefit with atezolizumab in these patients.
Little is known about large sulfur bacteria (LSB) that inhabit sulfidic groundwater seeps in large lakes. To examine how geochemically relevant microbial metabolisms are partitioned among community ...members, we conducted metagenomic analysis of a chemosynthetic microbial mat in the Isolated Sinkhole, which is in a deep, aphotic environment of Lake Huron. For comparison, we also analyzed a white mat in an artesian fountain that is fed by groundwater similar to Isolated Sinkhole, but that sits in shallow water and is exposed to sunlight.
assembly and binning of metagenomic data from these two communities yielded near complete genomes and revealed representatives of two families of LSB. The Isolated Sinkhole community was dominated by novel members of the
that are phylogenetically intermediate between known freshwater and marine groups. Several of these
had 16S rRNA genes that contained introns previously observed only in marine taxa. The Alpena fountain was dominated by populations closely related to
and an SM1 euryarchaeon known to live symbiotically with
spp. The SM1 genomic bin contained evidence of H
-based lithoautotrophy. Genomic bins of both the
and
contained genes for sulfur oxidation via the rDsr pathway, H
oxidation via Ni-Fe hydrogenases, and the use of O
and nitrate as electron acceptors. Mats at both sites also contained Deltaproteobacteria with genes for dissimilatory sulfate reduction (
, and
) and hydrogen oxidation (Ni-Fe hydrogenases). Overall, the microbial mats at the two sites held low-diversity microbial communities, displayed evidence of coupled sulfur cycling, and did not differ largely in their metabolic potentials, despite the environmental differences. These results show that groundwater-fed communities in an artesian fountain and in submerged sinkholes of Lake Huron are a rich source of novel LSB, associated heterotrophic and sulfate-reducing bacteria, and archaea.
Owing to an early age of symptom onset, genetically driven Alzheimer's disease offers an opportunity to study disease-related network degradation in the absence of age-related changes. Using data ...from young people with autosomal-dominant Alzheimer's disease, Chhatwal et al. identify a pattern of disease-related network degradation distinct from ageing alone.
Abstract
Converging evidence from structural, metabolic and functional connectivity MRI suggests that neurodegenerative diseases, such as Alzheimer's disease, target specific neural networks. However, age-related network changes commonly co-occur with neuropathological cascades, limiting efforts to disentangle disease-specific alterations in network function from those associated with normal ageing. Here we elucidate the differential effects of ageing and Alzheimer's disease pathology through simultaneous analyses of two functional connectivity MRI datasets: (i) young participants harbouring highly-penetrant mutations leading to autosomal-dominant Alzheimer's disease from the Dominantly Inherited Alzheimer's Network (DIAN), an Alzheimer's disease cohort in which age-related comorbidities are minimal and likelihood of progression along an Alzheimer's disease trajectory is extremely high; and (ii) young and elderly participants from the Harvard Aging Brain Study, a cohort in which imaging biomarkers of amyloid burden and neurodegeneration can be used to disambiguate ageing alone from preclinical Alzheimer's disease. Consonant with prior reports, we observed the preferential degradation of cognitive (especially the default and dorsal attention networks) over motor and sensory networks in early autosomal-dominant Alzheimer's disease, and found that this distinctive degradation pattern was magnified in more advanced stages of disease. Importantly, a nascent form of the pattern observed across the autosomal-dominant Alzheimer's disease spectrum was also detectable in clinically normal elderly with clear biomarker evidence of Alzheimer's disease pathology (preclinical Alzheimer's disease). At the more granular level of individual connections between node pairs, we observed that connections within cognitive networks were preferentially targeted in Alzheimer's disease (with between network connections relatively spared), and that connections between positively coupled nodes (correlations) were preferentially degraded as compared to connections between negatively coupled nodes (anti-correlations). In contrast, ageing in the absence of Alzheimer's disease biomarkers was characterized by a far less network-specific degradation across cognitive and sensory networks, of between- and within-network connections, and of connections between positively and negatively coupled nodes. We go on to demonstrate that formalizing the differential patterns of network degradation in ageing and Alzheimer's disease may have the practical benefit of yielding connectivity measurements that highlight early Alzheimer's disease-related connectivity changes over those due to age-related processes. Together, the contrasting patterns of connectivity in Alzheimer's disease and ageing add to prior work arguing against Alzheimer's disease as a form of accelerated ageing, and suggest multi-network composite functional connectivity MRI metrics may be useful in the detection of early Alzheimer's disease-specific alterations co-occurring with age-related connectivity changes. More broadly, our findings are consistent with a specific pattern of network degradation associated with the spreading of Alzheimer's disease pathology within targeted neural networks.
Our study aims to identify children at risk of developing high myopia for timely assessment and intervention, preventing myopia progression and complications in adulthood through the development of a ...deep learning system (DLS). Using a school-based cohort in Singapore comprising of 998 children (aged 6-12 years old), we train and perform primary validation of the DLS using 7456 baseline fundus images of 1878 eyes; with external validation using an independent test dataset of 821 baseline fundus images of 189 eyes together with clinical data (age, gender, race, parental myopia, and baseline spherical equivalent (SE)). We derive three distinct algorithms - image, clinical and mix (image + clinical) models to predict high myopia development (SE ≤ -6.00 diopter) during teenage years (5 years later, age 11-17). Model performance is evaluated using area under the receiver operating curve (AUC). Our image models (Primary dataset AUC 0.93-0.95; Test dataset 0.91-0.93), clinical models (Primary dataset AUC 0.90-0.97; Test dataset 0.93-0.94) and mixed (image + clinical) models (Primary dataset AUC 0.97; Test dataset 0.97-0.98) achieve clinically acceptable performance. The addition of 1 year SE progression variable has minimal impact on the DLS performance (clinical model AUC 0.98 versus 0.97 in primary dataset, 0.97 versus 0.94 in test dataset; mixed model AUC 0.99 versus 0.97 in primary dataset, 0.95 versus 0.98 in test dataset). Thus, our DLS allows prediction of the development of high myopia by teenage years amongst school-going children. This has potential utility as a clinical-decision support tool to identify "at-risk" children for early intervention.
Plasmids enable the dissemination of antimicrobial resistance (AMR) in common Enterobacterales pathogens, representing a major public health challenge. However, the extent of plasmid sharing and ...evolution between Enterobacterales causing human infections and other niches remains unclear, including the emergence of resistance plasmids. Dense, unselected sampling is essential to developing our understanding of plasmid epidemiology and designing appropriate interventions to limit the emergence and dissemination of plasmid-associated AMR. We established a geographically and temporally restricted collection of human bloodstream infection (BSI)-associated, livestock-associated (cattle, pig, poultry, and sheep faeces, farm soils) and wastewater treatment work (WwTW)-associated (influent, effluent, waterways upstream/downstream of effluent outlets) Enterobacterales. Isolates were collected between 2008 and 2020 from sites <60 km apart in Oxfordshire, UK. Pangenome analysis of plasmid clusters revealed shared 'backbones', with phylogenies suggesting an intertwined ecology where well-conserved plasmid backbones carry diverse accessory functions, including AMR genes. Many plasmid 'backbones' were seen across species and niches, raising the possibility that plasmid movement between these followed by rapid accessory gene change could be relatively common. Overall, the signature of identical plasmid sharing is likely to be a highly transient one, implying that plasmid movement might be occurring at greater rates than previously estimated, raising a challenge for future genomic One Health studies.
Resting-state fMRI is increasingly used to study the effects of gliomas on the functional organization of the brain. A variety of preprocessing techniques and functional connectivity analyses are ...represented in the literature. However, there so far has been no systematic comparison of how alternative methods impact observed results.
We first surveyed current literature and identified alternative analytical approaches commonly used in the field. Following, we systematically compared alternative approaches to atlas registration, parcellation scheme, and choice of graph-theoretical measure as regards differentiating glioma patients (N = 59) from age-matched reference subjects (N = 163).
Our results suggest that non-linear, as opposed to affine registration, improves structural match to an atlas, as well as measures of functional connectivity. Functionally- as opposed to anatomically-derived parcellation schemes maximized the contrast between glioma patients and reference subjects. We also demonstrate that graph-theoretic measures strongly depend on parcellation granularity, parcellation scheme, and graph density.
Our current work primarily focuses on technical optimization of rs-fMRI analysis in glioma patients and, therefore, is fundamentally different from the bulk of papers discussing glioma-induced functional network changes. We report that the evaluation of glioma-induced alterations in the functional connectome strongly depends on analytical approaches including atlas registration, choice of parcellation scheme, and graph-theoretical measures.
White matter hyperintensity (WMH) volume on MRI is increased among presymptomatic individuals with autosomal dominant mutations for Alzheimer's disease (AD). One potential explanation is that WMH, ...conventionally considered a marker of cerebrovascular disease, are a reflection of cerebral amyloid angiopathy (CAA) and that increased WMH in this population is a manifestation of this vascular form of primary AD pathology. We examined whether the presence of cerebral microbleeds, a marker of CAA, mediates the relationship between WMH and estimated symptom onset in individuals with and without autosomal dominant mutations for AD.
Participants (n = 175, mean age = 41.1 years) included 112 with an AD mutation and 63 first-degree non-carrier controls. We calculated the estimated years from expected symptom onset (EYO) and analyzed baseline MRI data for WMH volume and presence of cerebral microbleeds. Mixed effects regression and tests of mediation were used to examine microbleed and WMH differences between carriers and non-carriers and to test the whether the association between WMH and mutation status is dependent on the presence of microbleeds.
Mutation carriers were more likely to have microbleeds than non-carriers (p<0.05) and individuals with microbleeds had higher WMH volume than those without (p<0.05). Total WMH volume was increased in mutation carriers compared with non-carriers, up to 20 years prior to EYO, after controlling for microbleed status, as we demonstrated previously. Formal testing of mediation demonstrated that 21% of the association between mutation status and WMH was mediated by presence of microbleeds (p = 0.03) but a significant direct effect of WMH remained (p = 0.02) after controlling for presence of microbleeds.
Although there is some co-dependency between WMH and microbleeds, the observed increases in WMH among mutation carriers does not appear to be fully mediated by this marker of CAA. The findings highlight the possibility that WMH represent a core feature of AD independent of vascular forms of beta amyloid.
Primary brain tumors are composed of tumor cells, neural/glial tissues, edema, and vasculature tissue. Conventional MRI has a limited ability to evaluate heterogeneous tumor pathologies. We developed ...a novel diffusion MRI-based method-Heterogeneity Diffusion Imaging (HDI)-to simultaneously detect and characterize multiple tumor pathologies and capillary blood perfusion using a single diffusion MRI scan.
Seven adult patients with primary brain tumors underwent standard-of-care MRI protocols and HDI protocol before planned surgical resection and/or stereotactic biopsy. Twelve tumor sampling sites were identified using a neuronavigational system and recorded for imaging data quantification. Metrics from both protocols were compared between World Health Organization (WHO) II and III tumor groups. Cerebral blood volume (CBV) derived from dynamic susceptibility contrast (DSC) perfusion imaging was also compared with the HDI-derived perfusion fraction.
The conventional apparent diffusion coefficient did not identify differences between WHO II and III tumor groups. HDI-derived slow hindered diffusion fraction was significantly elevated in the WHO III group as compared with the WHO II group. There was a non-significantly increasing trend of HDI-derived tumor cellularity fraction in the WHO III group, and both HDI-derived perfusion fraction and DSC-derived CBV were found to be significantly higher in the WHO III group. Both HDI-derived perfusion fraction and slow hindered diffusion fraction strongly correlated with DSC-derived CBV. Neither HDI-derived cellularity fraction nor HDI-derived fast hindered diffusion fraction correlated with DSC-derived CBV.
Conventional apparent diffusion coefficient, which measures averaged pathology properties of brain tumors, has compromised accuracy and specificity. HDI holds great promise to accurately separate and quantify the tumor cell fraction, the tumor cell packing density, edema, and capillary blood perfusion, thereby leading to an improved microenvironment characterization of primary brain tumors. Larger studies will further establish HDI's clinical value and use for facilitating biopsy planning, treatment evaluation, and noninvasive tumor grading.