Development of Gestational Age-Based Fetal Brain and Intracranial Volume Reference Norms Using Deep Learning.

BACKGROUND AND PURPOSE: Fetal brain MR imaging interpretations are subjective and require subspecialty expertise. We aimed to develop a deep learning algorithm for automatically measuring intracranial and brain volumes of fetal brain MRIs across gestational ages. MATERIALS AND METHODS: This retrospective study included 246 patients with singleton pregnancies at 19-38 weeks gestation. A 3D U-Net was trained to segment the intracranial contents of 2D fetal brain MRIs in the axial, coronal, and sagittal planes. An additional 3D U-Net was trained to segment the brain from the output of the first model. Models were tested on MRIs of 10 patients (28 planes) via Dice coefficients and volume comparison with manual reference segmentations. Trained U-Nets were applied to 200 additional MRIs to develop normative reference intracranial and brain volumes across gestational ages and then to 9 pathologic fetal brains. RESULTS: Fetal intracranial and brain compartments were automatically segmented in a mean of 6.8 (SD, 1.2) seconds with median Dices score of 0.95 and 0.90, respectively (interquartile ranges, 0.91-0.96/0.89-0.91) on the test set. Correlation with manual volume measurements was high (Pearson r = 0.996, P < .001). Normative samples of intracranial and brain volumes across gestational ages were developed. Eight of 9 pathologic fetal intracranial volumes were automatically predicted to be >2 SDs from this age-specific reference mean. There were no effects of fetal sex, maternal diabetes, or maternal age on intracranial or brain volumes across gestational ages. CONCLUSIONS: Deep learning techniques can quickly and accurately quantify intracranial and brain volumes on clinical fetal brain MRIs and identify abnormal volumes on the basis of a normative reference standard.

Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging.

BACKGROUND AND PURPOSE: Most brain lesions are characterized by hyperintense signal on FLAIR. We sought to develop an automated deep learning-based method for segmentation of abnormalities on FLAIR and volumetric quantification on clinical brain MRIs across many pathologic entities and scanning parameters. We evaluated the performance of the algorithm compared with manual segmentation and existing automated methods. MATERIALS AND METHODS: We adapted a U-Net convolutional neural network architecture for brain MRIs using 3D volumes. This network was retrospectively trained on 295 brain MRIs to perform automated FLAIR lesion segmentation. Performance was evaluated on 92 validation cases using Dice scores and voxelwise sensitivity and specificity, compared with radiologists' manual segmentations. The algorithm was also evaluated on measuring total lesion volume. RESULTS: Our model demonstrated accurate FLAIR lesion segmentation performance (median Dice score, 0.79) on the validation dataset across a large range of lesion characteristics. Across 19 neurologic diseases, performance was significantly higher than existing methods (Dice, 0.56 and 0.41) and approached human performance (Dice, 0.81). There was a strong correlation between the predictions of lesion volume of the algorithm compared with true lesion volume (ρ = 0.99). Lesion segmentations were accurate across a large range of image-acquisition parameters on >30 different MR imaging scanners. CONCLUSIONS: A 3D convolutional neural network adapted from a U-Net architecture can achieve high automated FLAIR segmentation performance on clinical brain MR imaging across a variety of underlying pathologies and image acquisition parameters. The method provides accurate volumetric lesion data that can be incorporated into assessments of disease burden or into radiologic reports.

The distribution and numbers of cheetah (Acinonyx jubatus) in southern Africa.

Assessing the numbers and distribution of threatened species is a central challenge in conservation, often made difficult because the species of concern are rare and elusive. For some predators, this may be compounded by their being sparsely distributed over large areas. Such is the case with the cheetah Acinonyx jubatus. The IUCN Red List process solicits comments, is democratic, transparent, widely-used, and has recently assessed the species. Here, we present additional methods to that process and provide quantitative approaches that may afford greater detail and a benchmark against which to compare future assessments. The cheetah poses challenges, but also affords unique opportunities. It is photogenic, allowing the compilation of thousands of crowd-sourced data. It is also persecuted for killing livestock, enabling estimation of local population densities from the numbers persecuted. Documented instances of persecution in areas with known human and livestock density mean that these data can provide an estimate of where the species may or may not occur in areas without observational data. Compilations of extensive telemetry data coupled with nearly 20,000 additional observations from 39 sources show that free-ranging cheetahs were present across approximately 789,700 km2 of Namibia, Botswana, South Africa, and Zimbabwe (56%, 22%, 12% and 10% respectively) from 2010 to 2016, with an estimated adult population of 3,577 animals. We identified a further 742,800 km2 of potential cheetah habitat within the study region with low human and livestock densities, where another ∼3,250 cheetahs may occur. Unlike many previous estimates, we make the data available and provide explicit information on exactly where cheetahs occur, or are unlikely to occur. We stress the value of gathering data from public sources though these data were mostly from well-visited protected areas. There is a contiguous, transboundary population of cheetah in southern Africa, known to be the largest in the world. We suggest that this population is more threatened than believed due to the concentration of about 55% of free-ranging individuals in two ecoregions. This area overlaps with commercial farmland with high persecution risk; adult cheetahs were removed at the rate of 0.3 individuals per 100 km2 per year. Our population estimate for confirmed cheetah presence areas is 11% lower than the IUCN's current assessment for the same region, lending additional support to the recent call for the up-listing of this species from vulnerable to endangered status.

Cheetahs (Acinonyx jubatus) running the gauntlet: an evaluation of translocations into free-range environments in Namibia.

Following dramatic range and population declines, the cheetah is Africa's most endangered large felid. In Namibia, private land managers still trap cheetahs but increasingly consider moving animals instead of killing them. Across Africa, managers have translocated perceived conflict carnivores for decades, but rarely evaluated their actions. We analyse the outcomes of 15 cheetah translocations (for 23 adults and 10 dependent offspring) into free-range environments in Namibia. We released cheetahs at an average distance of 419.6 km ± 216.1 km SD (range: 71-816 km) after captive periods ranging from 1-1,184 days (350.6 days ± 439.0 days SD). An individual's ability to survive the first year predominantly determined the overall translocation success of 40%. Post-release conflict and homing had less impact on success. Cheetah survival was lowest in the first three months after release. Human persecution (50% of deaths) and spotted hyaenas (29% of deaths) had the highest effect on survival. The degree of habituation to humans acquired during captivity significantly influenced chances of survival. Cheetahs surviving the initial post-release period (∼90 days) often settled into ranges and females reproduced successfully. However, all individuals exhibited extensive movements, frequently roaming >4,000 km(2) in the first six months after release (with a maximum of 19,743 km(2) in 112 days), resulting in low release site fidelity. Soft release and larger recipient area size did not improve site fidelity. Based on these outcomes, we evaluated which unfenced conservation areas in Namibia could potentially receive cheetahs. We found that there are currently few public and/or private reserves large enough to contain the movement profiles we observed in this study. This suggests that most translocations will result in cheetahs re-entering farmlands where they face a high risk of persecution. In conclusion, translocations into unconfined areas can successfully conserve individual cheetahs. Due to high mortality and unpredictable outcomes, however, conservation efforts need to focus on improving tolerance of cheetahs in commercial livestock and game farming areas in order to reduce the number of indiscriminately trapped animals.

The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism.

Autism spectrum disorders (ASDs) represent a formidable challenge for psychiatry and neuroscience because of their high prevalence, lifelong nature, complexity and substantial heterogeneity. Facing these obstacles requires large-scale multidisciplinary efforts. Although the field of genetics has pioneered data sharing for these reasons, neuroimaging had not kept pace. In response, we introduce the Autism Brain Imaging Data Exchange (ABIDE)-a grassroots consortium aggregating and openly sharing 1112 existing resting-state functional magnetic resonance imaging (R-fMRI) data sets with corresponding structural MRI and phenotypic information from 539 individuals with ASDs and 573 age-matched typical controls (TCs; 7-64 years) (http://fcon_1000.projects.nitrc.org/indi/abide/). Here, we present this resource and demonstrate its suitability for advancing knowledge of ASD neurobiology based on analyses of 360 male subjects with ASDs and 403 male age-matched TCs. We focused on whole-brain intrinsic functional connectivity and also survey a range of voxel-wise measures of intrinsic functional brain architecture. Whole-brain analyses reconciled seemingly disparate themes of both hypo- and hyperconnectivity in the ASD literature; both were detected, although hypoconnectivity dominated, particularly for corticocortical and interhemispheric functional connectivity. Exploratory analyses using an array of regional metrics of intrinsic brain function converged on common loci of dysfunction in ASDs (mid- and posterior insula and posterior cingulate cortex), and highlighted less commonly explored regions such as the thalamus. The survey of the ABIDE R-fMRI data sets provides unprecedented demonstrations of both replication and novel discovery. By pooling multiple international data sets, ABIDE is expected to accelerate the pace of discovery setting the stage for the next generation of ASD studies.

Successful snakebite treatment in three juvenile African wild dogs (Lycaon pictus) with polyvalent antivenom: a Namibian case report.

This article reports the first documented treatment of venomous snakebite with a polyvalent snake antivenom from the South African Institute for Medical Research in endangered African wild dogs (Lycaon pictus). Three juvenile male animals (6.5 months of age) showed clinical signs after being bitten by an unidentified venomous snake. The signs included loss of appetite, disorientation, impaired locomotion, excessive facial swelling, profuse salivation, reduced respiratory effort and an apparent depressed mental state. Intravenous treatment with isotonic Ringer lactate solution, hetastarch 6% and dexamethazone, subcutaneous administration of procaine benzylpenicillin and benzathine benzylpenicillin, and ultimately intravenous administration of the polyvalent snake antivenom resulted in the complete recovery of all three wild dogs.

Altered functional and structural brain network organization in autism.

Structural and functional underconnectivity have been reported for multiple brain regions, functional systems, and white matter tracts in individuals with autism spectrum disorders (ASD). Although recent developments in complex network analysis have established that the brain is a modular network exhibiting small-world properties, network level organization has not been carefully examined in ASD. Here we used resting-state functional MRI (n = 42 ASD, n = 37 typically developing; TD) to show that children and adolescents with ASD display reduced short and long-range connectivity within functional systems (i.e., reduced functional integration) and stronger connectivity between functional systems (i.e., reduced functional segregation), particularly in default and higher-order visual regions. Using graph theoretical methods, we show that pairwise group differences in functional connectivity are reflected in network level reductions in modularity and clustering (local efficiency), but shorter characteristic path lengths (higher global efficiency). Structural networks, generated from diffusion tensor MRI derived fiber tracts (n = 51 ASD, n = 43 TD), displayed lower levels of white matter integrity yet higher numbers of fibers. TD and ASD individuals exhibited similar levels of correlation between raw measures of structural and functional connectivity (n = 35 ASD, n = 35 TD). However, a principal component analysis combining structural and functional network properties revealed that the balance of local and global efficiency between structural and functional networks was reduced in ASD, positively correlated with age, and inversely correlated with ASD symptom severity. Overall, our findings suggest that modeling the brain as a complex network will be highly informative in unraveling the biological basis of ASD and other neuropsychiatric disorders.

The effects of ambient music on simulated anaesthesia monitoring.

We examined the effect of no music, classical music or rock music on simulated patient monitoring. Twenty-four non-anaesthetist participants with high or low levels of musical training were trained to monitor visual and auditory displays of patients' vital signs. In nine anaesthesia test scenarios, participants were asked every 50-70 s whether one of five vital signs was abnormal and the trend of its direction. Abnormality judgements were unaffected by music or musical training. Trend judgements were more accurate when music was playing (p = 0.0004). Musical participants reported trends more accurately (p = 0.004), and non-musical participants tended to benefit more from music than did the musical participants (p = 0.063). Music may provide a pitch and rhythm standard from which participants can judge changes in vital signs from auditory displays. Nonetheless, both groups reported that it was easier to monitor the patient with no music (p = 0.0001), and easier to rely upon the auditory displays with no music (p = 0.014).

Changes in Alcohol Use and Drinking Problems in Relation to Role Transitions in Different Stages of the Life Course.

Older and younger generations are compared with respect to changes in alcohol use and alcohol-related problems associated with role transitions in the life course, using data from a 9-year follow-up study in the Netherlands. Transitions in several role domains are summarized in an index for structure of everyday life. It was hypothesized that role transitions involving an increase in structure of everyday life would lead to a decrease in drinking and in problems. As expected, the association of the index with alcohol use and alcohol related problems was negative among the younger generation. However, contrary to expectation, the association was positive among the older generation. It is concluded that the role-theoretic framework from which our expectations were derived should be amended when used for research among older people. More specific attention to the content of social roles and associated resources and coping mechanisms available at older age is recommended.