Novel AI-Based Algorithm for the Automated Measurement of Cervical Sagittal Balance Parameters. A Validation Study on Pre- and Postoperative Radiographs of 129 Patients.

STUDY DESIGN: Retrospective, mono-centric cohort research study. OBJECTIVES: The analysis of cervical sagittal balance parameters is essential for preoperative planning and dependent on the physician's experience. A fully automated artificial intelligence-based algorithm could contribute to an objective analysis and save time. Therefore, this algorithm should be validated in this study. METHODS: Two surgeons measured C2-C7 lordosis, C1-C7 Sagittal Vertical Axis (SVA), C2-C7-SVA, C7-slope and T1-slope in pre- and postoperative lateral cervical X-rays of 129 patients undergoing anterior cervical surgery. All parameters were measured twice by surgeons and compared to the measurements by the AI algorithm consisting of 4 deep convolutional neural networks. Agreement between raters was quantified, among other metrics, by mean errors and single measure intraclass correlation coefficients for absolute agreement. RESULTS: ICC-values for intra- (range: .92-1.0) and inter-rater (.91-1.0) reliability reflect excellent agreement between human raters. The AI-algorithm could determine all parameters with excellent ICC-values (preop:0.80-1.0; postop:0.86-.99). For a comparison between the AI algorithm and 1 surgeon, mean errors were smallest for C1-C7 SVA (preop: -.3 mm (95% CI:-.6 to -.1 mm), post: .3 mm (.0-.7 mm)) and largest for C2-C7 lordosis (preop:-2.2° (-2.9 to -1.6°), postop: 2.3°(-3.0 to -1.7°)). The automatic measurement was possible in 99% and 98% of pre- and postoperative images for all parameters except T1 slope, which had a detection rate of 48% and 51% in pre- and postoperative images. CONCLUSION: This study validates that an AI-algorithm can reliably measure cervical sagittal balance parameters automatically in patients suffering from degenerative spinal diseases. It may simplify manual measurements and autonomously analyze large-scale datasets. Further studies are required to validate the algorithm on a larger and more diverse patient cohort.

Automated Artificial Intelligence-Based Assessment of Lower Limb Alignment Validated on Weight-Bearing Pre- and Postoperative Full-Leg Radiographs.

The assessment of the knee alignment using standing weight-bearing full-leg radiographs (FLR) is a standardized method. Determining the load-bearing axis of the leg requires time-consuming manual measurements. The aim of this study is to develop and validate a novel algorithm based on artificial intelligence (AI) for the automated assessment of lower limb alignment. In the first stage, a customized mask-RCNN model was trained to automatically detect and segment anatomical structures and implants in FLR. In the second stage, four region-specific neural network models (adaptations of UNet) were trained to automatically place anatomical landmarks. In the final stage, this information was used to automatically determine five key lower limb alignment angles. For the validation dataset, weight-bearing, antero-posterior FLR were captured preoperatively and 3 months postoperatively. Preoperative images were measured by the operating orthopedic surgeon and an independent physician. Postoperative images were measured by the second rater only. The final validation dataset consisted of 95 preoperative and 105 postoperative FLR. The detection rate for the different angles ranged between 92.4% and 98.9%. Human vs. human inter-(ICCs: 0.85−0.99) and intra-rater (ICCs: 0.95−1.0) reliability analysis achieved significant agreement. The ICC-values of human vs. AI inter-rater reliability analysis ranged between 0.8 and 1.0 preoperatively and between 0.83 and 0.99 postoperatively (all p < 0.001). An independent and external validation of the proposed algorithm on pre- and postoperative FLR, with excellent reliability for human measurements, could be demonstrated. Hence, the algorithm might allow for the objective and time saving analysis of large datasets and support physicians in daily routine.

Enhanced habit formation in Tourette patients explained by shortcut modulation in a hierarchical cortico-basal ganglia model.

Devaluation protocols reveal that Tourette patients show an increased propensity to habitual behaviors as they continue to respond to devalued outcomes in a cognitive stimulus-response-outcome association task. We use a neuro-computational model of hierarchically organized cortico-basal ganglia-thalamo-cortical loops to shed more light on habit formation and its alteration in Tourette patients. In our model, habitual behavior emerges from cortico-thalamic shortcut connections, where enhanced habit formation can be linked to faster plasticity in the shortcut or to a stronger feedback from the shortcut to the basal ganglia. We explore two major hypotheses of Tourette pathophysiology-local striatal disinhibition and increased dopaminergic modulation of striatal medium spiny neurons-as causes for altered shortcut activation. Both model changes altered shortcut functioning and resulted in higher rates of responses towards devalued outcomes, similar to what is observed in Tourette patients. We recommend future experimental neuroscientific studies to locate shortcuts between cortico-basal ganglia-thalamo-cortical loops in the human brain and study their potential role in health and disease.

The information theory of developmental pruning: Optimizing global network architectures using local synaptic rules.

During development, biological neural networks produce more synapses and neurons than needed. Many of these synapses and neurons are later removed in a process known as neural pruning. Why networks should initially be over-populated, and the processes that determine which synapses and neurons are ultimately pruned, remains unclear. We study the mechanisms and significance of neural pruning in model neural networks. In a deep Boltzmann machine model of sensory encoding, we find that (1) synaptic pruning is necessary to learn efficient network architectures that retain computationally-relevant connections, (2) pruning by synaptic weight alone does not optimize network size and (3) pruning based on a locally-available measure of importance based on Fisher information allows the network to identify structurally important vs. unimportant connections and neurons. This locally-available measure of importance has a biological interpretation in terms of the correlations between presynaptic and postsynaptic neurons, and implies an efficient activity-driven pruning rule. Overall, we show how local activity-dependent synaptic pruning can solve the global problem of optimizing a network architecture. We relate these findings to biology as follows: (I) Synaptic over-production is necessary for activity-dependent connectivity optimization. (II) In networks that have more neurons than needed, cells compete for activity, and only the most important and selective neurons are retained. (III) Cells may also be pruned due to a loss of synapses on their axons. This occurs when the information they convey is not relevant to the target population.

Severe mental illness and substance use disorders in prisoners in low-income and middle-income countries: a systematic review and meta-analysis of prevalence studies.

BACKGROUND: Although more than two thirds of the world's incarcerated individuals are based in low-income and middle-income countries (LMICs), the burden of psychiatric disorders in this population is not known. This review provides estimates for the prevalence of severe mental illness and substance use disorders in incarcerated individuals in LMICs. METHODS: For this systematic review and meta-analysis, we searched 17 electronic databases to identify prevalence studies of psychiatric disorders in prison populations in LMICs, published between January, 1987, and May, 2018. We included representative studies from general prison samples, providing information about four major psychiatric diagnoses: psychosis, major depression, alcohol use disorders, and drug use disorders. We pooled data from studies using random-effects meta-analyses and assessed the sources of heterogeneity by meta-regression. We extracted general population estimates from the Global Burden of Diseases 2016 database to calculate comparative prevalence ratios. This study is registered with PROSPERO, number CRD42015020905. FINDINGS: We identified 23 publications reporting prevalence estimates of severe mental illness and substance use disorders for 14 527 prisoners from 13 LMICs. In this population, the estimated pooled 1 year prevalence rates for psychosis were 6·2% (95% CI 4·0-8·6), 16·0% (11·7-20·8) for major depression, 3·8% (1·2-7·6) for alcohol use disorders, and 5·1% (2·9-7·8) for drug use disorders. We noted increased prevalence at prison intake and geographic variations for substance use disorders. For alcohol use disorders, prevalence was higher in the southeast Asian region than in the eastern Mediterranean region; and drug use disorders were more prevalent in the eastern Mediterranean region than in Europe. Prevalence ratios indicated substantially higher rates of severe mental illness and substance use disorders among prisoners than in the general population (the prevalence of non-affective psychosis was on average 16 times higher, major depression and illicit drug use disorder prevalence were both six times higher, and prevalence of alcohol use disorders was double that of the general population). INTERPRETATION: The prevalence of major psychiatric disorders is high in prisoners in LMIC compared with general populations. As these findings are likely to reflect unmet needs, the development of scalable interventions should be a public health priority in resource-poor settings. FUNDING: CONICYT of the Chilean government and the Wellcome Trust.

Whole-body vibration improves functional recovery in spinal cord injured rats.

Whole-body vibration (WBV) is a relatively novel form of exercise used to improve neuromuscular performance in healthy individuals. Its usefulness as a therapy for patients with neurological disorders, in particular spinal cord injury (SCI), has received little attention in clinical settings and, surprisingly, even less in animal SCI models. We performed severe compression SCI at a low-thoracic level in Wistar rats followed by daily WBV starting 7 (10 rats) or 14 (10 rats) days after injury (WBV7 and WBV14, respectively) and continued over a 12-week post-injury period. Rats with SCI but no WBV training (sham, 10 rats) and intact animals (10 rats) served as controls. Compared to sham-treated rats, WBV did not improve BBB score, plantar stepping, or ladder stepping during the 12-week period. Accordingly, WBV did not significantly alter plantar H-reflex, lesion volume, serotonergic input to the lumbar spinal cord, nor cholinergic or glutamatergic inputs to lumbar motoneurons at 12 weeks after SCI. However, compared to sham, WBV14, but not WBV7, significantly improved body weight support (rump-height index) during overground locomotion and overall recovery between 6-12 weeks and also restored the density of synaptic terminals in the lumbar spinal cord at 12 weeks. Most remarkably, WBV14 led to a significant improvement of bladder function at 6-12 weeks after injury. These findings provide the first evidence for functional benefits of WBV in an animal SCI model and warrant further preclinical investigations to determine mechanisms underpinning this noninvasive, inexpensive, and easily delivered potential rehabilitation therapy for SCI.