Use of Neural Networks to Correlate Spine and Rib Deformity in Scoliosis

Abstract

Artificial neural networks (ANN's) recognize patterns relating input and output data in a manner analogous to the function of biological neurons. Here, we show that ANN's can predict rib deformity in scoliosis more accurately than regression analysis. ANN's and linear regression models were developed to predict rib rotation from several combinations of input spinal indices including Cobb angle, vertebral rotation, apex location and orientation of the plane of maximal curvature. ANN's averaged 60% correct predictions compared to 34% for regression analysis. This study provides evidence for the utility of artificial neural networks in scoliosis research. These data lend credence to the use of ANN's in future work on the prediction of scoliotic spinal deformity from torso surface data, which would permit assessment of scoliosis severity with minimal use of harmful X-rays.     

Extent of Spine Deformity Predicts Lung Growth and Function in Rabbit Model of Early Onset Scoliosis

Early onset deformity of the spine and chest wall (initiated <8 years of age) is associated with increased morbidity at adulthood relative to adolescent onset deformity of comparable severity. Presumably, inhibition of thoracic growth during late stage alveolarization leads to an irreversible loss of pulmonary growth and thoracic function; however the natural history of this disease from onset to adulthood has not been well characterized. In this study we establish a rabbit model of early onset scoliosis to establish the extent that thoracic deformity affects structural and functional respiratory development. Using a surgical right unilateral rib-tethering procedure, rib fusion with early onset scoliosis was induced in 10 young New Zealand white rabbits (3 weeks old). Progression of spine deformity, functional residual capacity, total lung capacity, and lung mass was tracked through longitudinal breath-hold computed tomography imaging up to skeletal maturity (28 weeks old). Additionally at maturity forced vital capacity and regional specific volume were calculated as functional measurements and histo-morphometry performed with the radial alveolar count as a measure of acinar complexity. Data from tethered rib rabbits were compared to age matched healthy control rabbits (N = 8). Results show unilateral rib-tethering created a progressive spinal deformity ranging from 30° to 120° curvature, the severity of which was strongly associated with pulmonary growth and functional outcomes. At maturity rabbits with deformity greater than the median (55°) had decreased body weight (89%), right (59%) and left (86%) lung mass, right (74%) and left (69%) radial alveolar count, right lung volume at total lung capacity (60%), and forced vital capacity (75%). Early treatment of spinal deformity in children may prevent pulmonary complications in adulthood and these results provide a basis for the prediction of pulmonary development from thoracic structure. This model may also have future use as a platform to evaluate treatment effectiveness.     

DR全脊柱摄影技术在脊柱侧弯中的应用与优势

目的:探讨数字化X线摄影(DR)全脊柱摄像技术在脊柱侧弯中的应用和优势。方法:收集2012年2月至2013年6月于本院进行治疗的脊柱侧弯病例88例,应用数字化X线摄影(DR)技术对脊柱由上至下进行正位和侧位的扫描,均进行3次曝光,每两次曝光间隔均为9秒,曝光后通过图像拼接技术将患者脊柱图像进行拼接和重叠,形成全景图像,对全部患者的图像质量进行观察和评估。结果:所有入选病例中有84例患者图像清晰显示了脊柱侧弯的方向和角度、椎体和椎间隙、对称的椎弓根、根间距及对脏器的影响程度。其中1例因运动不合作出现伪影,3例曝光不足。全脊柱图像质量正位优秀率为92.43%,侧位优秀率为85.92%;全脊柱图像拼接正位优秀率为83.44%,侧位优秀率为86.58%。结论:数字化X线摄影(DR)技术应用上方便快捷,患者配合时间较短,图像质量较好,能够满足临床医生进行诊断和治疗,有助于患者预后康复情况的评估,值得在临床诊断中推广应用。     

Reconstruction of Laser-scanned 3D Torso Topography and Stereoradiographical Spine and Rib-cage Geometry in Scoliosis

Assessments of scoliosis are routinely done by means of clinical examination and full spinal x-rays. Multiple exposure to ionization radiation, however, can be hazardous to the child and is costly. Here, we explain the use of a noninvasive imaging technique, based on laser optical scanning, for quantifying the three-dimensional (3D) trunk surface topography that can be used to estimate parameters of 3D deformity of the spine. The laser optical scanning system consisted of four BIRIS laser cameras mounted on a ring moving along a vertical axis, producing a topographical mapping of the entire torso. In conjunction with the laser scans, an accurate 3D reconstruction of the spine and rib cage were developed from the digitized x-ray images. Results from 14 scoliotic patients are reported. The digitized surfaces provided the foundation data to start studying concordance of trunk surface asymmetry and spinal shape in idiopathic scoliosis.     

Simulation of Soybean Phenology with the Use of Artificial Neural Networks

Biophysics - The phenology of soybean explicitly indicates environmental changes and strongly depends on temperature and day length. We adapted an artificial neural network model to predict the...     

How to Find Decision Makers in Neural Networks

Nervous systems often face the problem of classifying stimuli and making decisions based on these classifications. The neurons involved in these tasks can be characterized as sensory or motor, according to their correlation with sensory stimulus or motor response. In this study we define a third class of neurons responsible for making perceptual decisions. Our mathematical formalism enables the weighting of neuronal units according to their contribution to decision making, thus narrowing the field for more detailed studies of underlying mechanisms. We develop two definitions of a contribution to decision making. The first definition states that decision making activity can be found at the points of emergence for behavioral correlations in the system. The second definition involves the study of propagation of noise in the network. The latter definition is shown to be equivalent to the first one in the cases when they can be compared. Our results suggest a new approach to analyzing decision making networks An erratum to this article can be found at     

Use of Artificial Neural Networks To Accurately Identify Cryptosporidium Oocyst and Giardia Cyst Images

Cryptosporidium parvum and Giardia lamblia are protozoa capable of causing gastrointestinal diseases. Currently, these organisms are identified using immunofluorescent antibody (IFA)-based microscopy, and identification requires trained individuals for final confirmation. Since artificial neural networks (ANN) can provide an automated means of identification, thereby reducing human errors related to misidentification, ANN were developed to identify Cryptosporidium oocyst and Giardia cyst images. Digitized images of C. parvum oocysts and G. lamblia cysts stained with various commercial IFA reagents were used as positive controls. The images were captured using a color digital camera at 400× (total magnification), processed, and converted into a binary numerical array. A variety of “negative” images were also captured and processed. The ANN were developed using these images and a rigorous training and testing protocol. The Cryptosporidium oocyst ANN were trained with 1,586 images, while Giardia cyst ANN were trained with 2,431 images. After training, the best-performing ANN were selected based on an initial testing performance against 100 images (50 positive and 50 negative images). The networks were validated against previously “unseen” images of 500 Cryptosporidium oocysts (250 positive, 250 negative) and 282 Giardia cysts (232 positive, 50 negative). The selected ANNs correctly identified 91.8 and 99.6% of the Cryptosporidium oocyst and Giardia cyst images, respectively. These results indicate that ANN technology can be an alternate to having trained personnel for detecting these pathogens and can be a boon to underdeveloped regions of the world where there is a chronic shortage of adequately skilled individuals to detect these pathogens.     

基于卷积神经网络和循环神经网络的环形RNA剪接位点识别研究

本文提出了一种基于卷积神经网络和循环神经网络的深度学习模型,通过分析基因组序列数据,识别人基因组中环形RNA剪接位点.首先,根据预处理后的核苷酸序列,设计了2种网络深度、8种卷积核大小和3种长短期记忆(long short term memory,LSTM)参数,共8组16个模型;其次,进一步针对池化层进行均值池化和最大池化的测试,并加入GC含量提高模型的预测能力;最后,对已经实验验证过的人类精浆中环形RNA进行了预测.结果表明,卷积核尺寸为32×4、深度为1、LSTM参数为32的模型识别率最高,在训练集上为0.9824,在测试数据集上准确率为0.95,并且在实验验证数据上的正确识别率为83%.该模型在人的环形RNA剪接位点识别方面具有较好的性能.     

Varieties of Representation in Evolved and Embodied Neural Networks

In this paper I discuss one of the key issuesin the philosophy of neuroscience:neurosemantics. The project of neurosemanticsinvolves explaining what it means for states ofneurons and neural systems to haverepresentational contents. Neurosemantics thusinvolves issues of common concern between thephilosophy of neuroscience and philosophy ofmind. I discuss a problem that arises foraccounts of representational content that Icall ``the economy problem': the problem ofshowing that a candidate theory of mentalrepresentation can bear the work requiredwithin in the causal economy of a mind and anorganism. My approach in the current paper isto explore this and other key themes inneurosemantics through the use of computermodels of neural networks embodied and evolvedin virtual organisms. The models allow for thelaying bare of the causal economies of entireyet simple artificial organisms so that therelations between the neural bases of, forinstance, representation in perception andmemory can be regarded in the context of anentire organism. On the basis of thesesimulations, I argue for an account ofneurosemantics adequate for the solution of theeconomy problem.     

The Use of Artificial Neural Networks for Automatic Analysis and Genetic Identification of Gliadin Electrophoretic Spectra in Durum Wheat

Each wheat cultivar has a characteristic spectrum of gliadins. This makes it possible to use blocks of the components of reserve proteins as genetic markers when estimating seed purity and identity. However, identification of the blocks that constitute the electrophoretic spectrum is a complicated task. For this purpose artificial neural network (ANN) technology is proposed. Using experimental data, a teaching database and testing databases have been created. ANN was shown to be highly efficient (efficiency up to 100%) expert system for deciphering the electrophoretic spectra of gliadins of durum wheat cultivars.     

Use of Anti-Aedes aegypti Salivary Extract Antibody Concentration to Correlate Risk of Vector Exposure and Dengue Transmission Risk in Colombia

Norte de Santander is a region in Colombia with a high incidence of dengue virus (DENV). In this study, we examined the serum concentration of anti-Aedes salivary gland extract (SGE) antibodies as a biomarker of DENV infection and transmission, and assessed the duration of anti-SGE antibody concentration after exposure to the vector ceased. We also determined whether SGE antibody concentration could differentiate between positive and negative DENV infected individuals and whether there are differences in exposure for each DENV serotype. We observed a significant decrease in the concentration of IgG antibodies at least 40 days after returning to an “Ae. aegypti-free” area. In addition, we found significantly higher anti-SGE IgG concentrations in DENV positive patients with some difference in exposure to mosquito bites among DENV serotypes. We conclude that the concentration of IgG antibodies against SGE is an accurate indicator of risk of dengue virus transmission and disease presence.     

Neural Networks for Mindfulness and Emotion Suppression

Mindfulness, an attentive non-judgmental focus on “here and now” experiences, has been incorporated into various cognitive behavioral therapy approaches and beneficial effects have been demonstrated. Recently, mindfulness has also been identified as a potentially effective emotion regulation strategy. On the other hand, emotion suppression, which refers to trying to avoid or escape from experiencing and being aware of one’s own emotions, has been identified as a potentially maladaptive strategy. Previous studies suggest that both strategies can decrease affective responses to emotional stimuli. They would, however, be expected to provide regulation through different top-down modulation systems. The present study was aimed at elucidating the different neural systems underlying emotion regulation via mindfulness and emotion suppression approaches. Twenty-one healthy participants used the two types of strategy in response to emotional visual stimuli while functional magnetic resonance imaging was conducted. Both strategies attenuated amygdala responses to emotional triggers, but the pathways to regulation differed across the two. A mindful approach appears to regulate amygdala functioning via functional connectivity from the medial prefrontal cortex, while suppression uses connectivity with other regions, including the dorsolateral prefrontal cortex. Thus, the two types of emotion regulation recruit different top-down modulation processes localized at prefrontal areas. These different pathways are discussed.     

Intrathecal Morphine Use in Adolescent Idiopathic Scoliosis Surgery is Associated with Decreased Opioid Use and Decreased Length of Stay

BackgroundLength of stay (LOS) in the hospital following posterior spinal fusion (PSF) for adolescent idiopathic scoliosis (AIS) has decreased over the past decade due to well-defined postoperative clinical pathways, earlier mobilization, and improved pain control methods. Historically, liberal use of parenteral and oral opioids for pain control caused side effects, resulting in delayed discharge. Intraoperative intrathecal morphine (ITM) has been posited to reduce the need for postoperative opioids and to expedite the discharge process. This study examines the relationship between the use of ITM with average required postoperative opioid usage and with average LOS.MethodsThis IRB-approved retrospective cohort study examined 105 patients with AIS who received PSF with instrumentation split into two cohorts. One cohort underwent PSF via standard surgical protocol (n=40) while the other cohort received intraoperative ITM with the standard surgical protocol (n=65). Power analysis demonstrated a study power of 0.8. LOS and total postoperative opioid analgesic medication (morphine milligram equivalent, MME) data were collected. Age at surgery, gender, number of spinal levels fused, estimated intraoperative blood loss (EBL), preoperative Cobb angle, and any complications related to the use of ITM were also recorded. Continuous variables were analyzed with Student’s t-test and categorical variables were analyzed with chi-square independent-sample tests using SAS 9.4 (α = 0.05).ResultsPatients who were treated with ITM displayed shorter LOS (p<0.0001) and reduced postoperative analgesic requirement (p<0.0001). Patients who received ITM spent an average of 1.8 fewer midnights in the hospital and received an average of 221.2 MME less than patients who received standard protocol (57% decrease). There were no significant differences between the two groups for any other variable.ConclusionIntraoperative ITM is a simple and effective treatment for scoliosis surgeons to better control postoperative pain in patients, reduce the risk of dependency, and achieve earlier discharge from the hospital. Shortened LOS reduces the overall cost of care, benefitting patients, hospitals, and insurance companies. Based on the results of this study and several earlier studies, the authors recommended that scoliosis surgeons consider incorporating use of ITM into their standard operative protocols. Level of Evidence: IV