Neighbourhood looking glass: 360º automated characterisation of the built environment for neighbourhood effects research.

BACKGROUND: Neighbourhood quality has been connected with an array of health issues, but neighbourhood research has been limited by the lack of methods to characterise large geographical areas. This study uses innovative computer vision methods and a new big data source of street view images to automatically characterise neighbourhood built environments. METHODS: A total of 430 000 images were obtained using Google's Street View Image API for Salt Lake City, Chicago and Charleston. Convolutional neural networks were used to create indicators of street greenness, crosswalks and building type. We implemented log Poisson regression models to estimate associations between built environment features and individual prevalence of obesity and diabetes in Salt Lake City, controlling for individual-level and zip code-level predisposing characteristics. RESULTS: Computer vision models had an accuracy of 86%-93% compared with manual annotations. Charleston had the highest percentage of green streets (79%), while Chicago had the highest percentage of crosswalks (23%) and commercial buildings/apartments (59%). Built environment characteristics were categorised into tertiles, with the highest tertile serving as the referent group. Individuals living in zip codes with the most green streets, crosswalks and commercial buildings/apartments had relative obesity prevalences that were 25%-28% lower and relative diabetes prevalences that were 12%-18% lower than individuals living in zip codes with the least abundance of these neighbourhood features. CONCLUSION: Neighbourhood conditions may influence chronic disease outcomes. Google Street View images represent an underused data resource for the construction of built environment features.

Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks.

Contextual information plays an important role in solving vision problems such as image segmentation. However, extracting contextual information and using it in an effective way remains a difficult problem. To address this challenge, we propose a multi-resolution contextual framework, called cascaded hierarchical model (CHM), which learns contextual information in a hierarchical framework for image segmentation. At each level of the hierarchy, a classifier is trained based on downsampled input images and outputs of previous levels. Our model then incorporates the resulting multi-resolution contextual information into a classifier to segment the input image at original resolution. We repeat this procedure by cascading the hierarchical framework to improve the segmentation accuracy. Multiple classifiers are learned in the CHM; therefore, a fast and accurate classifier is required to make the training tractable. The classifier also needs to be robust against overfitting due to the large number of parameters learned during training. We introduce a novel classification scheme, called logistic disjunctive normal networks (LDNN), which consists of one adaptive layer of feature detectors implemented by logistic sigmoid functions followed by two fixed layers of logical units that compute conjunctions and disjunctions, respectively. We demonstrate that LDNN outperforms state-of-theart classifiers and can be used in the CHM to improve object segmentation performance.

A promising method of enhancement for early detection of ischemic stroke.

BACKGROUND: Computed Tomography (CT) scan without contrast is the modality of choice for diagnosis of stroke. However, routine brain CT scan, with linear processing has some limitations in early diagnosis of ischemic stroke. The aim of this study was to evaluate and compare the sensitivity and specificity of processed CT images with conventional ones in early diagnosis of cerebrovascular attack (CVA). PATIENTS AND METHODS: This was a self-controlled study conducted in a university referal hospital from 2010 to 2011. Seventy CT scans underwent a process using Laplacian Pyramid transform. Thirty five of participants were diagnosed with CVA while others had only headache and no ischemic stroke diagnosis based on the first and follow-up CT scans. A neuroradiologist made diagnosis with and without the help of processed CT scans. The McNemar and Wilcoxon analysis were used to compare the sensitivity, specificity, positive and negative predictive values of two methods. RESULTS: The sensitivity (% 65.7 vs. %31.4, P value = 0.001), positive predictive value (% 85.2 vs. % 61, P value = 0.03) and negative predictive value (% 73.9% vs. %49, P value = 0.01) of the processed method were significantly higher than the routine one, while no difference was seen in specificity (% 88.6 vs. %77.1, P value = 0.15). Moreover, the accuracy of the processed method was significantly better than the linear one (P value < 0.001). CONCLUSIONS: It was concluded that nonlinear modified Laplacian Pyramid method can composed CT scans which can be more helpful in early detection of ischemic stroke.