Deep Green Diagnostics: Urban Green Space Analysis Using Deep Learning and Drone Images.
Ontology highlight
ABSTRACT:
SUBMITTER: Moreno-Armendariz MA
PROVIDER: S-EPMC6928838 | biostudies-literature | 2019 Nov
REPOSITORIES: biostudies-literature
Publications
Deep Green Diagnostics: Urban Green Space Analysis Using Deep Learning and Drone Images.
Moreno-Armendáriz Marco A MA Calvo Hiram H Duchanoy Carlos A CA López-Juárez Anayantzin P AP Vargas-Monroy Israel A IA Suarez-Castañon Miguel Santiago MS
Sensors (Basel, Switzerland) 20191130 23
Nowadays, more than half of the world's population lives in urban areas, and this number continues increasing. Consequently, there are more and more scientific publications that analyze health problems of people associated with living in these highly urbanized locations. In particular, some of the recent work has focused on relating people's health to the quality and quantity of urban green areas. In this context, and considering the huge amount of land area in large cities that must be supervis ...[more]
Similar Datasets
Project description:Context:Landscape metrics represent powerful tools for quantifying landscape structure, but uncertainties persist around their interpretation. Urban settings add unique considerations, containing habitat structures driven by the surrounding built-up environment. Understanding urban ecosystems, however, should focus on the habitats rather than the matrix. Objectives:We coupled a multivariate approach with landscape metric analysis to overcome existing shortcomings in interpretation. We then explored relationships between landscape characteristics and modelled ecosystem service provision. Methods:We used principal component analysis and cluster analysis to isolate the most effective measures of landscape variability and then grouped habitat patches according to their attributes, independent of the surrounding urban form. We compared results to the modelled provision of three ecosystem services. Seven classes resulting from cluster analysis were separated primarily on patch area, and secondarily by measures of shape complexity and inter-patch distance. Results:When compared to modelled ecosystem services, larger patches up to 10 ha in size consistently stored more carbon per area and supported more pollinators, while exhibiting a greater risk of soil erosion. Smaller, isolated patches showed the opposite, and patches larger than 10 ha exhibited no additional areal benefit. Conclusions:Multivariate landscape metric analysis offers greater confidence and consistency than analysing landscape metrics individually. Independent classification avoids the influence of the urban matrix surrounding habitats of interest, and allows patches to be grouped according to their own attributes. Such a grouping is useful as it may correlate more strongly with the characteristics of landscape structure that directly affect ecosystem function.
| S-EPMC6561088 | biostudies-literature
Project description:One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed. In this study, we propose a novel application of deep learning principles to reconstruct undersampled PAM images and transcend the trade-off between spatial resolution and imaging speed. We compared various convolutional neural network (CNN) architectures, and selected a Fully Dense U-net (FD U-net) model that produced the best results. To mimic various undersampling conditions in practice, we artificially downsampled fully-sampled PAM images of mouse brain vasculature at different ratios. This allowed us to not only definitively establish the ground truth, but also train and test our deep learning model at various imaging conditions. Our results and numerical analysis have collectively demonstrated the robust performance of our model to reconstruct PAM images with as few as 2% of the original pixels, which can effectively shorten the imaging time without substantially sacrificing the image quality.
| S-EPMC7858223 | biostudies-literature
Project description:IntroductionEvaluating histopathology via machine learning has gained research and clinical interest, and the performance of supervised learning tasks has been described in various areas of medicine. Unsupervised learning of histological images has the advantage of reproducibility for labeling; however, the relationship between unsupervised evaluation and clinical information remains unclear in nephrology.MethodsWe propose an unsupervised approach combining convolutional neural networks (CNNs) and a visualization algorithm to cluster the histological images and calculate the score for patients. We applied the approach to the entire images or patched images of the glomerulus of kidney biopsy samples stained with hematoxylin and eosin obtained from 68 patients with immunoglobulin A nephropathy. We assessed the relationship between the obtained scores and clinical variables of urinary occult blood, urinary protein, serum creatinine (SCr), systolic blood pressure, and age.ResultsThe glomeruli of the patients were classified into 12 distinct classes and 10 patches. The output of the fine-tuned CNN, which we defined as the histological scores, had significant relationships with assessed clinical variables. In addition, the clustering and visualization results suggested that the defined clusters captured important findings when evaluating renal histopathology. For the score of the patch-based cluster containing crescentic glomeruli, SCr (coefficient = 0.09, P = 0.019) had a significant relationship.ConclusionThe proposed approach could successfully extract features that were related to the clinical variables from the kidney biopsy images along with the visualization for interpretability. The approach could aid in the quantified evaluation of renal histopathology.
| S-EPMC8418980 | biostudies-literature
Project description:BackgroundDevelopment and validation of a deep learning method to automatically segment the peri-ampullary (PA) region in magnetic resonance imaging (MRI) images.MethodsA group of patients with or without periampullary carcinoma (PAC) was included. The PA regions were manually annotated in MRI images by experts. Patients were randomly divided into one training set, one validation set, and one test set. Deep learning methods were developed to automatically segment the PA region in MRI images. The segmentation performance of the methods was compared in the validation set. The model with the highest intersection over union (IoU) was evaluated in the test set.ResultsThe deep learning algorithm achieved optimal accuracies in the segmentation of the PA regions in both T1 and T2 MRI images. The value of the IoU was 0.68, 0.68, and 0.64 for T1, T2, and combination of T1 and T2 images, respectively.ConclusionsDeep learning algorithm is promising with accuracies of concordance with manual human assessment in segmentation of the PA region in MRI images. This automated non-invasive method helps clinicians to identify and locate the PA region using preoperative MRI scanning.
| S-EPMC8193851 | biostudies-literature
Project description:IntroductionThe number of glomeruli and glomerulosclerosis evaluated on kidney biopsy slides constitute standard components of a renal pathology report. Prevailing methods for glomerular assessment remain manual, labor intensive, and nonstandardized. We developed a deep learning framework to accurately identify and segment glomeruli from digitized images of human kidney biopsies.MethodsTrichrome-stained images (n = 275) from renal biopsies of 171 patients with chronic kidney disease treated at the Boston Medical Center from 2009 to 2012 were analyzed. A sliding window operation was defined to crop each original image to smaller images. Each cropped image was then evaluated by at least 3 experts into 3 categories: (i) no glomerulus, (ii) normal or partially sclerosed (NPS) glomerulus, and (iii) globally sclerosed (GS) glomerulus. This led to identification of 751 unique images representing nonglomerular regions, 611 images with NPS glomeruli, and 134 images with GS glomeruli. A convolutional neural network (CNN) was trained with cropped images as inputs and corresponding labels as output. Using this model, an image processing routine was developed to scan the test images to segment the GS glomeruli.ResultsThe CNN model was able to accurately discriminate nonglomerular images from NPS and GS images (performance on test data: Accuracy: 92.67% ± 2.02% and Kappa: 0.8681 ± 0.0392). The segmentation model that was based on the CNN multilabel classifier accurately marked the GS glomeruli on the test data (Matthews correlation coefficient = 0.628).ConclusionThis work demonstrates the power of deep learning for assessing complex histologic structures from digitized human kidney biopsies.
| S-EPMC6612039 | biostudies-literature
Project description:BackgroundExposure to a diverse environmental microbiome is thought to play an important role in "educating" the immune system and facilitating competitive exclusion of pathogens to maintain human health. Vegetation and soil are key sources of airborne microbiota--the aerobiome. A limited number of studies have attempted to characterize the dynamics of near surface green space aerobiomes, and no studies to date have investigated these dynamics from a vertical perspective. Vertical stratification in the aerobiome could have important implications for public health and for the design, engineering, and management of urban green spaces.ObjectivesThe primary objectives of this study were to: a) assess whether significant vertical stratification in bacterial species richness and evenness (alpha diversity) of the aerobiome occurred in a parkland habitat in Adelaide, South Australia; b) assess whether significant compositional differences (beta diversity) between sampling heights occurred; and c) to preliminarily assess whether there were significant altitudinal differences in potentially pathogenic and beneficial bacterial taxa.MethodsWe combined an innovative columnar sampling method at soil level, 0.0, 0.5, 1.0, and 2.0m, using passive petri dish sampling to collect airborne bacteria. We used a geographic information system (GIS) to select study sites, and we used high-throughput sequencing of the bacterial 16S rRNA gene to assess whether significant vertical stratification of the aerobiome occurred.ResultsOur results provide evidence of vertical stratification in both alpha and beta (compositional) diversity of airborne bacterial communities, with diversity decreasing roughly with height. We also found significant vertical stratification in potentially pathogenic and beneficial bacterial taxa.DiscussionAlthough additional research is needed, our preliminary findings point to potentially different exposure attributes that may be contingent on human height and activity type. Our results lay the foundations for further research into the vertical characteristics of urban green space aerobiomes and their implications for public health and urban planning. https://doi.org/10.1289/EHP7807.
| S-EPMC7687659 | biostudies-literature
Project description:Tumor histology is an important predictor of therapeutic response and outcomes in lung cancer. Tissue sampling for pathologist review is the most reliable method for histology classification, however, recent advances in deep learning for medical image analysis allude to the utility of radiologic data in further describing disease characteristics and for risk stratification. In this study, we propose a radiomics approach to predicting non-small cell lung cancer (NSCLC) tumor histology from non-invasive standard-of-care computed tomography (CT) data. We trained and validated convolutional neural networks (CNNs) on a dataset comprising 311 early-stage NSCLC patients receiving surgical treatment at Massachusetts General Hospital (MGH), with a focus on the two most common histological types: adenocarcinoma (ADC) and Squamous Cell Carcinoma (SCC). The CNNs were able to predict tumor histology with an AUC of 0.71(p = 0.018). We also found that using machine learning classifiers such as k-nearest neighbors (kNN) and support vector machine (SVM) on CNN-derived quantitative radiomics features yielded comparable discriminative performance, with AUC of up to 0.71 (p = 0.017). Our best performing CNN functioned as a robust probabilistic classifier in heterogeneous test sets, with qualitatively interpretable visual explanations to its predictions. Deep learning based radiomics can identify histological phenotypes in lung cancer. It has the potential to augment existing approaches and serve as a corrective aid for diagnosticians.
| S-EPMC7943565 | biostudies-literature
Project description:Urban green space is thought to contribute to citizen happiness by promoting physical and mental health. Nevertheless, how urban green space and happiness are related across many countries with different socioeconomic conditions has not been explored. By measuring the urban green space score (UGS) from high-resolution satellite imagery of 90 global cities covering 179,168 km2 and 230 million people in 60 developed countries, we find that the amount of urban green space and GDP are correlated with a nation's happiness level. More specifically, urban green space and GDP are each individually associated with happiness. Yet, only urban green space is related to happiness in the 30 wealthiest countries, whereas GDP alone can explain happiness in the subsequent 30 countries in terms of wealth. We further show that the relationship between urban green space and happiness is mediated by social support and that GDP moderates this relationship. These findings corroborate the importance of maintaining urban green space as a place for social cohesion to support people's happiness.Supplementary informationThe online version contains supplementary material available at 10.1140/epjds/s13688-021-00278-7.
| S-EPMC8164893 | biostudies-literature
Project description:Contemporary epidemiological methods testing the associations between green space and psychological well-being treat all vegetation cover as equal. However, there is very good reason to expect that variations in ecological "quality" (number of species, integrity of ecological processes) may influence the link between access to green space and benefits to human health and well-being. We test the relationship between green space quality and restorative benefit in an inner city urban population in Bradford, United Kingdom. We selected 12 urban parks for study where we carried out botanical and faunal surveys to quantify biodiversity and assessed the site facilities of the green space (cleanliness, provision of amenities). We also conducted 128 surveys with park users to quantify psychological restoration based on four self-reported measure of general restoration, attention-grabbing distractions, being away from everyday life, and site preference. We present three key results. First, there is a positive association between site facilities and biodiversity. Second, restorative benefit is predicted by biodiversity, which explained 43% of the variance in restorative benefit across the parks, with minimal input from other variables. Third, the benefits accrued through access to green space were unrelated to age, gender, and ethnic background. The results add to a small but growing body of evidence that emphasize the role of nature in contributing to the well-being of urban populations and, hence, the need to consider biodiversity in the design of landscapes that enhance multiple ecosystem services.
| S-EPMC6277587 | biostudies-literature
Project description:The COVID-19 pandemic is causing a major outbreak in more than 150 countries around the world, having a severe impact on the health and life of many people globally. One of the crucial step in fighting COVID-19 is the ability to detect the infected patients early enough, and put them under special care. Detecting this disease from radiography and radiology images is perhaps one of the fastest ways to diagnose the patients. Some of the early studies showed specific abnormalities in the chest radiograms of patients infected with COVID-19. Inspired by earlier works, we study the application of deep learning models to detect COVID-19 patients from their chest radiography images. We first prepare a dataset of 5000 Chest X-rays from the publicly available datasets. Images exhibiting COVID-19 disease presence were identified by board-certified radiologist. Transfer learning on a subset of 2000 radiograms was used to train four popular convolutional neural networks, including ResNet18, ResNet50, SqueezeNet, and DenseNet-121, to identify COVID-19 disease in the analyzed chest X-ray images. We evaluated these models on the remaining 3000 images, and most of these networks achieved a sensitivity rate of 98% ( ± 3%), while having a specificity rate of around 90%. Besides sensitivity and specificity rates, we also present the receiver operating characteristic (ROC) curve, precision-recall curve, average prediction, and confusion matrix of each model. We also used a technique to generate heatmaps of lung regions potentially infected by COVID-19 and show that the generated heatmaps contain most of the infected areas annotated by our board certified radiologist. While the achieved performance is very encouraging, further analysis is required on a larger set of COVID-19 images, to have a more reliable estimation of accuracy rates. The dataset, model implementations (in PyTorch), and evaluations, are all made publicly available for research community at https://github.com/shervinmin/DeepCovid.git.
| S-EPMC7372265 | biostudies-literature