Automatic fetal biometry prediction using a novel deep convolutional network architecture

PurposeFetal biometric measurements face a number of challenges, including the presence of speckle, limited soft-tissue contrast and difficulties in the presence of low amniotic fluid. This work proposes a convolutional neural network for automatic segmentation and measurement of fetal biometric parameters, including biparietal diameter (BPD), head circumference (HC), abdominal circumference (AC), and femur length (FL) from ultrasound images that relies on the attention gates incorporated into the multi-feature pyramid Unet (MFP-Unet) network.MethodsThe proposed approach, referred to as Attention MFP-Unet, learns to extract/detect salient regions automatically to be treated as the object of interest via the attention gates. After determining the type of anatomical structure in the image using a convolutional neural network, Niblack's thresholding technique was applied as pre-processing algorithm for head and abdomen identification, whereas a novel algorithm was used for femur extraction. A publicly-available dataset (HC18 grand-challenge) and clinical data of 1334 subjects were utilized for training and evaluation of the Attention MFP-Unet algorithm.ResultsDice similarity coefficient (DSC), hausdorff distance (HD), percentage of good contours, the conformity coefficient, and average perpendicular distance (APD) were employed for quantitative evaluation of fetal anatomy segmentation. In addition, correlation analysis, good contours, and conformity were employed to evaluate the accuracy of the biometry predictions. Attention MFP-Unet achieved 0.98, 1.14 mm, 100%, 0.95, and 0.2 mm for DSC, HD, good contours, conformity, and APD, respectively.ConclusionsQuantitative evaluation demonstrated the superior performance of the Attention MFP-Unet compared to state-of-the-art approaches commonly employed for automatic measurement of fetal biometric parameters.     

A structured decision making analysis to increase a Red-cockaded Woodpecker population and balance stakeholder objectives for a National Forest

Longleaf pine (Pinus palustris) savanna is a biodiverse ecosystem native to the southeastern United States. Due to fire suppression and timber harvest, longleaf pine has declined to 3% of its original range. The extant forest provides habitat for many threatened and endangered species, including the endangered Red-cockaded Woodpecker (Picoides borealis; RCW), a cavity-nesting bird that co-evolved with fire-maintained forest, resulting in savanna-like old-growth forest as the bird’s preferred habitat. Our study site, the Oakmulgee Ranger District of the Talladega National Forest, harbors the largest RCW population in Alabama and is managed with an emphasis on RCW conservation. The United States Forest Service (USFS) also manages the Oakmulgee for uses such as wildlife conservation, recreation, and timber harvest. Despite efforts to restore RCW habitat and install artificial cavities in the Oakmulgee, the number of RCW groups has not exceeded 123, although the Recovery Plan objective is 394 groups. Our project was motivated by the USFS expressing interest in determining why the RCW population has not exceeded 123 groups. We proposed using structured decision making (SDM) with the USFS and other stakeholders to address this problem. Our goals were to explicitly define management objectives, build a Bayesian belief network with a model of how decision alternatives are believed to affect management objectives, and use a sensitivity analysis to determine the part of the model to which RCW population growth was most sensitive. Therefore, results from the analysis were expected to give insights into 1) ecological factors limiting RCW population growth, 2) how management can overcome these limits, plus 3) the relative expected ability of different decision alternatives to satisfy multiple objectives in addition to increasing RCW group number. We held four SDM workshops with representatives from the USFS, the Animal and Plant Health Inspection Service, the Longleaf Alliance, the Birmingham Audubon Society, and local residents. Stakeholder objectives consisted of maximizing the following: RCW group number, forest health, recreational enjoyment, community economic health, and aesthetics. Cavity insert installation had the greatest probability of increasing the number of RCW groups. The number of RCW groups was most affected by cavity availability, adult survival, reproductive output, food availability, and herbaceous understory. Prescribed burning was most likely to meet the combination of stakeholder objectives, followed by midstory removal. Our findings suggest that cavity installation efforts may need to be increased in the Oakmulgee to increase RCW group number. Also it could be beneficial to investigate how RCWs select cavity tree locations with the goal of increasing the chance that RCWs use artificial cavities to form new groups. The Bayesian belief network provided insights into factors limiting RCW population growth and how management can overcome these limits. The Bayesian belief network also can be used to prioritize management methods in the Oakmulgee given stakeholder objectives and time constraints.     

Pockmarks enhance deep‐sea benthic biodiversity: a case study in the western Mediterranean Sea

Aim Pockmarks are craters on the sea floor formed by sub‐sea‐floor fluid expulsions, which occur world‐wide at all ocean depths. These habitats potentially host a highly specialized fauna that can exploit the hydrocarbons released. Pockmarks at relatively shallow depths can be easily destroyed by human activities, such as bottom trawling. In the present study, we investigated the combined effects of sea‐floor heterogeneity, rate of fluid emission and trophic conditions of different pockmarks on the biodiversity of the deep‐sea assemblages. Location Continental slope of the Gulf of Lions, western Mediterranean Sea, at water depths from 265 to 434 m. Methods We investigated the biodiversity associated with sea‐floor pockmarks that are both inactive and that have active gas emissions. Control sites were selected on the sea floor outside the influence of the gas seepage, both within and outside the pockmark fields. We examined the combined effects of: (i) sea‐floor heterogeneity; (ii) variable levels of fluid (gas) emissions; and (iii) trophic characteristics of the meiofaunal assemblage structure and nematode diversity. Results Sediments within the pockmark fields had lower meiofaunal abundance and biomass when compared with the surrounding sediments that were not influenced by the gas seepage. Although several higher taxa were absent in the pockmarks (e.g. Turbellaria, Tardigrada, Cumacea, Isopoda, Tanaidacea, Nemertina and Priapulida, which were present in the control areas), the richness of the nematode species within all of these pockmarks was very high. About 25% of the total species encountered in the deep‐sea sediments of the investigated areas was exclusively associated with these pockmarks. Main conclusions We conclude that both active and inactive pockmarks provide significant contributions to the regional (gamma) diversity of the continental slope in the western Mediterranean Sea, and thus the protection of these special and fragile habitats is highly relevant to the conservation of deep‐sea biodiversity.     

Machine learning in protein structure prediction

Prediction of protein structure from sequence has been intensely studied for many decades, owing to the problem's importance and its uniquely well-defined physical and computational bases. While progress has historically ebbed and flowed, the past two years saw dramatic advances driven by the increasing “neuralization” of structure prediction pipelines, whereby computations previously based on energy models and sampling procedures are replaced by neural networks. The extraction of physical contacts from the evolutionary record; the distillation of sequence–structure patterns from known structures; the incorporation of templates from homologs in the Protein Databank; and the refinement of coarsely predicted structures into finely resolved ones have all been reformulated using neural networks. Cumulatively, this transformation has resulted in algorithms that can now predict single protein domains with a median accuracy of 2.1 Å, setting the stage for a foundational reconfiguration of the role of biomolecular modeling within the life sciences.     

Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives

Over the last years, technological innovation in Radiotherapy (RT) led to the introduction of Magnetic Resonance-guided RT (MRgRT) systems.Due to the higher soft tissue contrast compared to on-board CT-based systems, MRgRT is expected to significantly improve the treatment in many situations. MRgRT systems may extend the management of inter- and intra-fraction anatomical changes, offering the possibility of online adaptation of the dose distribution according to daily patient anatomy and to directly monitor tumor motion during treatment delivery by means of a continuous cine MR acquisition.Online adaptive treatments require a multidisciplinary and well-trained team, able to perform a series of operations in a safe, precise and fast manner while the patient is waiting on the treatment couch.Artificial Intelligence (AI) is expected to rapidly contribute to MRgRT, primarily by safely and efficiently automatising the various manual operations characterizing online adaptive treatments. Furthermore, AI is finding relevant applications in MRgRT in the fields of image segmentation, synthetic CT reconstruction, automatic (on-line) planning and the development of predictive models based on daily MRI.This review provides a comprehensive overview of the current AI integration in MRgRT from a medical physicist’s perspective. Medical physicists are expected to be major actors in solving new tasks and in taking new responsibilities: their traditional role of guardians of the new technology implementation will change with increasing emphasis on the managing of AI tools, processes and advanced systems for imaging and data analysis, gradually replacing many repetitive manual tasks.     

草原火烧严重度燃烧指数的适用性比较分析

基于遥感影像的燃烧指数被广泛应用于火烧严重度(fire severity)研究,选取适宜燃烧指数定量评估草原火烧严重度,对草原生态系统植被的恢复与管理具有重要意义。以呼伦贝尔草原火烧迹地为研究区域,基于landsat8 OLI影像分别构建4种燃烧指数(NBR、NSTV1、d NBR和Rd NBR)与综合燃烧指数(CBI)的回归模型并进行精度验证,对比分析不同燃烧指数识别草原火烧严重度等级的能力。结果表明:在燃烧指数与CBI构建的回归模型中,d NBR指数的相关性(n=70,R~2=0.856)最高;4种燃烧指数识别火烧严重度的精度存在差异,中度火烧区域(1CBI≤2)内,NSTV1指数识别精度最高,未过火(CBI=0)、轻度火烧(0CBI≤1)和重度火烧(2CBI≤3)区域内,d NBR指数识别精度均表现最好,分别为80%、62.5%和100%;基于不同燃烧指数的草原火烧严重度制图中,d NBR指数的总体精度同样高于其他燃烧指数,为82.1%,Kappa系数高达0.76。综上所述,d NBR指数是草原火烧严重度分析与评价的适宜遥感指数。     

Quantitative structure–activity relationship analysis using deep learning based on a novel molecular image input technique

Quantitative structure–activity relationship (QSAR) analysis uses structural, quantum chemical, and physicochemical features calculated from molecular geometry as explanatory variables predicting physiological activity. Recently, deep learning based on advanced artificial neural networks has demonstrated excellent performance in the discipline of QSAR research. While it has properties of feature representation learning that directly calculate feature values from molecular structure, the use of this potential function is limited in QSAR modeling. The present study applied this function of feature representation learning to QSAR analysis by incorporating 360° images of molecular conformations into deep learning. Accordingly, I successfully constructed a highly versatile identification model for chemical compounds that induce mitochondrial membrane potential disruption with the external validation area under the receiver operating characteristic curve of ≥0.9.     

DeepNitro: Prediction of Protein Nitration and Nitrosylation Sites by Deep Learning

Protein nitration and nitrosylation are essential post-translational modifications(PTMs)involved in many fundamental cellular processes. Recent studies have revealed that excessive levels of nitration and nitrosylation in some critical proteins are linked to numerous chronic diseases.Therefore, the identification of substrates that undergo such modifications in a site-specific manner is an important research topic in the community and will provide candidates for targeted therapy. In this study, we aimed to develop a computational tool for predicting nitration and nitrosylation sites in proteins. We first constructed four types of encoding features, including positional amino acid distributions, sequence contextual dependencies, physicochemical properties, and position-specificscoring features, to represent the modified residues. Based on these encoding features, we established a predictor called DeepNitro using deep learning methods for predicting protein nitration and nitrosylation. Using n-fold cross-validation, our evaluation shows great AUC values for DeepNitro, 0.65 for tyrosine nitration, 0.80 for tryptophan nitration, and 0.70 for cysteine nitrosylation, respectively,demonstrating the robustness and reliability of our tool. Also, when tested in the independent dataset, DeepNitro is substantially superior to other similar tools with a 7%à42% improvement in the prediction performance. Taken together, the application of deep learning method and novel encoding schemes, especially the position-specific scoring feature, greatly improves the accuracy of nitration and nitrosylation site prediction and may facilitate the prediction of other PTM sites. DeepNitro is implemented in JAVA and PHP and is freely available for academic research at http://deepnitro.renlab.org.     

Effect of nano-silver hydrogel coating film on deep partial thickness scald model of rabbit

Objective

Observing the effect of nano-silver hydrogel coating film on deep partial thickness scald model of rabbit.

Bioenergetic Constraints on Microbial Hydrogen Utilization in Precambrian Deep Crustal Fracture Fluids

Precambrian Shield rocks host the oldest fracture fluids on Earth, with residence times up to a billion years or more. Water–rock reactions in these fracture systems over geological time have produced highly saline fluids, which can contain millimolar concentrations of H₂. Mixing of these ancient Precambrian fluids with meteoric or palaeo-meteoric water can occur through tectonic fracturing, providing microbial inocula and redox couples to fuel blooms of subsurface growth. Here, we present geochemical and microbiological data from a series of borehole fluids of varying ionic strength (0.6–6.4 M) from the Thompson Mine (Manitoba) within the Canadian Precambrian Shield. Thermodynamic calculations demonstrate sufficient energy for H₂-based catabolic reactions across the entire range of ionic strengths during mixing of high ionic strength fracture fluids with meteoric water, although microbial H₂ consumption and cultivable H₂-utilizing microbes were only detected in fluids of ≤1.9 M ionic strength. This pattern of microbial H₂ utilization can be explained by the higher potential bioenergetic cost of organic osmolyte synthesis at increasing ionic strengths. We propose that further research into the bioenergetics of osmolyte regulation in halophiles is warranted to better constrain the habitability zones of hydrogenotrophic ecosystems in both terrestrial subsurface, including potential future radioactive waste disposal sites, and other planetary body crustal environments, including Mars.