Structural Metrics Research Articles

Evolution of system connectivity to support food production in the Indus Basin in Pakistan

Sustainability challenges related to food production arise from multiple nature-society interactions occurring over long time periods. Traditional methods of quantitative analysis do not represent long-term changes in the networks of system components, including institutions and knowledge that affect system behavior. Here, we develop an approach to study system structure and evolution by combining a qualitative framework that represents sustainability-relevant human, technological, and environmental components, and their interactions, mediated by knowledge and institutions, with network modeling that enables quantitative metrics. We use this approach to examine the water and food system in the Punjab province of the Indus River Basin in Pakistan, exploring how food production has been sustained, despite high population growth, periodic floods, and frequent political and economic disruptions. Using network models of five periods spanning 75 y (1947 to 2022), we examine how quantitative metrics of network structure relate to observed sustainability-relevant outcomes and how potential interventions in the system affect these quantitative metrics. We find that the persistent centrality of some and evolving centrality of other key nodes, coupled with the increasing number and length of pathways connecting them, are associated with sustaining food production in the system over time. Our assessment of potential interventions shows that regulating groundwater pumping and phasing out fossil fuels alters network pathways, and helps identify potential vulnerabilities for future food production.

Fuel Drivers of Fire Behaviour in Coastal Mallee Shrublands

Coastal mallee shrubland wildfires present challenges for accurately predicting fire spread sustainability and rate of spread. In this study, we assess the fuel drivers contributing to coastal mallee shrubland fires. A review of shrubland fire behaviour models and fuel metrics was conducted to determine the current practice of assessing shrubland fuels. This was followed by workshops designed to elicit which fuel structural metrics are key drivers of fire behaviour in coastal mallee shrublands. We found that height is the most commonly used fuel metric in shrubland fire models due to the ease of collection in situ or as a surrogate for more complex fuel structures. Expert workshop results suggest that cover and connectivity metrics are key to modelling fire behaviour in coastal mallee shrublands. While height and cover are frequently used in fire models, we conclude that connectivity metrics would offer additional insights into fuel drivers in mallee shrublands. Future research into coastal mallee fire behaviour should include the measurements of fuel height, cover, and horizontal and vertical connectivity.

Program evaluation and early outcomes of a severe preeclampsia and eclampsia maternal safety bundle in a single institution in the Philippines

BACKGROUND: To reduce maternal morbidity and mortality associated with hypertension, standards for maternal safety and efforts to implement a structured team approach have been undertaken. Following the formulation of a policy document, a maternal safety bundle was developed. The implementation of bundle components including eclampsia kits, clinical pathways, and educational module occurred in phases due to pandemic restrictions. An eclampsia kit and clinical pathways were implemented in 2020. An online lecture was launched in 2021 followed by in-person eclampsia simulation workshop beginning 2022. OBJECTIVES: This paper aims to report the early outcomes of a severe preeclampsia and eclampsia maternal safety bundle implementation in a private hospital between 2020 to 2023. MATERIALS AND METHODS: Demographic information, posttest knowledge assessment and pre- and post- eclampsia workshop confidence scores were recorded. Structure, process, and outcome measures were determined. Descriptive statistics were used for participant demographics and score percentages. Paired t-Test with a significance level of P<0.05 was used to compare the pre- and post-simulation confidence scores. Summary data for outcome and process metrics were manually calculated. Summary categorical data was used for structure metrics. RESULTS: Two hundred eighty-eight (288) participants completed the online didactic lecture. Average posttest knowledge assessment score was 88.1%, 88.88%, and 82.6% from 2020 to 2023. Ninety-nine participants completed the eclampsia simulation workshops. Mean post-simulation confidence scores were greater than mean pre-simulation confidence scores (42.3 vs. 39, p=0.0259 in 2022 and 41.975 vs 36.65, P=0.0035 in 2023). There is 100% compliance with timely management of severe hypertension and eclampsia prevention and a decreasing trend in hypertension related severe maternal morbidity rates. CONCLUSION: A severe preeclampsia and eclampsia maternal safety bundle is a feasible quality improvement initiative that promotes peer learning, strengthens clinical competencies, and improves access to emergency resuscitation supplies. The results of this program evaluation may serve as a framework for implementing quality improvement initiatives on maternal safety.

Pretreatment Brain White Matter Integrity Associated With Neuropathic Pain Relief and Changes in Temporal Summation of Pain Following Ketamine

Neuropathic pain (NP) is a prevalent condition often associated with heightened pain responsiveness suggestive of central sensitization. Neuroimaging biomarkers of treatment outcomes may help develop personalized treatment strategies, but white matter (WM) properties have been underexplored for this purpose. Here we assessed whether WM pathways of the default mode network (DMN: medial prefrontal cortex [mPFC], posterior cingulate cortex, and precuneus) and descending pain modulation system (periaqueductal gray [PAG]) are associated with ketamine analgesia and attenuated temporal summation of pain (TSP, reflecting central sensitization) in NP. We used a fixel-based analysis of diffusion-weighted imaging data to evaluate WM microstructure (fiber density [FD]) and macrostructure (fiber bundle cross-section) within the DMN and mPFC-PAG pathways in 70 individuals who underwent magnetic resonance imaging and TSP testing; 35 with NP who underwent ketamine treatment and 35 age- and sex-matched pain-free individuals. Individuals with NP were assessed before and 1 month after treatment; those with ≥30% pain relief were considered responders (n = 18), or otherwise as nonresponders (n = 17). We found that WM structure within the DMN and mPFC-PAG pathways did not differentiate responders from nonresponders. However, pretreatment FD in the anterior limb of the internal capsule correlated with pain relief (r=.48). Moreover, pretreatment FD in the DMN (left mPFC-precuneus/posterior cingulate cortex; r=.52) and mPFC-PAG (r=.42) negatively correlated with changes in TSP. This suggests that WM microstructure in the DMN and mPFC-PAG pathway is associated with the degree to which ketamine reduces central sensitization. Thus, fixel metrics of WM structure may hold promise to predict ketamine NP treatment outcomes. PerspectiveWe used advanced fixel-based analyses of MRI diffusion-weighted imaging data to identify pretreatment WM microstructure associated with ketamine outcomes, including analgesia and markers of attenuated central sensitization. Exploring associations between brain structure and treatment outcomes could contribute to a personalized approach to treatment for individuals with NP.

Functional and structural connectivity success predictors of real-time fMRI neurofeedback targeting DLPFC: Contributions from central executive, salience, and default mode networks.

Real-time functional magnetic resonance imaging (rt-fMRI) neurofeedback (NF), a training method for the self-regulation of brain activity, has shown promising results as a neurorehabilitation tool, depending on the ability of the patient to succeed in neuromodulation. This study explores connectivity-based structural and functional success predictors in an NF n-back working memory paradigm targeting the dorsolateral prefrontal cortex (DLPFC). We established as the NF success metric the linear trend on the ability to modulate the target region during NF runs and performed a linear regression model considering structural and functional connectivity (intrinsic and seed-based) metrics. We found a positive correlation between NF success and the default mode network (DMN) intrinsic functional connectivity and a negative correlation with the DLPFC-precuneus connectivity during the 2-back condition, indicating that success is associated with larger uncoupling between DMN and the executive network. Regarding structural connectivity, the salience network emerges as the main contributor to success. Both functional and structural classification models showed good performance with 77% and 86% accuracy, respectively. Dynamic switching between DMN, salience network and central executive network seems to be the key for neurofeedback success, independently indicated by functional connectivity on the localizer run and structural connectivity data.

UAV‐derived greenness and within‐crown spatial patterning can detect ash dieback in individual trees

Abstract Ash Dieback (ADB) has been present in the UK since 2012 and is expected to kill up to 80% of UK ash trees. Detecting and quantifying the extent of ADB in individual tree crowns (ITCs), which is crucial to understanding resilience and resistance, currently relies on visual assessments which are impractical over large scales or at high frequency. The improved imaging capabilities and declining cost of consumer UAVs, together with new remote sensing methods such as structure from motion photogrammetry (SfM) offers potential to quantify the fine‐scale structural and spectral metrics of ITCs that are indicative of ADB, rapidly, and at low‐cost. We extract high‐resolution 3D RGB point clouds derived from SfM of canopy ash trees taken monthly throughout the growing season at Marden Park, Surrey, UK, a woodland impacted by ADB. We segment ITCs, extract green chromatic coordinate (gcc), and test the relationship with visual assessments of crown health. Next, we quantify spatial patterning of dieback within ITCs by testing the relationship between internal variation of gcc and path length, a measure of the distance from foliage to trunk, for small clusters of foliage. We find gcc correlates with visual assessments of crown health throughout the growing season, but the strongest relationships are in measurements taken after peak greenness, when the effects of ADB on foliage are likely to be most prevalent. We also find a negative relationship between gcc and path length in infected trees, indicating foliage loss is more severe at crown extremities. We demonstrate a new method for identifying ADB at scale using a consumer‐grade 3D RGB UAV system and suggest this approach could be adopted for widespread rapid monitoring. We recommend the optimum time of year for data acquisition, which we find to be an important factor for detecting ADB. Although here applied to ADB, this framework is applicable to a multitude of drivers of crown dieback, presenting a method for identifying spectral‐structural relationships which may be characteristic of disturbance type.

DEMIST: A Deep-Learning-Based Detection-Task-Specific Denoising Approach for Myocardial Perfusion SPECT.

There is an important need for methods to process myocardial perfusion imaging (MPI) single-photon emission computed tomography (SPECT) images acquired at lower-radiation dose and/or acquisition time such that the processed images improve observer performance on the clinical task of detecting perfusion defects compared to low-dose images. To address this need, we build upon concepts from model-observer theory and our understanding of the human visual system to propose a detection task-specific deep-learning-based approach for denoising MPI SPECT images (DEMIST). The approach, while performing denoising, is designed to preserve features that influence observer performance on detection tasks. We objectively evaluated DEMIST on the task of detecting perfusion defects using a retrospective study with anonymized clinical data in patients who underwent MPI studies across two scanners (N = 338). The evaluation was performed at low-dose levels of 6.25%, 12.5%, and 25% and using an anthropomorphic channelized Hotelling observer. Performance was quantified using area under the receiver operating characteristics curve (AUC). Images denoised with DEMIST yielded significantly higher AUC compared to corresponding low-dose images and images denoised with a commonly used task-agnostic deep learning-based denoising method. Similar results were observed with stratified analysis based on patient sex and defect type. Additionally, DEMIST improved visual fidelity of the low-dose images as quantified using root mean squared error and structural similarity index metric. A mathematical analysis revealed that DEMIST preserved features that assist in detection tasks while improving the noise properties, resulting in improved observer performance. The results provide strong evidence for further clinical evaluation of DEMIST to denoise low-count images in MPI SPECT.

Brain connectivity patterns derived from aging-related alterations in dynamic brain functional networks and their potential as features for brain age classification.

Objective.Recent studies have demonstrated that the analysis of brain functional networks (BFNs) is a powerful tool for exploring brain aging and age-related neurodegenerative diseases. However, investigating the mechanism of brain aging associated with dynamic BFN is still limited. The purpose of this study is to develop a novel scheme to explore brain aging patterns by constructing dynamic BFN using resting-state functional magnetic resonance imaging data.Approach.A dynamic sliding-windowed non-negative block-diagonal representation (dNBDR) method is proposed for constructing dynamic BFN, based on which a collection of dynamic BFN measures are suggested for examining age-related differences at the group level and used as features for brain age classification at the individual level.Results.The experimental results reveal that the dNBDR method is superior to the sliding time window with Pearson correlation method in terms of dynamic network structure quality. Additionally, significant alterations in dynamic BFN structures exist across the human lifespan. Specifically, average node flexibility and integration coefficient increase with age, while the recruitment coefficient shows a decreased trend. The proposed feature extraction scheme based on dynamic BFN achieved the highest accuracy of 78.7% in classifying three brain age groups.Significance. These findings suggest that dynamic BFN measures, dynamic community structure metrics in particular, play an important role in quantitatively assessing brain aging.

Quantifying the role of submesoscale Lagrangian transport features in the concentration of phytoplankton in a coastal system

Abstract Food resources in the ocean are often found in low densities, and need to be concentrated for efficient consumption. This is done in part by oceanographic features transporting and locally concentrating plankton, creating a highly patchy resource. Lagrangian approaches applied to ocean dynamics can identify these transport features, linking Lagrangian transport and spatial ecology. However, little is known about how Lagrangian approaches perform in ageostrophic coastal flows. This study evaluates two Lagrangian Coherent Structure metrics against the distribution of phytoplankton; Finite Time Lyapunov Exponents (FTLE) and Relative Particle Density (RPD). FTLE and RPD are applied to High Frequency Radar (HFR) observed surface currents within a biological hotspot, Palmer Deep Canyon Antarctica. FTLE and RPD identify different transport patterns, with RPD mapping single particle trajectories and FTLE tracking relative motion of paired particles. Simultaneous measurements of circulation and phytoplankton were gathered through the integration of vessel and autonomous glider surveys within the HFR footprint. Results show FTLE better defined phytoplankton patches compared to RPD, with the strongest associations occurring in stratified conditions, suggesting that phytoplankton congregate along FTLE ridges in coastal flows. This quantified relationship between circulation and phytoplankton patches emphasizes the role of transport in the maintenance of coastal food webs.

APOEε4 carriage associates with improved myocardial performance from adolescence to older age

BackgroundAlthough APOE ε4 allele carriage confers a risk for coronary artery disease, its persistence in humans might be explained by certain survival advantages (antagonistic pleiotropy).MethodsCombining data from ~ 37,000 persons from three older age British cohorts (1946 National Survey of Health and Development [NSHD], Southall and Brent Revised [SABRE], and UK Biobank) and one younger age cohort (Avon Longitudinal Study of Parents and Children [ALSPAC]), we explored whether APOE ε4 carriage associates with beneficial or unfavorable left ventricular (LV) structural and functional metrics by echocardiography and cardiovascular magnetic resonance (CMR).ResultsCompared to the non-APOE ε4 group, APOE ε4 carriers had similar cardiac phenotypes in terms of LV ejection fraction, E/e’, posterior wall and interventricular septal thickness, and LV mass. However, they had improved myocardial performance resulting in greater LV stroke volume generation per 1 mL of myocardium (higher myocardial contraction fraction). In NSHD (n = 1467) and SABRE (n = 1187), ε4 carriers had a 4% higher MCF (95% CI 1–7%, p = 0.016) using echocardiography. Using CMR data, in UK Biobank (n = 32,972), ε4 carriers had a 1% higher MCF 95% (CI 0–1%, p = 0.020) with a dose-response relationship based on the number of ε4 alleles. In addition, UK Biobank ε4 carriers also had more favorable radial and longitudinal strain rates compared to non APOE ε4 carriers. In ALSPAC (n = 1397), APOE ε4 carriers aged < 24 years had a 2% higher MCF (95% CI 0–5%, p = 0.059).ConclusionsBy triangulating results in four independent cohorts, across imaging modalities (echocardiography and CMR), and in ~ 37,000 individuals, our results point towards an association between ε4 carriage and improved cardiac performance in terms of LV MCF. This potentially favorable cardiac phenotype adds to the growing number of reported survival advantages attributed to the pleiotropic effects APOE ε4 carriage that might collectively explain its persistence in human populations.

Deep-learning-based super-resolution for accelerating chemical exchange saturation transfer MRI.

Chemical exchange saturation transfer (CEST) MRI is a molecular imaging tool that provides physiological information about tissues, making it an invaluable tool for disease diagnosis and guided treatment. Its clinical application requires the acquisition of high-resolution images capable of accurately identifying subtle regional changes in vivo, while simultaneously maintaining a high level of spectral resolution. However, the acquisition of such high-resolution images is time consuming, presenting a challenge for practical implementation in clinical settings. Among several techniques that have been explored to reduce the acquisition time in MRI, deep-learning-based super-resolution (DLSR) is a promising approach to address this problem due to its adaptability to any acquisition sequence and hardware. However, its translation to CEST MRI has been hindered by the lack of the large CEST datasets required for network development. Thus, we aim to develop a DLSR method, named DLSR-CEST, to reduce the acquisition time for CEST MRI by reconstructing high-resolution images from fast low-resolution acquisitions. This is achieved by first pretraining the DLSR-CEST on human brain T1w and T2w images to initialize the weights of the network and then training the network on very small human and mouse brain CEST datasetsto fine-tune the weights. Using the trained DLSR-CEST network, the reconstructed CEST source images exhibited improved spatial resolution in both peak signal-to-noise ratio and structural similarity index measure metrics at all downsampling factors (2-8). Moreover, amide CEST and relayed nuclear Overhauser effect maps extrapolated from the DLSR-CEST source images exhibited high spatial resolution and low normalized root mean square error, indicating a negligible loss in Z-spectrum information. Therefore, our DLSR-CEST demonstrated a robust reconstruction of high-resolution CEST source images from fast low-resolution acquisitions, thereby improving the spatial resolution and preserving most Z-spectrum information.

Quantitative Foveal Structural Metrics as Predictors of Visual Acuity in Human Albinism.

To assess the degree to which quantitative foveal structural measurements account for variation in best-corrected visual acuity (BCVA) in human albinism. BCVA was measured and spectral domain optical coherence tomography (SD-OCT) images were acquired for 74 individuals with albinism. Categorical foveal hypoplasia grades were assessed using the Leicester Grading System for Foveal Hypoplasia. Foveal anatomical specialization (foveal versus parafoveal value) was quantified for inner retinal layer (IRL) thickness, outer segment (OS) length, and outer nuclear layer (ONL) thickness. These metrics, participant sex, and age were used to build a multiple linear regression of BCVA. This combined linear model's predictive properties were compared to those of categorical foveal hypoplasia grading. The cohort included three participants with type 1a foveal hypoplasia, 23 participants with type 1b, 33 with type 2, ten with type 3, and five with type 4. BCVA ranged from 0.08 to 1.00 logMAR (mean ± SD: 0.53 ± 0.21). IRL ratio, OS ratio, and ONL ratio were measured in all participants and decreased with increasing severity of foveal hypoplasia. The best-fit combined linear model included all three quantitative metrics and participant age expressed as a binary variable (divided into 0-18years and 19years or older; adjusted R2 = 0.500). This model predicted BCVA more accurately than a categorical foveal hypoplasia model (adjusted R2 = 0.352). A quantitative model of foveal specialization accounts for more variance in BCVA in albinism than categorical foveal hypoplasia grading. Other factors, such as optical aberrations and eye movements, may account for the remaining unexplained variance.

Removing Heavy Metals: Cutting-Edge Strategies and Advancements in Biosorption Technology.

This article explores recent advancements and innovative strategies in biosorption technology, with a particular focus on the removal of heavy metals, such as Cu(II), Pb(II), Cr(III), Cr(VI), Zn(II), and Ni(II), and a metalloid, As(V), from various sources. Detailed information on biosorbents, including their composition, structure, and performance metrics in heavy metal sorption, is presented. Specific attention is given to the numerical values of the adsorption capacities for each metal, showcasing the efficacy of biosorbents in removing Cu (up to 96.4%), Pb (up to 95%), Cr (up to 99.9%), Zn (up to 99%), Ni (up to 93.8%), and As (up to 92.9%) from wastewater and industrial effluents. In addition, the issue of biosorbent deactivation and failure over time is highlighted as it is crucial for the successful implementation of adsorption in practical applications. Such phenomena as blockage by other cations or chemical decomposition are reported, and chemical, thermal, and microwave treatments are indicated as effective regeneration techniques. Ongoing research should focus on the development of more resilient biosorbent materials, optimizing regeneration techniques, and exploring innovative approaches to improve the long-term performance and sustainability of biosorption technologies. The analysis showed that biosorption emerges as a promising strategy for alleviating pollutants in wastewater and industrial effluents, offering a sustainable and environmentally friendly approach to addressing water pollution challenges.

Non-Destructive Estimation of Deciduous Forest Metrics: Comparisons between UAV-LiDAR, UAV-DAP, and Terrestrial LiDAR Leaf-Off Point Clouds Using Two QSMs

Timely acquisition of forest structure is crucial for understanding the dynamics of ecosystem functions. Despite the fact that the combination of different quantitative structure models (QSMs) and point cloud sources (ALS and DAP) has shown great potential to characterize tree structure, few studies have addressed their pros and cons in alpine temperate deciduous forests. In this study, different point clouds from UAV-mounted LiDAR and DAP under leaf-off conditions were first processed into individual tree point clouds, and then explicit 3D tree models of the forest were reconstructed using the TreeQSM and AdQSM methods. Structural metrics obtained from the two QSMs were evaluated based on terrestrial LiDAR (TLS)-based surveys. The results showed that ALS-based predictions of forest structure outperformed DAP-based predictions at both plot and tree levels. TreeQSM performed with comparable accuracy to AdQSM for estimating tree height, regardless of ALS (plot level: 0.93 vs. 0.94; tree level: 0.92 vs. 0.92) and DAP (plot level: 0.86 vs. 0.86; tree level: 0.89 vs. 0.90) point clouds. These results provide a robust and efficient workflow that takes advantage of UAV monitoring for estimating forest structural metrics and suggest the effectiveness of LiDAR in temperate deciduous forests.

Evaluating the Environmental Quality of Forest Remnants Using Landscape Metrics

Forest remnants are hotspots of biodiversity and play an important role in providing services such as regulating the climate, reducing surface runoff, helping erosion control, protecting and contributing to the balance of ecosystems, and other functions. Despite this, natural vegetation is fragmented and limited to a few remnants, which are gradually suffering from anthropogenic pressures. Assessing the environmental quality of these remnants is therefore vital to understanding their current condition and to provide support for their conservation. This study aims to assess the environmental quality of forest remnants in six water basins in the municipality of Campinas/SP, Brazil. Forest remnants were mapped, and their environmental quality was assessed by applying an analytic hierarchy process (AHP), considering a set of structural landscape metrics previously selected from the literature. Of the 2319 forest remnants evaluated, 4.5% and 30%, respectively, registered high and low environmental quality. The Atibaia and Jaguari basins recorded the highest number of environmentally fragile remnants due to their small size and being predominantly elongated, and to the high erodibility of the soil. In the Anhumas, Capivari, Capivari-Mirim, and Quilombo basins, medium-sized forest remnants predominate. There is a greater distance between them, with a high intensity of land use/land cover in their surroundings, related to the prevalence of urbanized areas. Specific management actions should be taken in each of these basins.

Design and methodology for a proof of mechanism study of individualized neuronavigated continuous Theta burst stimulation for auditory processing in adolescents with autism spectrum disorder.

It has been suggested that aberrant excitation/inhibition (E/I) balance and dysfunctional structure and function of relevant brain networks may underlie the symptoms of autism spectrum disorder (ASD). However, the nomological network linking these constructs to quantifiable measures and mechanistically relating these constructs to behavioral symptoms of ASD is lacking. Herein we describe a within-subject, controlled, proof-of-mechanism study investigating the pathophysiology of auditory/language processing in adolescents with ASD. We utilize neurophysiological and neuroimaging techniques including magnetic resonance spectroscopy (MRS), diffusion-weighted imaging (DWI), functional magnetic resonance imaging (fMRI), and magnetoencephalography (MEG) metrics of language network structure and function. Additionally, we apply a single, individually targeted session of continuous theta burst stimulation (cTBS) as an experimental probe of the impact of perturbation of the system on these neurophysiological and neuroimaging outcomes. MRS, fMRI, and MEG measures are evaluated at baseline and immediately prior to and following cTBS over the posterior superior temporal cortex (pSTC), a region involved in auditory and language processing deficits in ASD. Also, behavioral measures of ASD and language processing and DWI measures of auditory/language network structures are obtained at baseline to characterize the relationship between the neuroimaging and neurophysiological measures and baseline symptom presentation. We hypothesize that local gamma-aminobutyric acid (GABA) and glutamate concentrations (measured with MRS), and structural and functional activity and network connectivity (measured with DWI and fMRI), will significantly predict MEG indices of auditory/language processing and behavioral deficits in ASD. Furthermore, a single session of cTBS over left pSTC is hypothesized to lead to significant, acute changes in local glutamate and GABA concentration, functional activity and network connectivity, and MEG indices of auditory/language processing. We have completed the pilot phase of the study (n=20 Healthy Volunteer adults) and have begun enrollment for the main phase with adolescents with ASD (n=86; age 14-17). If successful, this study will establish a nomological network linking local E/I balance measures to functional and structural connectivity within relevant brain networks, ultimately connecting them to ASD symptoms. Furthermore, this study will inform future therapeutic trials using cTBS to treat the symptoms of ASD.

Deep Q-Learning-Based Molecular Graph Generation for Chemical Structure Prediction From Infrared Spectra

In this paper, we present a novel approach to predicting chemical structures from their infrared (IR) spectra using deep Q-learning. IR spectra measurements are widely used in chemical analysis because they provide information on the types and characteristics of chemical bonds present within compounds. However, there are currently no algorithms to predict the entire chemical structure of a broad range of compounds relying solely on IR spectra, unless there is an exact or closely matched spectrum in an existing reference spectra library. To address this, we apply double deep Q-learning for automated prediction of the entire chemical structures of organic compounds based on IR spectra. Our method builds predicted structures by starting from a single carbon atom and subsequently adding an atom and bond step-by-step by ranking the rewards of each possible addition based on Q-values. We devised new structural similarity metrics, atom bond count and substructure count metrics to achieve our goal. Compared to the commonly used structural similarity score, the Jaccard index of extended-connectivity fingerprints, the devised metrics exhibit more suitable properties for Q-learning. The deep Q-model, which uses the combination of our two proposed metrics, gives the overall best performance and can generate structures similar to the actual structures in terms of their structural features and molecular weight in most tested cases.

Deep Learning for Daily 2‐m Temperature Downscaling

AbstractThis study proposes a novel method, which is a U‐shaped convolutional neural network that combines non‐local attention mechanisms, Res2net residual modules, and terrain information (UNR‐Net). The original U‐Net method and the linear regression (LR) method are conducted as benchmarks. Generally, the UNR‐Net has demonstrated promise in performing a 10× downscaling for daily 2‐m temperature over North China with lead times of 1–7 days and shows superiority to the U‐Net and LR methods. To be specific, U‐Net and UNR‐Net demonstrate higher Nash‐Sutcliffe Efficiency coefficient values compared to LR by 0.052 and 0.077, respectively. The corresponding improvements in pattern correlation coefficient are 0.013 and 0.016, while the root mean square error values are higher by 0.22 and 0.338, respectively. Additionally, the structural similarity index metric is higher by 0.033 and lower by 0.015. Furthermore, regions with significant errors are primarily distributed in complex terrain areas such as the Taihang Mountains, where UNR‐Net exhibits noticeable improvements. In addition, the 12 components‐based error decomposition method is proposed to analyze the error source of different models. Generally, the smallest errors are observed during the summer season and the sequence error component is proven to be the main source error of 2‐m temperature forecasts. Furthermore, UNR‐Net consistently demonstrates the lowest errors among all 12 error components. Therefore, combining the numerical weather prediction model and deep learning method is very promising in downscaling temperature forecasts and can be applied to routine forecasting of other atmospheric variables in the future.

Individual variability in functional connectivity of human auditory cortex.

Individual variability in functional connectivity underlies individual differences in cognition and behaviors, yet its association with functional specialization in the auditory cortex remains elusive. Using resting-state functional magnetic resonance imaging data from the Human Connectome Project, this study was designed to investigate the spatial distribution of auditory cortex individual variability in its whole-brain functional network architecture. An inherent hierarchical axis of the variability was discerned, which radiates from the medial to lateral orientation, with the left auditory cortex demonstrating more pronounced variations than the right. This variability exhibited a significant correlation with the variations in structural and functional metrics in the auditory cortex. Four auditory cortex subregions, which were identified from a clustering analysis based on this variability, exhibited unique connectional fingerprints and cognitive maps, with certain subregions showing specificity to speech perception functional activation. Moreover, the lateralization of the connectional fingerprint exhibited a U-shaped trajectory across the subregions. These findings emphasize the role of individual variability in functional connectivity in understanding cortical functional organization, as well as in revealing its association with functional specialization from the activation, connectome, and cognition perspectives.

Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO)

BackgroundIt is not unusual to see some parts of tissues are excluded in the field of view of CT simulation images. A typical mitigation is to avoid beams entering the missing body parts at the cost of sub-optimal planning.MethodsThis study is to solve the problem by developing 3 methods, (1) deep learning (DL) mechanism for missing tissue generation, (2) using patient body outline (PBO) based on surface imaging, and (3) hybrid method combining DL and PBO. The DL model was built upon a Globally and Locally Consistent Image Completion to learn features by Convolutional Neural Networks-based inpainting, based on Generative Adversarial Network. The database used comprised 10,005 CT training slices of 322 lung cancer patients and 166 CT evaluation test slices of 15 patients. CT images were from the publicly available database of the Cancer Imaging Archive. Since existing data were used PBOs were acquired from the CT images. For evaluation, Structural Similarity Index Metric (SSIM), Root Mean Square Error (RMSE) and Peak signal-to-noise ratio (PSNR) were evaluated. For dosimetric validation, dynamic conformal arc plans were made with the ground truth images and images generated by the proposed method. Gamma analysis was conducted at relatively strict criteria of 1%/1 mm (dose difference/distance to agreement) and 2%/2 mm under three dose thresholds of 1%, 10% and 50% of the maximum dose in the plans made on the ground truth image sets.ResultsThe average SSIM in generation part only was 0.06 at epoch 100 but reached 0.86 at epoch 1500. Accordingly, the average SSIM in the whole image also improved from 0.86 to 0.97. At epoch 1500, the average values of RMSE and PSNR in the whole image were 7.4 and 30.9, respectively. Gamma analysis showed excellent agreement with the hybrid method (equal to or higher than 96.6% of the mean of pass rates for all scenarios).ConclusionsIt was first demonstrated that missing tissues in simulation imaging could be generated with high similarity, and dosimetric limitation could be overcome. The benefit of this study can be significantly enlarged when MR-only simulation is considered.