Coverage Metrics Research Articles

Triggering daily online adaptive radiotherapy in the pelvis: Dosimetric effects and procedural implications of trigger parameter-value selection.

Online adaptive radiotherapy (ART) can address dosimetric consequences of variations in anatomy by creating a new plan during treatment. However, ART is time- and labor-intensive and should be implemented in a resource-conscious way. Adaptive triggers composed of parameter-value pairs may direct the judicious use of online ART. This work analyzed our clinical experience using CBCT-based daily online ART to demonstrate how a conceptual framework based on adaptive triggers affects the dosimetric and procedural impact of ART. Sixteen patients across several pelvic sites were treated with CBCT-based daily online ART. Differences in standardized dose metrics were compared between the original plan, the original plan recalculated on the daily anatomy, and an adaptive plan. For each metric, trigger values were analyzed in terms of the proportion of treatments adapted and the distribution of metric values. Target coverage metrics were compromised due to anatomic variation with the average change per treatment ranging from -0.90 to -0.05 Gy, -0.47 to -0.02 Gy, -0.31 to -0.01 Gy, and -12.45% to -2.65% for PTV D99%, PTV D95%, CTV D99%, and CTV V100%, respectively. These were improved using the adaptive plan (-0.03 to 0.01 Gy, -0.02 to 0.00 Gy, -0.03 to 0.00 Gy, and -4.70% to 0.00%, respectively). Increasingly strict triggers resulted in a non-linear increase in the proportion of treatments adapted and improved the distribution of metric values with diminishing returns. Some organ-at-risk (OAR) metrics were compromised by anatomic variation and improved using the adaptive plan, but changes in most OAR metrics were randomly distributed. Daily online ART improved target coverage across multiple pelvic treatment sites and techniques. These effects were larger than those for OAR metrics, suggesting that maintaining target coverage was our primary benefit of CBCT-based daily online ART. Analyses like these can determine online ART triggers from a cost-benefit perspective.

Vehicular Crowdsensing with High-Mileage Vehicles: Investigating Spatiotemporal Coverage Dynamics in Historical Cities with Complex Urban Road Networks

Background. Vehicular crowdsensing (VCS) can be a cost-effective solution to gather data in urban environments, leveraging the onboard sensors of modern vehicles moving around the city. Many experimental studies have proven that high-mileage vehicles, such as taxis, can be effectively used for VCS. However, these studies have been mostly carried out in cities with regular, grid-based, road networks. Conversely, little work has been conducted to assess the suitability of VCS in cities with more complex urban road networks, such as historical ones. Goal. As a step towards filling this gap, the present study investigates the feasibility of using different-sized fleets of taxis to crowdsense information in the urban areas of the historical cities of Porto (Portugal) and Rome (Italy), whose road networks evolved over the centuries and feature a complex topology. Data and Methodology. This work leverages massive real-world datasets of taxi trajectories collected over three contiguous weeks in the cities of Porto and Rome to estimate the spatiotemporal coverage achievable by different-sized fleets of taxis if they were used for VCS. Indeed, using these trajectories, several simulations were conducted, considering four sizes of taxi fleets, ranging from 50 to 400 vehicles, for both cities. The achievable spatiotemporal road network coverage metrics were computed at a fine-grained scale of single road segments. Results. Results show that the achievable coverage in both historical cities exhibits very similar trends, with as few as 50 vehicles being capable of visiting a relevant part of the road network at least once in the considered time frame. As expected, increasing the number of involved vehicles improves spatial and temporal coverage. Still, time gaps between subsequent visits can be possibly inadequate for some VCS use cases. As a consequence, recruiting more vehicles and/or devising specialized routing/incentivization mechanisms might be necessary to achieve more comprehensive coverage of the urban road network.

Black-Box Testing of Deep Neural Networks through Test Case Diversity

Deep Neural Networks (DNNs) have been extensively used in many areas including image processing, medical diagnostics, and autonomous driving. However, DNNs can exhibit erroneous behaviours that may lead to critical errors, especially when used in safety-critical systems. Inspired by testing techniques for traditional software systems, researchers have proposed neuron coverage criteria, as an analogy to source code coverage, to guide the testing of DNN models. Despite very active research on DNN coverage, several recent studies have questioned the usefulness of such criteria in guiding DNN testing. Further, from a practical standpoint, these criteria are white-box as they require access to the internals or training data of DNN models, which is in many contexts not feasible or convenient. In this paper, we investigate black-box input diversity metrics as an alternative to white-box coverage criteria. To this end, we first select and adapt three diversity metrics and study, in a controlled manner, their capacity to measure actual diversity in input sets. We then analyse their statistical association with fault detection using four datasets and five DNN models. We further compare diversity with state-of-the-art white-box coverage criteria. Our experiments show that relying on the diversity of image features embedded in test input sets is a more reliable indicator than coverage criteria to effectively guide the testing of DNNs. Indeed, we found that one of our selected black-box diversity metrics far outperforms existing coverage criteria in terms of fault-revealing capability and computational time. Results also confirm the suspicions that state-of-the-art coverage metrics are not adequate to guide the construction of test input sets to detect as many faults as possible with natural inputs.

An improved differential evolution algorithm for quantifying fraudulent transactions

Identification of fraudulent credit card transactions is a complex problem mainly due to the following factors: 1) The relative behavior of customers and fraudsters may alter over time. 2) The ratio of legitimate to fraudulent transactions is highly imbalanced, and 3) Investigators examine a small segment of transactions in a reasonable time frame. Researchers have proposed various algorithms to identify potential fraud in a new incoming transaction. However, these approaches require significant human investigator effort and are sometimes misleading. To address this issue, this paper proposes an improved multiobjective differential evolution (DE) algorithm to estimate the distribution of fraudulent transactions in a set of new incoming transactions, referred to as quantifying fraudulent transactions. Our paper has three major novelties. First, we present the problem formulation of cost-based feature selection with maximum quantification ability. Second, we improve the DE by applying effective trial vector generation algorithms to the random control parameter settings to exploit the advantage of individual DE variants. Third, we develop the maximum-relevancy-minimum-redundancy-based Pareto refining operator to enhance the self-learning ability of individuals in Pareto solutions. We compare our approach against four other modifications of DE and five state-of-the-art evolutionary algorithms on real-time credit datasets in streaming and non-streaming frameworks using hyper-volume, two-set coverage, and spread performance metrics.

Evaluating Surprise Adequacy for Deep Learning System Testing

The rapid adoption of Deep Learning (DL) systems in safety critical domains such as medical imaging and autonomous driving urgently calls for ways to test their correctness and robustness. Borrowing from the concept of test adequacy in traditional software testing, existing work on testing of DL systems initially investigated DL systems from structural point of view, leading to a number of coverage metrics. Our lack of understanding of the internal mechanism of Deep Neural Networks (DNNs), however, means that coverage metrics defined on the Boolean dichotomy of coverage are hard to intuitively interpret and understand. We propose the degree of out-of-distribution-ness of a given input as its adequacy for testing: the more surprising a given input is to the DNN under test, the more likely the system will show unexpected behavior for the input. We develop the concept of surprise into a test adequacy criterion, called Surprise Adequacy (SA). Intuitively, SA measures the difference in the behavior of the DNN for the given input and its behavior for the training data. We posit that a good test input should be sufficiently, but not overtly, surprising compared to the training dataset. This article evaluates SA using a range of DL systems from simple image classifiers to autonomous driving car platforms, as well as both small and large data benchmarks ranging from MNIST to ImageNet. The results show that the SA value of an input can be a reliable predictor of the correctness of the mode behavior. We also show that SA can be used to detect adversarial examples, and also be efficiently computed against large training dataset such as ImageNet using sampling.

RNNCon: Contribution Coverage Testing for Stacked Recurrent Neural Networks

Recurrent Neural Networks (RNNs) are applied in safety-critical fields such as autonomous driving, aircraft collision detection, and smart credit. They are highly susceptible to input perturbations, but little research on RNN-oriented testing techniques has been conducted, leaving a threat to a large number of sequential application domains. To address these gaps, improve the test adequacy of RNNs, find more defects, and improve the performance of RNNs models and their robustness to input perturbations. We aim to propose a test coverage metric for the underlying structure of RNNs, which is used to guide the generation of test inputs to test RNNs. Although coverage metrics have been proposed for RNNs, such as the hidden state coverage in RNN-Test, they ignore the fact that the underlying structure of RNNs is still a fully connected neural network but with an additional "delayer" that records the network state at the time of data input. We use the contributions, i.e., the combination of the outputs of neurons and the weights they emit, as the minimum computational unit of RNNs to explore the finer-grained logical structure inside the recurrent cells. Compared to existing coverage metrics, our research covers the decision mechanism of RNNs in more detail and is more likely to generate more adversarial samples and discover more flaws in the model. In this paper, we redefine the contribution coverage metric applicable to Stacked LSTMs and Stacked GRUs by considering the joint effect of neurons and weights in the underlying structure of the neural network. We propose a new coverage metric, RNNCon, which can be used to guide the generation of adversarial test inputs. And we design and implement a test framework prototype RNNCon-Test. 2 datasets, 4 LSTM models, and 4 GRU models are used to verify the effectiveness of RNNCon-Test. Compared to the current state-of-the-art study RNN-Test, RNNCon can cover a deeper decision logic of RNNs. RNNCon-Test is not only effective in identifying defects in Deep Learning (DL) systems but also in improving the performance of the model if the adversarial inputs generated by RNNCon-Test are filtered and added to the training set to retrain the model. In the case where the accuracy of the model is already high, RNNCon-Test is still able to improve the accuracy of the model by up to 0.45%.

Revisiting deep neural network test coverage from the test effectiveness perspective

AbstractMany test coverage metrics have been proposed to measure the deep neural network (DNN) testing effectiveness, including structural coverage and nonstructural coverage. These test coverage metrics are proposed based on the fundamental assumption: They are correlated with test effectiveness. However, the fundamental assumption is still not validated sufficiently and reasonably, which brings question on the usefulness of DNN test coverage. This paper conducted a revisiting study on the existing DNN test coverage from the test effectiveness perspective, to effectively validate the fundamental assumption. Here, we carefully considered the diversity of subjects, three test effectiveness criteria, and both typical and state‐of‐the‐art test coverage metrics. Different from all the existing studies that deliver negative conclusions on the usefulness of existing DNN test coverage, we identified some positive conclusions on their usefulness from the test effectiveness perspective. In particular, we found the complementary relationship between structural and nonstructural coverage and identified the practical usage scenarios and promising research directions for these existing test coverage metrics.

Lessons learned from EV charging infrastructure in mega cities: A data-driven approach

E-mobility has witnessed a major evolution in the last couple of years due to climate action concerns. Cities that have employed e-mobility across the globe can be classified into two groups: e-mobility forerunners and cities at the early market stages of e-mobility. Electric Vehicle Charging Infrastructure (EVCI) is one of the main pillars of e-mobility rollout. Thus, it is important to investigate the lessons learned from EVCI installation across those forerunner cities around the world. This research addresses a data-driven multi-dimensional serviceability analysis of EVCI in 25 cities across the globe, to unveil many of those complex patterns associated with EVCI planning by discussing: EVCI service coverage, radius, and standard evaluation metrics. City comparisons, market patterns, and worldwide trends have been observed and geo-spatially analyzed including: 1) EVCI coverage vs EVs sales, 2) density distribution of charging pools/1km2 covered cell, 3) the analogy between demand-driven networks and density distribution of EVCI locations, 4) the structure of EVCI covered areas in relation to cities’ urban fabric, 5) charging pools/million population in relation to the type of parking citizens have access to and drivers’ charging preferences, 6) the effect of road network topology on EVCI service radius, 7) the effect of prevalent degree of electrification and traffic conditions on EVCI service coverage and radius, and 8) the effect of ambient temperature on EVCI service radius. Other factors related to e-mobility public policies (such as: EVCI incentives) have resulted in – along with cities’ characteristics – different levels of success across the studied cities. The provided analysis shall help in: 1) providing e-mobility early adopters’ cities with a high-level guidance on the best practices for EVCI planning, 2) spreading the praiseworthy EVCI installation practices among e-mobility forerunners to further optimize EVCI deployment.

IMF 2 O 2 : A Fully Connected Sensor Deployment Algorithm for Underwater Sensor Networks

To address the problems of node deployment schemes in existing underwater sensor networks that lack consideration of network connectivity and high deployment costs, this article constructs an optimization model that maximizes network coverage and minimizes deployment costs while ensuring full connectivity. For the NP-hard property of this optimization model, an improved moth flame optimization node deployment algorithm based on fuzzy operators (IMF 2 O 2 ) is proposed. First, comprehensively considering the two performance metrics of network coverage and network connectivity, a multi-objective selection mechanism based on fuzzy operators is proposed to improve network coverage while ensuring full connectivity. Second, a fixed number of nodes are used to monitor the target event points, transforming the node deployment of sensors into an optimal problem and proposing an improved moth flame optimization algorithm to solve this problem. Finally, the two metrics of coverage and deployment cost are measured and the fuzzy operator is used to select the optimal number of nodes to be deployed. Numerical results showed that the proposed algorithm improved network coverage rate by 10%, 22%, and 25%, and improved network connectivity rate by 12%, 20%, and 8% as compared to PSSD, RAWS, and VODA, respectively, while ensuring full connectivity.

The effect of integrating knowledge-based planning with multicriteria optimization in treatment planning for prostate SBRT.

Knowledge-based planning (KBP) and multicriteria optimization (MCO) are two powerful tools to assist treatment planners in achieving optimal target coverage and organ-at-risk (OAR) sparing. The purpose of this work is to investigate if integrating MCO with conventional KBP can further improve treatment plan quality for prostate cancer stereotactic body radiation therapy (SBRT). A two-phase study was designed to investigate the impact of MCO and KBP in prostate SBRT treatment planning. The first phase involved the creation of a KBP model based on thirty clinical SBRT plans, generated by manual optimization (KBP_M). A ten-patient validation cohort was used to compare manual, MCO, and KBP_M optimization techniques. The next phase involved replanning the original model cohort with additional tradeoff optimization via MCO to create a second model, KBP_MCO. Plans were then generated using linear integration (KBP_M+MCO), non-linear integration (KBP_MCO), and a combination of integration methods (KBP_MCO+MCO). All plans were analyzed for planning target volume (PTV) coverage, OAR constraints, and plan quality metrics. Comparisons were generated to evaluate plan and model quality. Phase 1 highlighted the necessity of KBP and MCO in treatment planning, as both optimization methods improved plan quality metrics (Conformity and Heterogeneity Indices) and reduced mean rectal dose by 2Gy, as compared to manual planning. Integrating MCO with KBP did not further improve plan quality, as little significance was seen over KBP or MCO alone. Principal component score (PCS) fitting showed KBP_MCO improved bladder and rectum estimated and modeled dose correlation by 5% and 22%, respectively; however, model improvements did not significantly impact plan quality. KBP and MCO have shown to reduce OAR dose while maintaining desired PTV coverage in this study. Further integration of KBP and MCO did not show marked improvements in treatment plan quality while requiring increased time in model generation and optimization time.

Effective Coverage in Health Systems: Evolution of a Concept.

The manner in which high-impact, life-saving health interventions reach populations in need is a critical dimension of health system performance. Intervention coverage has been a standard metric for such performance. To better understand and address the decay of intervention effectiveness in real-world health systems, the more complex measure of "effective coverage" is required, which includes the health gain the health system could potentially deliver. We have carried out a narrative review to trace the origins, timeline, and evolution of the concept of effective coverage metrics to illuminate potential improvements in coherence, terminology, application, and visualizations, based on which a combination of approaches appears to have the most influence on policy and practice. We found that the World Health Organization first proposed the concept over 45 years ago. It became increasingly popular with the further development of theoretical underpinnings, and after the introduction of quantification and visualization tools. The approach has been applied in low- and middle-income countries, mainly for HIV/AIDS, TB, malaria, child health interventions, and more recently for non-communicable diseases, particularly diabetes and hypertension. Nevertheless, despite decades of application of effective coverage concepts, there is considerable variability in the terminology used and the choices of effectiveness decay steps included in the measures. Results frequently illustrate a profound loss of service effectiveness due to health system factors. However, policy and practice rarely address these factors, and instead favour narrowly targeted technical interventions.

Dosimetric Impact of Intrafraction Prostate Motion and Interfraction Anatomical Changes in Dose-Escalated Linac-Based SBRT

The dosimetric impact of intrafraction prostate motion and interfraction anatomical changes and the effect of beam gating and motion correction were investigated in dose-escalated linac-based SBRT. Fifty-six gated fractions were delivered using a novel electromagnetic tracking device with a 2 mm threshold. Real-time prostate motion data were incorporated into the patient's original plan with an isocenter shift method. Delivered dose distributions were obtained by recalculating these motion-encoded plans on deformed CTs reflecting the patient's CBCT daily anatomy. Non-gated treatments were simulated using the prostate motion data assuming that no treatment interruptions have occurred. The mean relative dose differences between delivered and planned treatments were -3.0% [-18.5-2.8] for CTV D99% and -2.6% [-17.8-1.0] for PTV D95%. The median cumulative CTV coverage with 93% of the prescribed dose was satisfactory. Urethra sparing was slightly degraded, with the maximum dose increased by only 1.0% on average, and a mean reduction in the rectum and bladder doses was seen in almost all dose metrics. Intrafraction prostate motion marginally contributed in gated treatments, while in non-gated treatments, further deteriorations in the minimum target coverage and bladder dose metrics would have occurred on average. The implemented motion management strategy and the strict patient preparation regimen, along with other treatment optimization strategies, ensured no significant degradations of dose metrics in delivered treatments.

Evaluation of metaheuristic optimization algorithms for optimal allocation of surface water and groundwater resources for crop production

Extensive variability in current climatic conditions necessitates the need for optimal planning of water resources to manage socio-economic and environmental requirements efficiently. The optimal allocation of surface water and groundwater is essential to maximize crop net return due to uncertainty in seasonal rainfall, groundwater, and surface water availability in each region. This study demonstrated a multi-objective model to maximize the crop net return and efficient management of water resources. The multi-objective model comprised three objective functions maximizing the crop net return, minimizing the water deficit, and maximizing the aquifer recharge. The model’s practicability was analyzed through the case study of the Pennar-Palar-Cauvery link canal command in India. Three meta-heuristic approaches, particle swarm optimization (PSO), genetic algorithm (GA), and marine predators algorithm (MPA), were employed to solve the presented model. And their performance was evaluated using hypervolume and coverage metrics, indicating MPA’s superiority in obtaining well-distributed Pareto-optimal solutions. Thus, decision-makers can choose the best feasible solution based on current resource availability and preferences. The model was executed considering different cropping area deviations (5–25%) in the existing cropping pattern and allowance of groundwater mining from 0% to 70%. The obtained cropping pattern utilizing MPA at 25% cropping deviation achieved an increased net return of 1327.05 million INR.

Evaluation of the Quality and Comparison of Dosimetric Parameters of Plans for Craniospinal Irradiation Using VMAT Method at Varian TrueBeam and Varian Halcyon Accelerators

Purpose: To carry out a comparative analysis of the dosimetric characteristics of plans for craniospinal irradiation (CSI) performed by the VMAT technique on Varian TrueBeam and Halcyon electron accelerators.
 Material and methods: Comparison of dose distributions was carried out for a group of 5 patients with tumors of the central nervous system. Contouring and planning were in Eclipse version 15.6. The following dose characteristics were calculated and evaluated: homogeneity index (HI), conformity index (CI), target coverage (CO) and constraints (lenses, esophagus, lungs, heart, liver, bowel bag and kidneys). Patient-Specific QA was performed to verify the consistency of the dose distribution calculated in the planning system and obtained at the accelerators.
 Results: For all CSI plans the target coverage metric was D98>95 % and constraints for critical organs were obtained. Homogeneity index was HI<=0.12 for two accelerators. The mean value of the CI conformity index was 1.09 for the TrueBeam accelerator, and CI=1.12 for the Halcyon. Gamma analysis showed results within tolerance both plans at TrueBeam and Halcyon. Conclusions have been made about the advantages and disadvantages of CSI on TrueBeam and Halcyon electron accelerators.
 Conclusion: It is possible to treat patients with the CSI method on the Halcyon accelerator using the VMAT method with the same quality as on the TrueBeam accelerator.

For Hepatocellular Carcinoma Treated with Yttrium-90 Microspheres, Dose Volumetrics on Post-Treatment Bremsstrahlung SPECT/CT Predict Clinical Outcomes.

In transarterial radioembolization (TARE) of hepatocellular carcinoma (HCC) with Yttrium-90 (Y-90) microspheres, recent studies correlate dosimetry from bremsstrahlung single photon emission tomography (SPECT/CT) with treatment outcomes; however, these studies focus on measures of central tendency rather than volumetric coverage metrics commonly used in radiation oncology. We hypothesized that three-dimensional (3D) isodose coverage of gross tumor volume (GTV) is the driving factor in HCC treatment response to TARE and is best assessed using advanced dosimetry techniques applied to nuclear imaging of actual Y-90 biodistribution. We reviewed 51 lobar TARE Y-90 treatments of 43 HCC patients. Dose prescriptions were 120 Gy for TheraSpheres and 85 Gy for SIR-Spheres. All patients underwent post-TARE Y-90 bremsstrahlung SPECT/CT imaging. Commercial software was used to contour gross tumor volume (GTV) and liver on post-TARE SPECT/CT. Y-90 dose distributions were calculated using the Local Deposition Model based on post-TARE SPECT/CT activity maps. Median gross tumor volume (GTV) dose; GTV receiving less than 100 Gy, 70 Gy and 50 Gy; minimum dose covering the hottest 70%, 95%, and 98% of the GTV (D70, D95, D98); mean dose to nontumorous liver, and disease burden (GTV/liver volume) were obtained. Clinical outcomes were collected for all patients by chart and imaging review. HCC treatment response was assessed according to the modified response criteria in solid tumors (mRECIST) guidelines. Kaplan-Meier (KM) survival estimates and multivariate regression analyses (MVA) were performed using STATA. Median survival was 22.5 months for patients achieving objective response (OR) in targeted lesions (complete response (CR) or partial response (PR) per mRECIST) vs. 7.6 months for non-responders (NR, stable disease or disease progression per mRECIST). On MVA, the volume of underdosed tumor (GTV receiving less than 100 Gy) was the only significant dosimetric predictor for CR (p = 0.0004) and overall survival (OS, p = 0.003). All targets with less than CR (n = 39) had more than 20 cc of underdosed tumor. D70 (p = 0.038) correlated with OR, with mean D70 of 95 Gy for responders and 60 Gy for non-responders (p = 0.042). On MVA, mean dose to nontumorous liver trended toward significant association with grade 3+ toxicity (p = 0.09) and correlated with delivered activity (p < 0.001) and burden of disease (p = 0.05). Dosimetric models supplied area under the curve estimates of > 0.80 predicting CR, OR, and ≥grade 3 acute toxicity. Dosimetric parameters derived from the retrospective analysis of post-TARE Y-90 bremsstrahlung SPECT/CT after lobar treatment of HCC suggest that volumetric coverage of GTV, not a high mean or median dose, is the driving factor in treatment response and that this is best assessed through the analysis of actual Y-90 biodistribution.

Preliminary dosimetric comparison between fixed and rotating source stereotactic radiosurgery systems.

The Akesis Galaxy RTi (AK) is a novel rotational 60 Co-based cranial stereotactic radiosurgery (SRS) system. While similar systems have been compared against the fixed-source Leksell Gamma Knife (GK) system using stylized phantoms, dosimetric plan quality with realistic anatomy has yet to be characterized for this or any other rotating system versus GK. This study aims to benchmark AK dosimetric performance against GK by retrospectively replanning previously-treated GK patients at our institution. Thirteen patients, previously treated on a GK Icon, were re-planned on the AK treatment planning system using the same prescription doses and isodoses as the original GK plans. The cohort includes patients treated for brain metastases, schwannomas, pituitary adenomas, trigeminal neuralgias, and arteriovenous malformations. Plans are evaluated with target coverage metrics (Dmin , Dmean , D95% , V150% ) and dose conformality indices: Radiation Therapy Oncology Group conformity index (CI), selectivity, Paddick CI (PCI), gradient index (GI). AK plans use fewer shots and larger collimation compared to GK plans, resulting in statistically significant reductions in treatment time (p=0.047) by as much as 88.4 minutes while maintaining comparable target V100% . For most metastatic cases, GK produces higher Dmin (16.0-25.9 vs. 12.5-24.3Gy, p=0.008) while AK produces higher V150% (0.03-14.92 vs. 0.02-11.59 cc, p=0.028). For non-metastatic cases, GK provides superior CI (p=0.025) and GI (p=0.044). No statistically significant differences were found in the remaining metrics. This cohort demonstrates that the AK system is able to achieve largely comparable dosimetric results to GK, typically with shorter treatment times. Further investigation with a larger cohort is underway.

Image analysis reveals environmental influences on the seagrass-epiphyte dynamic relationship for Thalassia testudinum in the northwestern Gulf of Mexico

Spatiotemporal patterns in seagrass-epiphyte dynamics for Thalassia testudinum in the northwestern Gulf of Mexico were evaluated through biomass measurements and scanned-image based metrics to investigate the potentially harmful impact of excessive epiphyte accumulations on seagrass condition. Image analysis with Spectral Angle Mapper algorithms distinguished epiphyte and uncovered seagrass leaf pixels to generate a normalized metric of leaf area coverage (epiphyte pixels/total leaf pixels). Imaging metrics were compared to biomass-based metrics seasonally, among three locations with different environmental conditions (depth, salinity, temperature and nutrient levels inferred from sediment porewater measurements) near Redfish Bay, Texas, USA. Image analysis, in conjunction with biomass measures, provides enhanced insight into the seagrass-epiphyte dynamic relationship and how it varies with environmental conditions. Compared with the biomass and morphological measures, image analysis may be more informative as an indicator of environmental changes. Variation in linear regressions of epiphyte biomass vs. epiphyte area (pixels) suggested changes in the thickness and/or density of accumulated epiphytes across environmental contexts and seasons. Two different epiphyte colonization patterns were presented based on the correlation between the normalized metrics of epiphyte load and epiphyte leaf coverage. The epiphyte load was highest at low temperatures and locations with elevated DIN:P ratio in sediment porewater. Conversely, the mean leaf coverage by epiphytes stayed relatively constant (± 10%) across seasons but differed by location (25% ~55% in this case), suggesting that leaf growth in this study is regulated to maintain the proportion of uncolonized leaf surface and that epiphyte coverage plays a role in its regulation.

Spatial and Temporal Sampling Properties of a Large GNSS-R Satellite Constellation

Using large constellations of smallsats, mission designers can improve sampling density and coverage. We develop performance metrics that characterize key sampling properties for applications in numerical weather prediction and optimize orbit design parameters of the constellation with respect to those metrics. Orbits are defined by a set of Keplerian elements, and the relationship between those elements and the spatial and temporal coverage metrics are examined in order to maximize global and zonal (latitude-dependent) coverage. Additional optimization is performed by dividing a constellation into multiple orbit planes. An iterative method can be applied to this design process to compare the performance of current and previous designs. The main objective of this work is the design of optimized configurations of satellites in low Earth orbiting constellations to maximize the spatial and temporal sampling and coverage provided by its sensors. The key innovations developed are a new cost function which measures the temporal sampling properties of a satellite constellation, and the use of it together with existing cost functions for spatial sampling to design satellite constellations that optimize performance with respect to both performance metrics.

Quality rectal hydrogel placement allows for gel-enabled dose-escalated EBRT (GEDE-EBRT) without rectal interference in prostate cancer.

Multiple trials have shown that dose-escalation of radiation for prostate cancer provides a biochemical progression-free survival benefit (bPFS); however, rectal constraints are often limiting. In this dosimetric study, we hypothesized that a well-placed rectal hydrogel (RH) would permit improved dose-escalation and target coverage. We selected patients with good-quality RH and created plans with and without RH, prescribing 70 Gy in 28 fractions to the prostate and proximal seminal vesicles (PSV), and a peripheral zone (PZ) boost to 84 Gy, 98 Gy, or 112 Gy. We then compared plans with and without RH, prescribing a 112 Gy boost to 1 to 2 cm simulated dominant intraprostatic lesions (DIL). In the 18 plans created with a PZ boost, the PTV_boost D95% was higher in RH plans compared to non-RH plans (median 98.5 Gy vs 75.53 Gy, p < 0.01). The PSV planning target volume (PTV_PSV) D95% was also marginally higher with RH (71.87 Gy vs 71.04 Gy, p < 0.01). All rectal metrics were improved with RH. For the 32 plans created for simulated DILs treated to 112 Gy, the PTV_boost coverage (median D95% 112.48 Gy vs 102.63 Gy, p < 0.01) and rectal metrics were improved with RH. Four non-RH plans with at least a 4 mm rectal-PTV_boost gap achieved D95% > 98% of the prescription dose for the PTV_boost. Our study showed that placement of a high-quality RH allowed for GEDE-EBRT up to 112 Gy in 28 fractions (EQD2 160 Gy with α/β = 2.5). This concept should be tested prospectively, particularly to assess for increases in nonrectal toxicities.

GradFuzz: Fuzzing deep neural networks with gradient vector coverage for adversarial examples

Deep neural networks (DNNs) are susceptible to adversarial attacks that add perturbations to the input data, leading to misclassification errors and causing machine-learning systems to fail. For defense, adversarial training leverages possible crashing inputs, i.e., adversarial examples; but, the input space of DNNs is enormous and high-dimensional, making it difficult to find in a wide range. Coverage-guided fuzzing is promising in this respect. However, this leaves the question of what coverage metrics are appropriate for DNNs. We observed that the abilities of existing coverage metrics are limited. They lack gradual guidance toward crashes because of a simple search for a wide neuron activation area. None of the existing approaches can simultaneously achieve high crash quantity, high crash diversity, and efficient fuzzing time. Apart from this, the evaluation methodologies adopted by state-of-the-art fuzzers need rigorous improvements. To address these problems, we present a new DNN fuzzer named GradFuzz. Our idea is the gradient vector coverage, which provides gradual guidance to misclassified categories. We implemented our system and performed experiments under rigorous evaluation methodologies. Our evaluation results indicate that GradFuzz outperforms state-of-the-art DNN fuzzers: GradFuzz can locate a more diverse set of errors, beneficial to adversarial training, on the MNIST and CIFAR-10 datasets without sacrificing both crash quantity and fuzzing efficiency.