Search

Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.

IntroductionColorectal cancer (CRC) incidence and mortality rates are increasing in adults aged

BACKGROUND AND AIMS: Traditional serrated adenomas (TSAs) may confer increased risk for colorectal cancer (CRC). Our objective with this study was to examine clinical characteristics and long-term outcomes associated with TSA diagnosis. METHODS: We conducted a retrospective cohort study of U.S. Veterans ≥18 years of age with ≥1 TSA between 1999 and 2018. Baseline characteristics, colonoscopy findings, and diagnosis of incident and fatal CRC were abstracted. Advanced neoplasia was defined by CRC or adenoma with high-grade dysplasia, villous histology, or size ≥1 cm. Follow-up was through CRC diagnosis, death, or end of study (December 31, 2018). RESULTS: A total of 853 Veterans with a baseline TSA were identified; 74% were ≥60 years of age, 96% were men, 14% were Black, and 73% were non-Hispanic White. About 64% were current or former smokers. Over 2044 total person-years at follow-up, there were 11 incident CRC cases and 1 CRC death. Cumulative CRC incidence was 1.34% (95% confidence interval [CI], 0.67%-2.68%), and cumulative CRC death was 0.12% (95% CI, 0.00%-0.35%). Among the subset of 378 TSA patients with ≥1 surveillance colonoscopy, 65.1% had high-risk neoplasia on follow-up. CRC incidence among TSA patients was significantly higher than in a comparison cohort of patients with normal baseline colonoscopy at baseline (hazard ratio, 3.70; 95% CI, 1.63-8.41) and similar to a comparison cohort with baseline conventional advanced adenoma (hazard ratio, 0.86; 95% CI, 0.45-1.64). CONCLUSION: Individuals with TSA have substantial risk for CRC based on their cumulative CRC incidence, as well as significant risk of developing other high-risk neoplasia at follow-up surveillance colonoscopy. These data underscore importance of current recommendations for close colonoscopy surveillance after TSA diagnosis.

Delays in colonoscopy work-up for red flag signs or symptoms of colorectal cancer (CRC) during the COVID-19 pandemic are not well characterized. To examine colonoscopy uptake and time to colonoscopy after red flag diagnosis, before and during the COVID-19 pandemic. Cohort study of adults ages 50-75 with iron deficiency anemia (IDA), hematochezia, or abnormal stool blood test receiving Veterans Health Administration (VHA) care from April 2019 to December 2020. Index date was first red flag diagnosis date, categorized into "pre" (April-December 2019) and "intra" (April-December 2020) policy implementation prioritizing diagnostic procedures, allowing for a 3-month "washout" (January-March 2020) period. Outcomes were colonoscopy completion and time to colonoscopy pre- vs. intra-COVID-19, examined using multivariable Cox models with hazard ratios (aHRs) and 95% confidence intervals (CIs). There were 52,539 adults with red flag signs or symptoms (pre-COVID: 25,154; washout: 7527; intra-COVID: 19,858). Proportion completing colonoscopy was similar pre- vs. intra-COVID-19 (27.0% vs. 26.5%; p = 0.24). Median time to colonoscopy among colonoscopy completers was similar for pre- vs. intra-COVID-19 (46 vs. 42 days), but longer for individuals with IDA (60 vs. 49 days). There was no association between time period and colonoscopy completion (aHR: 0.99, 95% CI 0.95-1.03). Colonoscopy work-up of CRC red flag signs and symptoms was not delayed within VHA during the COVID-19 pandemic, possibly due to VHA policies supporting prioritization and completion. Further work is needed to understand how COVID-19 policies on screening and surveillance impact CRC-related outcomes, and how to optimize colonoscopy completion after a red flag diagnosis.

In assessing food microbial safety, the presence of Escherichia coli is a critical indicator of fecal contamination. However, conventional detection methods require the isolation of bacterial macrocolonies for biochemical or genetic characterization, which takes a few days and is labor-intensive. In this study, we show that the real-time object detection and classification algorithm You Only Look Once version 4 (YOLOv4) can accurately identify the presence of E. coli at the microcolony stage after a 3-h cultivation. Integrating with phase-contrast microscopic imaging, YOLOv4 discriminated E. coli from seven other common foodborne bacterial species with an average precision of 94%. This approach also enabled the rapid quantification of E. coli concentrations over 3 orders of magnitude with an R2 of 0.995. For romaine lettuce spiked with E. coli (10 to 103 CFU/g), the trained YOLOv4 detector had a false-negative rate of less than 10%. This approach accelerates analysis and avoids manual result determination, which has the potential to be applied as a rapid and user-friendly bacterial sensing approach in food industries. IMPORTANCE A simple, cost-effective, and rapid method is desired to identify potential pathogen contamination in food products and thus prevent foodborne illnesses and outbreaks. This study combined artificial intelligence (AI) and optical imaging to detect bacteria at the microcolony stage within 3 h of inoculation. This approach eliminates the need for time-consuming culture-based colony isolation and resource-intensive molecular approaches for bacterial identification. The approach developed in this study is broadly applicable for the identification of diverse bacterial species. In addition, this approach can be implemented in resource-limited areas, as it does not require expensive instruments and significantly trained human resources. This AI-assisted detection not only achieves high accuracy in bacterial classification but also provides the potential for automated bacterial detection, reducing labor workloads in food industries, environmental monitoring, and clinical settings.

Background and Aims: There are limited contemporary population-based data on Helicobacter pylori epidemiology and outcomes in the United States. Our primary aim was to create a validated cohort of veterans with H pylori testing or treatment using Veterans Health Administration data. Methods: Using Veterans Health Administration structured and unstructured data, we developed and validated 4 algorithms for H pylori infection (3 algorithms) and treatment status (1 algorithm). During the development phase, we iteratively modified each algorithm based on a manual review of random sets of electronic health records (reference standard). The a priori validation goal was to achieve a one-sided 95% confidence lower bound (LB) for positive predictive value (PPV) and/or negative predictive value (NPV) >90%. We applied the Bonferroni correction when both PPV and NPV were relevant. Results: For H pylori infection, we achieved 99.0% PPV (LB = 94.6%) and 100% NPV (LB = 96.4%) for discriminating H pylori positive vs negative status using structured (ie, laboratory tests) and 95% PPV (LB = 90.3%) and 97.9% NPV (LB = 93.9%) using unstructured (ie, histopathology reports) data. Diagnostic codes achieved 98% PPV (LB = 93.0%) for H pylori diagnosis. The treatment algorithm was composed of multiple antimicrobial combinations and overall achieved ≥98% PPV (LB = 93.0%) for H pylori treatment, except for amoxicillin/levofloxacin (PPV

Similar to other cropping systems, few walnut cultivars are used as scion in commercial production. Germplasm collections can be used to diversify cultivar options and hold potential for improving crop productivity, disease resistance and stress tolerance. In this study, we explored the anatomical and biochemical bases of photosynthetic capacity and response to water stress in 11 Juglans regia accessions in the U.S. department of agriculture, agricultural research service (USDA-ARS) National Clonal Germplasm. Net assimilation rate (An ) differed significantly among accessions and was greater in lower latitudes coincident with higher stomatal and mesophyll conductances, leaf thickness, mesophyll porosity, gas-phase diffusion, leaf nitrogen and lower leaf mass and stomatal density. High CO2 -saturated assimilation rates led to increases in An under diffusional and biochemical limitations. Greater An was found in lower-latitude accessions native to climates with more frost-free days, greater precipitation seasonality and lower temperature seasonality. As expected, water stress consistently impaired photosynthesis with the highest % reductions in lower-latitude accessions (A3, A5 and A9), which had the highest An under well-watered conditions. However, An for A3 and A5 remained among the highest under dehydration. J. regia accessions, which have leaf structural traits and biochemistry that enhance photosynthesis, could be used as commercial scions or breeding parents to enhance productivity.

Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.

Background and aimsPancreatic cancer incidence and mortality among patients with pancreas cysts are unclear. The aims of this study are to evaluate incidence of pancreatic cancer and cause-specific mortality among patients with pancreatic cysts using a large national cohort over a long follow-up period.MethodsWe conducted a retrospective cohort study of US Veterans diagnosed with a pancreatic cyst 1999-2013, based on International Classification of Diseases, 9th edition (ICD9) coding within national Department of Veterans Affairs (VA) data. Pancreatic cancer incidence was ascertained using VA cancer registry data, ICD-9 codes, and the National Death Index, a national centralized database of death records, including cause-specific mortality.ResultsAmong 7211 Veterans with pancreatic cysts contributing 31,501 person-years of follow-up (median follow-up 4.4 years), 79 (1.1%) developed pancreatic cancer. A total of 1982 patients (27.5%) died during the study follow-up period. Sixty-three patients (3.2% of deaths; 0.9% of pancreas cyst cohort) died from pancreatic cancer, but the leading causes of death in the cohort were non-pancreatic cancer (n = 498, 25% of deaths) and cardiovascular disease (n = 398, 20% of deaths).ConclusionsPancreas cancer incidence and pancreatic cancer-associated mortality are very low in a large national cohort of VA pancreatic cyst patients with long-term follow-up. Most deaths were from non-pancreas cancers and cardiovascular causes, and only a minority (3.2%) were attributable to pancreas cancer. Given death from pancreas cancer is rare, future research should focus on identifying criteria for selecting individuals at high risk for death from pancreatic cancer for pancreatic cyst surveillance.

X-ray micro-computed tomography (X-ray μCT) has enabled the characterization of the properties and processes that take place in plants and soils at the micron scale. Despite the widespread use of this advanced technique, major limitations in both hardware and software limit the speed and accuracy of image processing and data analysis. Recent advances in machine learning, specifically the application of convolutional neural networks to image analysis, have enabled rapid and accurate segmentation of image data. Yet, challenges remain in applying convolutional neural networks to the analysis of environmentally and agriculturally relevant images. Specifically, there is a disconnect between the computer scientists and engineers, who build these AI/ML tools, and the potential end users in agricultural research, who may be unsure of how to apply these tools in their work. Additionally, the computing resources required for training and applying deep learning models are unique, more common to computer gaming systems or graphics design work, than to traditional computational systems. To navigate these challenges, we developed a modular workflow for applying convolutional neural networks to X-ray μCT images, using low-cost resources in Google's Colaboratory web application. Here we present the results of the workflow, illustrating how parameters can be optimized to achieve best results using example scans from walnut leaves, almond flower buds, and a soil aggregate. We expect that this framework will accelerate the adoption and use of emerging deep learning techniques within the plant and soil sciences.

Background & aimsThe incidence and mortality of early-onset colorectal cancer (CRC) are increasing. Adenoma detection, removal, and subsequent endoscopic surveillance might modify risk of CRC diagnosed before age 50 years (early-onset CRC). We conducted a systematic review of young-onset adenoma (YOA) prevalence, associated risk factors, and rate of metachronous advanced neoplasia after YOA diagnosis.MethodsWe performed a systematic search of multiple electronic databases through February 12, 2019 and identified studies of individuals 18 to 49 years old that reported prevalence of adenoma, risk factors for adenoma, and/or risk for metachronous advanced neoplasia. Summary estimates were derived using random effects meta-analysis, when feasible.ResultsThe pooled overall prevalence of YOA was 9.0% (95% CI, 7.1%-11.4%), based on 24 studies comprising 23,142 individuals. On subgroup analysis, the pooled prevalence of YOA from autopsy studies was 3.9% (95% CI, 1.9%-7.6%), whereas the prevalence from colonoscopy studies was 10.7% (95% CI, 8.5%-13.5). Only advancing age was identified as a consistent risk factor for YOA, based on 4 studies comprising 78,880 individuals. Pooled rate of metachronous advanced neoplasia after baseline YOA diagnosis was 6.0% (95% CI, 4.1%-8.6%), based on 3 studies comprising 1493 individuals undergoing follow-up colonoscopy, with only 1 CRC case reported. Overall, few studies reported metachronous advanced neoplasia and no studies evaluated whether routine surveillance colonoscopy decreases risk of CRC.ConclusionsIn a systematic review, we estimated the prevalence of YOA to be 9% and to increase with age. Risk for metachronous advanced neoplasia after YOA diagnosis is estimated to be 6%. More research is needed to understand the prevalence, risk factors, and risk of CRC associated with YOA.

Maintaining high rates of photosynthesis in leaves requires efficient movement of CO2 from the atmosphere to the mesophyll cells inside the leaf where CO2 is converted into sugar. CO2 diffusion inside the leaf depends directly on the structure of the mesophyll cells and their surrounding airspace, which have been difficult to characterize because of their inherently three-dimensional organization. Yet faster CO2 diffusion inside the leaf was probably critical in elevating rates of photosynthesis that occurred among angiosperm lineages. Here we characterize the three-dimensional surface area of the leaf mesophyll across vascular plants. We show that genome size determines the sizes and packing densities of cells in all leaf tissues and that smaller cells enable more mesophyll surface area to be packed into the leaf volume, facilitating higher CO2 diffusion. Measurements and modelling revealed that the spongy mesophyll layer better facilitates gaseous phase diffusion while the palisade mesophyll layer better facilitates liquid-phase diffusion. Our results demonstrate that genome downsizing among the angiosperms was critical to restructuring the entire pathway of CO2 diffusion into and through the leaf, maintaining high rates of CO2 supply to the leaf mesophyll despite declining atmospheric CO2 levels during the Cretaceous.

Developing low-cost technology for custom water delivery to individual or small groups of plants is a critical next step to advance precision irrigation. Current systems for estimating evapotranspiration (ET), or plant water use, work on the scale of a full vineyard (e.g., 3–5 acres) or the scale of a single vine, but at a cost that prohibits monitoring past a small number of representative vines. To develop and evaluate low-cost ET sensors for individual grapevines, we used three head-pruned Zinfandel vines in pots and placed them on load cells to collect continuous weights indicative of actual ET. We mounted research-grade sensors for humidity, temperature, and wind speed on each vine and saved data at 2-minute intervals during three growing seasons. We developed three models based on first principles (Convective Mass Transfer or Mass Balance approaches) or simple correlations to predict actual single-plant ET from these data. We present here the results of a multi-year trial at the UC-Davis RMI vineyard to illustrate the performance of each of the models for ET estimation. Relative model performance was assessed by comparing model predictions to ground truth data provided by measurements from load cells–including assessments of estimated instantaneous ET rate, estimated cumulative water use over a one-hour window surrounding solar noon, and estimated cumulative water use over a full 24-hour period. The three algorithms developed consistently performed well, with single vine ET rate predictions showing a strong linear relationship with ground truth (range in r2 over three seasons CMT r2 = 0.61–0.86; MB r2 = 0.07–0.91; EM r2 = 0.57–0.92). The MB approach, which includes two measurements of relative humidity and temperature, was the most variable, likely due to the impact of sensor placement. In all seasons, we also examined the trend in the plant scaling factor found in each model, deemed As, which, based on model theory, is a function of vine size. Taken together, these results suggest that high-resolution irrigation (HRI) models are a promising new method for ET estimation at the single plant level.

Background & aimsColorectal cancer (CRC) incidence and mortality are increasing among persons younger than 50 years old in the United States, but risk factors associated with early-onset CRC (EOCRC) have not been widely studied.MethodsWe conducted a case-control study of US veterans 18 to 49 years old who underwent colonoscopy examinations from 1999 through 2014. EOCRC cases were identified from a national cancer registry; veterans who were free of CRC at their baseline colonoscopy through 3 years of follow-up were identified as controls. We collected data on age, sex, race/ethnicity, body weight, body mass index (BMI), diabetes, smoking status, and aspirin use. Multivariate-adjusted EOCRC odds were estimated for each factor, with corresponding 95% confidence interval (CI) values.ResultsOur final analysis included 651 EOCRC cases and 67,416 controls. Median age was 45.3 years, and 82.3% were male. Higher proportions of cases were older, male, current smokers, nonaspirin users, and had lower BMIs, compared with controls (P < .05). In adjusted analyses, increasing age and male sex were significantly associated with increased risk of EOCRC, whereas aspirin use and being overweight or obese (relative to normal BMI) were significantly associated with decreased odds of EOCRC. In post hoc analyses, weight loss of 5 kg or more within the 5-year period preceding colonoscopy was associated with higher odds of EOCRC (odds ratio 2.23; 95% CI 1.76-2.83).ConclusionsIn a case-control study of veterans, we found increasing age and male sex to be significantly associated with increased risk of EOCRC, and aspirin use to be significantly associated with decreased risk; these factors also affect risk for CRC onset after age 50. Weight loss may be an early clinical sign of EOCRC. More intense efforts are required to identify the factors that cause EOCRC and signs that can be used to identify individuals at highest risk.

PremiseX-ray microcomputed tomography (microCT) can be used to measure 3D leaf internal anatomy, providing a holistic view of tissue organization. Previously, the substantial time needed for segmenting multiple tissues limited this technique to small data sets, restricting its utility for phenotyping experiments and limiting our confidence in the inferences of these studies due to low replication numbers.Methods and resultsWe present a Python codebase for random forest machine learning segmentation and 3D leaf anatomical trait quantification that dramatically reduces the time required to process single-leaf microCT scans into detailed segmentations. By training the model on each scan using six hand-segmented image slices out of >1500 in the full leaf scan, it achieves >90% accuracy in background and tissue segmentation.ConclusionsOverall, this 3D segmentation and quantification pipeline can reduce one of the major barriers to using microCT imaging in high-throughput plant phenotyping.

An exponentially growing body of international research engages with plastic pollution using different ideas on the right ways to frame, research, and intervene in the problem. The premise of this study is that all scientists work with understandings of what is right and wrong and why that is (models of justice) in their research, even when it is not explicitly stated, reflected upon, or a conscious part of the discussion. We surveyed 755 published articles on marine debris and plastic chemical additives and found that all evoked at least one model of justice, and often more. The most routinely used models included: developmental justice, distributive justice, and procedural justice. More rarely, we found appeals to environment-first justice and Indigenous sovereignty. While occasionally these multiple models worked synergistically, more often they conflicted. Our findings ground a call for fellow researchers to use a more intentional and systematic approach to evoking models of justice in our work. Our goal is to offer descriptions and insights about models of justice that are already being deployed to increase the sophistication of the ethical and normative orientations of our research and our fields, both in plastic pollution sciences and beyond.

ObjectiveTo conduct an anatomic site-specific case-control study of candidate colorectal cancer (CRC) risk factors.DesignCase-control study of US veterans with >1 colonoscopy during 1999-2011. Cases had cancer registry-identified CRC at colonoscopy, while controls were CRC free at colonoscopy and within 3 years of colonoscopy. Primary outcome was CRC, stratified by anatomic site: proximal, distal, or rectal. Candidate risk factors included age, sex, race/ethnicity, body mass index, height, diabetes, smoking status, and aspirin exposure summarised by adjusted ORs and 95% CIs.Results21 744 CRC cases (n=7017 rectal; n=7039 distal; n=7688 proximal) and 612 646 controls were included. Males had significantly higher odds relative to females for rectal cancer (OR=2.84, 95% CI 2.25 to 3.58) than distal cancer (OR=1.84, 95% CI 1.50 to 2.24). Relative to whites, blacks had significantly lower rectal cancer odds (OR=0.88, 95% CI 0.82 to 0.95), but increased distal (OR=1.27, 95% CI 1.19 to 1.37) and proximal odds (OR=1.62, 95% CI 1.52 to 1.72). Diabetes prevalence was more strongly associated with proximal (OR=1.29, 95% CI 1.22 to 1.36) than distal (OR=1.15, 95% CI 1.08 to 1.22) or rectal cancer (OR=1.12, 95% CI 1.06 to 1.19). Current smoking was more strongly associated with rectal cancer (OR=1.81, 95% CI 1.68 to 1.95) than proximal cancer (OR=1.53, 95% CI 1.43 to 1.65) or distal cancer (OR=1.46, 95% CI 1.35 to 1.57) compared with never smoking. Aspirin use was significantly more strongly associated with reduced rectal cancer odds (OR=0.71, 95% CI 0.67 to 0.76) than distal (OR=0.85, 95% CI 0.81 to 0.90) or proximal (OR=0.91, 95% CI 0.86 to 0.95).ConclusionCandidate CRC risk factor associations vary significantly by anatomic site. Accounting for site may enable better insights into CRC pathogenesis and cancer control strategies.

PurposeCancer ascertainment using large-scale electronic health records is a challenge. Our aim was to propose and apply a structured approach for evaluating multiple candidate approaches for cancer ascertainment using colorectal cancer (CRC) ascertainment within the US Department of Veterans Affairs (VA) as a use case.MethodsThe proposed approach for evaluating cancer ascertainment strategies includes assessment of individual strategy performance, comparison of agreement across strategies, and review of discordant diagnoses. We applied this approach to compare three strategies for CRC ascertainment within the VA: administrative claims data consisting of International Classification of Diseases, Ninth Revision (ICD9) diagnosis codes; the VA Central Cancer Registry (VACCR); and the newly accessible Oncology Domain, consisting of cases abstracted by local cancer registrars. The study sample consisted of 1,839,043 veterans with index colonoscopy performed from 1999 to 2014. Strategy-specific performance was estimated based on manual record review of 100 candidate CRC cases and 100 colonoscopy controls. Strategies were further compared using Cohen's κ and focused review of discordant CRC diagnoses.ResultsA total of 92,197 individuals met at least one CRC definition. All three strategies had high sensitivity and specificity for incident CRC. However, the ICD9-based strategy demonstrated poor positive predictive value (58%). VACCR and Oncology Domain had almost perfect agreement with each other (κ, 0.87) but only moderate agreement with ICD9-based diagnoses (κ, 0.51 and 0.57, respectively). Among discordant cases reviewed, 15% of ICD9-positive but VACCR- or Oncology Domain-negative cases had incident CRC.ConclusionEvaluating novel strategies for identifying cancer requires a structured approach, including validation against manual record review, agreement among candidate strategies, and focused review of discordant findings. Without careful assessment of ascertainment methods, analyses may be subject to bias and limited in clinical impact.

We present a reverse-taper quantum cascade laser (QCL) emitting at 4.6 μm, a novel-geometry device that can scale the output power while maintaining good beam quality. Buried-ridge waveguides with tapered and straight regions were formed by ICP etching and HVPE regrowth – the tapered region scales the output power, while the emitting facet is located at the narrow-end taper section, which provides mode filtering by suppressing high-order spatial modes. Beam profiles were observed under quasi-continuous-wave (QCW)/CW operation and beam quality (M2) measurements along with beam-stability measurements were performed – a small degree of collimated-beam centroid movement (2 values close to 1 up to ∼1 W QCW power. Devices of shorter cavity lengths were also investigated, indicating that the output power scales with the core-region volume but results in a small increase in angular deviation.

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural datasets. This lack of agriculture-specific fine-tuning potentially increases training time and resource use, and decreases model performance, leading to an overall decrease in data efficiency. To overcome this limitation, we collect a wide range of existing public datasets for 3 distinct tasks, standardize them, and construct standard training and evaluation pipelines, providing us with a set of benchmarks and pretrained models. We then conduct a number of experiments using methods that are commonly used in deep learning tasks but unexplored in their domain-specific applications for agriculture. Our experiments guide us in developing a number of approaches to improve data efficiency when training agricultural deep learning models, without large-scale modifications to existing pipelines. Our results demonstrate that even slight training modifications, such as using agricultural pretrained model weights, or adopting specific spatial augmentations into data processing pipelines, can considerably boost model performance and result in shorter convergence time, saving training resources. Furthermore, we find that even models trained on low-quality annotations can produce comparable levels of performance to their high-quality equivalents, suggesting that datasets with poor annotations can still be used for training, expanding the pool of currently available datasets. Our methods are broadly applicable throughout agricultural deep learning and present high potential for substantial data efficiency improvements.

ObjectiveTo describe a framework for leveraging big data for research and quality improvement purposes and demonstrate implementation of the framework for design of the Department of Veterans Affairs (VA) Colonoscopy Collaborative.MethodsWe propose that research utilizing large-scale electronic health records (EHRs) can be approached in a 4 step framework: 1) Identify data sources required to answer research question; 2) Determine whether variables are available as structured or free-text data; 3) Utilize a rigorous approach to refine variables and assess data quality; 4) Create the analytic dataset and perform analyses. We describe implementation of the framework as part of the VA Colonoscopy Collaborative, which aims to leverage big data to 1) prospectively measure and report colonoscopy quality and 2) develop and validate a risk prediction model for colorectal cancer (CRC) and high-risk polyps.ResultsExamples of implementation of the 4 step framework are provided. To date, we have identified 2,337,171 Veterans who have undergone colonoscopy between 1999 and 2014. Median age was 62 years, and 4.6 percent (n = 106,860) were female. We estimated that 2.6 percent (n = 60,517) had CRC diagnosed at baseline. An additional 1 percent (n = 24,483) had a new ICD-9 code-based diagnosis of CRC on follow up.ConclusionWe hope our framework may contribute to the dialogue on best practices to ensure high quality epidemiologic and quality improvement work. As a result of implementation of the framework, the VA Colonoscopy Collaborative holds great promise for 1) quantifying and providing novel understandings of colonoscopy outcomes, and 2) building a robust approach for nationwide VA colonoscopy quality reporting.