Search NASA⌕ Search

SEARCH · Search NASA

Results for “ROC analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10

An image classification deep-learning algorithm for shrapnel detection from ultrasound images

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.

59 BASIC BIOLOGICAL SCIENCES↗

Preliminary performance assessment of biotoxin detection for UWS applications using a MicroChemLab device.

In a multiyear research agreement with Tenix Investments Pty. Ltd., Sandia has been developing field deployable technologies for detection of biotoxins in water supply systems. The unattended water sensor or UWS employs microfluidic chip based gel electrophoresis for monitoring biological analytes in a small integrated sensor platform. This instrument collects, prepares, and analyzes water samples in an automated manner. Sample analysis is done using the {mu}ChemLab{trademark} analysis module. This report uses analysis results of two datasets collected using the UWS to estimate performance of the device. The first dataset is made up of samples containing ricin at varying concentrations and is used for assessing instrument response and detection probability. The second dataset is comprised of analyses of water samples collected at a water utility which are used to assess the false positive probability. The analyses of the two sets are used to estimate the Receiver Operating Characteristic or ROC curves for the device at one set of operational and detection algorithm parameters. For these parameters and based on a statistical estimate, the ricin probability of detection is about 0.9 at a concentration of 5 nM for a false positive probability of 1 x 10{sup -6}.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Dosimetric Predictors of Patient-Reported Xerostomia and Dysphagia With Deintensified Chemoradiation Therapy for HPV-Associated Oropharyngeal Squamous Cell Carcinoma

Purpose/Objective(s): To estimate the association between different dose-volume metrics of the salivary glands and pharyngeal constrictors with patient reported severity of xerostomia/dysphagia in the setting of deintensified chemoradiation therapy (CRT). Methods and Materials: Forty-five patients were treated on a phase 2 study assessing the efficacy of deintensified CRT for favorable-risk, HPV-associated oropharyngeal squamous cell carcinoma. Patients received 60 Gy intensity modulated radiation therapy with concurrent weekly cisplatin (30 mg/m{sup 2}), and reported the severity of their xerostomia/dysphagia (before and after treatment) using the patient-reported outcome version of the Common Terminology Criteria for Adverse Events (CTCAE) (PRO-CTCAE). Individual patient dosimetric data of the contralateral parotid and submandibular glands and pharyngeal constrictors were correlated with changes in PRO-CTCAE severity. A change in severity (from baseline) of ≥2 was considered clinically meaningful. Associations between dose-volume metrics and patient outcomes were assessed with receiver operating characteristic (ROC) curve and logistic regression model. Results: Six months after CRT, patients reporting <2 change in xerostomia severity (n=14) had an average D{sub mean} = 22 ± 9 Gy to the sum of the contralateral glands (parotid + submandibular) compared with the patients reporting ≥2 change (n=21), who had an average D{sub mean} = 34 ± 8 Gy. V15 to V55 for the combined contralateral glands showed the strongest association with xerostomia (area under the curve [AUC] = 0.83-0.86). Based on the regression analysis, a 20% risk of toxicity was associated with V15 = 48%, V25 = 30%, and D{sub mean}=21 Gy. Six months after CRT, patients reporting <2 change in dysphagia severity (n=26) had an average V55 = 76 ± 13 (%) to the superior pharyngeal constrictor compared with the patients reporting ≥2 change in severity (n=9), who had average V55 = 89 ± 13 (%). V55to V60 had the strongest association with dysphagia (AUC = 0.70-0.75). Based on the regression analysis, a 20% risk of toxicity was associated with V55 = 78%, V60 = 40%. The findings at 12 months were similar. Conclusions: After deintensified CRT, the rate of patient-reported xerostomia/dysphagia appears to be associated with the V15 of the combined contralateral salivary glands and V55 to V60 of the superior pharyngeal constrictors.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Assessment of Rare Earth Element Fingerprints for Distinguishing Between Site-Related Wastes and Background - 19441

Actinides such as uranium, thorium and radium are known to be present in sites associated with various phases of the cold war weapons research, development and production. Remediation of these sites as well as others associated with chemical plants that may have generated radioactive actinide-containing wastes have been the focus of the Formerly Utilized Sites Remedial Action Program (FUSRAP) for the past 20 years. The goal is to remediate a site to established cleanup standards as efficiently and cost-effectively as possible. For radiologically-contaminated sites, one potential challenge is the presence of non-FUSRAP media such as naturally-occurring radioactive material (NORM) or technologically-enhanced naturally-occurring radioactive material (TENORM), from non-FUSRAP sources, at concentrations exceeding site cleanup standards. Such NORM and TENORM, and even byproduct radionuclides from other unrelated activities on or near the site, can be mistaken for project waste and thus incur significant additional excavation and waste transport and disposal costs. Past studies have provided examples of NORM and non-FUSRAP waste and described strategies to distinguish them from FUSRAP waste. This paper describes various sources of NORM, summarizes the types of project-related waste at some active FUSRAP sites, and identifies TENORM sites from which radionuclides could possibly migrate via various environmental pathways to nearby FUSRAP sites. The authors also examine two Case Studies that calculate distinctive elemental ratios and are examples of tools which may be used for distinguishing FUSRAP waste from other radionuclides present in natural or other man-made contributors to background. Case Study I examines two bodies of data and calculates distinctive elemental ratios between pairs of rare earth elements (REE) to see if significant differences may exist between such ratios in unregulated coal ash residue, common in fill in well-established towns and cities, and FUSRAP waste. The first group of data, consisting of eighteen sample results, was obtained from the FUSRAP Maywood Superfund Site's historical data while the second was obtained from a paper which provided extensive data (more than 100 samples) on the REE content in fly ash residues from three major coal-producing areas in the United States. This example illustrates statistically significant differences in five of six REE ratios and thus provides a potential tool for distinguishing FUSRAP waste from coal ash-based NORM. Case Study II examines differences in the mean REE:Actinide and REE:REE ratios in Welsbach-impacted sample results to distinguish project waste from background. While the purpose of this study was to distinguish project waste from background levels of the radionuclides of concern (ROC), it provides a good example of how one or more ratios could potentially be used to distinguish FUSRAP waste from NORM. Lastly, the authors recommend that future projects ensure robust characterization, that considers all potential radionuclide contributors from both FUSRAP activities as well as from other contributors to background for the region during the Planning Phase of the Data Life Cycle described within the Multi-Agency Radiation Survey and Site Investigation Manual (MARSSIM). It is expected that the incremental characterization sampling and analysis costs will be dwarfed by potential savings from efforts to better delineate and limit remediation to FUSRAP wastes rather than other potentially unregulated contributors to regional background. Other agencies or commercial entities with radiological environmental liabilities similar to FUSRAP would benefit from similar considerations of REEs and other radionuclides that could contribute to regional background. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

The Role of Seven-Coordination in Ru-Catalyzed Water Oxidation

A family of Ru complexes based on the pentadentate ligand t5a 3– ((2,5-bis(6-carboxylatopyridin-2-yl)pyrrol-1-ide) and pyridine (py) that includes {Ru II (Ht5a-κ-N 2 O)(py) 3 } (1H II (κ-N 2 O)), {Ru III (t5a-κ-N 3 O 1.5 )(py) 2 } (2 III (κ-N 3 O 1.5 )), and {Ru IV (t5a-κ-N 3 O 2 )(py) 2 }+ ({2 IV (κ-N3O 2 )}+) has been prepared and thoroughly characterized. Complexes 1HII(κ-N 2 O), 2 III (κ-N 3 O 1.5 ), and {2 IV (κ-N 3 O 2 )}+ have been investigated in solution by spectroscopic methods (NMR, UV–vis) and in the solid state by single-crystal X-ray diffraction analysis and complemented by density functional theory (DFT) calculations. The redox properties of complex 2 III (κ-N 3 O 1.5 ) have been studied by electrochemical methods (CV and DPV), showing its easy access to high oxidation states, thanks to the trianionic nature of the t5a 3– ligand. Under neutral to basic conditions complex {2 IV (κ-N3O 2 )}+ undergoes aquation, generating {Ru IV (OH)(t5a-κ-N 2 O)(py) 2 } (2 IV (OH)(κ-N 2 O)). Further oxidation of the complex forms {Ru V (O)(t5a-κ-N 2 O)(py) 2 } (2 V (O)(κ-N 2 O)), which is a very efficient water oxidation catalyst, reaching a TOF MAX value of 9400 s –1 at pH 7.0, as measured via foot of the wave analysis. The key to fast kinetics for the catalytic oxidation of water to dioxygen by 2 V (O)(κ-N 2 O) is due not only to the easy access to high oxidation states but also to the intramolecular hydrogen bonding provided by the noncoordinated dangling carboxylate at the transition state, as corroborated by DFT calculations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Intramolecular Proton Transfer Boosts Water Oxidation Catalyzed by a Ru Complex

We introduce a new family of complexes with the general formula [Run(tda)(py)2]m+ (n = 2, m = 0, 1; n = 3, m = 1, 2+; n = 4, m = 2, 32+), with tda2– being [2,2':6',2''-terpyridine]-6,6''-dicarboxylate, including complex [RuIV(OH)(tda-κ-N3O)(py)2]+, 4H+, which we find to be an impressive water oxidation catalyst, formed by hydroxo coordination to 32+ under basic conditions. The complexes are synthesized, isolated, and thoroughly characterized by analytical, spectroscopic (UV–vis, nuclear magnetic resonance, electron paramagnetic resonance), computational, and electrochemical techniques (cyclic voltammetry, differential pulse voltammetry, coulometry), including solid-state monocrystal X-ray diffraction analysis. In oxidation state IV, the Ru center is seven-coordinated and diamagnetic, whereas in oxidation state II, the complex has an unbonded dangling carboxylate and is six-coordinated while still diamagnetic. With oxidation state III, the coordination number is halfway between the coordination of oxidation states II and IV. Species generated in situ have also been characterized by spectroscopic, computational, and electrochemical techniques, together with the related species derived from a different degree of protonation and oxidation states. 4H+ can be generated potentiometrically, or voltammetrically, from 32+, and both coexist in solution. While complex 32+ is not catalytically active, the catalytic performance of complex 4H+ is characterized by the foot of the wave analysis, giving an impressive turnover frequency record of 8000 s–1 at pH 7.0 and 50 000 s–1 at pH 10.0. Density functional theory calculations provide a complete description of the water oxidation catalytic cycle of 4H+, manifesting the key functional role of the dangling carboxylate in lowering the activation free energies that lead to O–O bond formation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

B-spline active rays segmentation of microcalcifications in mammography

Accurate segmentation of microcalcifications in mammography is crucial for the quantification of morphologic properties by features incorporated in computer-aided diagnosis schemes. A novel segmentation method is proposed implementing active rays (polar-transformed active contours) on B-spline wavelet representation to identify microcalcification contour point estimates in a coarse-to-fine strategy at two levels of analysis. An iterative region growing method is used to delineate the final microcalcification contour curve, with pixel aggregation constrained by the microcalcification contour point estimates. A radial gradient-based method was also implemented for comparative purposes. The methods were tested on a dataset consisting of 149 mainly pleomorphic microcalcification clusters originating from 130 mammograms of the DDSM database. Segmentation accuracy of both methods was evaluated by three radiologists, based on a five-point rating scale. The radiologists' average accuracy ratings were 3.96{+-}0.77, 3.97{+-}0.80, and 3.83{+-}0.89 for the proposed method, and 2.91{+-}0.86, 2.10{+-}0.94, and 2.56{+-}0.76 for the radial gradient-based method, respectively, while the differences in accuracy ratings between the two segmentation methods were statistically significant (Wilcoxon signed-ranks test, p<0.05). The effect of the two segmentation methods in the classification of benign from malignant microcalcification clusters was also investigated. A least square minimum distance classifier was employed based on cluster features reflecting three morphological properties of individual microcalcifications (area, length, and relative contrast). Classification performance was evaluated by means of the area under ROC curve (A{sub z}). The area and length morphologic features demonstrated a statistically significant (Mann-Whitney U-test, p<0.05) higher patient-based classification performance when extracted from microcalcifications segmented by the proposed method (0.82{+-}0.06 and 0.86{+-}0.05, respectively), as compared to segmentation by the radial gradient-based method (0.71{+-}0.08 and 0.75{+-}0.08). The proposed method demonstrates improved segmentation accuracy, fulfilling human visual criteria, and enhances the ability of morphologic features to characterize microcalcification clusters.

61 RADIATION PROTECTION AND DOSIMETRY↗

Automated Detection of Microaneurysms Using Scale-Adapted Blob Analysis and Semi-Supervised Learning

Despite several attempts, automated detection of microaneurysm (MA) from digital fundus images still remains to be an open issue. This is due to the subtle nature of MAs against the surrounding tissues. In this paper, the microaneurysm detection problem is modeled as finding interest regions or blobs from an image and an automatic local-scale selection technique is presented. Several scale-adapted region descriptors are then introduced to characterize these blob regions. A semi-supervised based learning approach, which requires few manually annotated learning examples, is also proposed to train a classifier to detect true MAs. The developed system is built using only few manually labeled and a large number of unlabeled retinal color fundus images. The performance of the overall system is evaluated on Retinopathy Online Challenge (ROC) competition database. A competition performance measure (CPM) of 0.364 shows the competitiveness of the proposed system against state-of-the art techniques as well as the applicability of the proposed features to analyze fundus images.

59 BASIC BIOLOGICAL SCIENCES↗

MO-F-CAMPUS-I-01: Accuracy of Radiologists Interpretation of Mammographic Breast Density

Purpose: Several commercial and non-commercial software and techniques are available for determining breast density from mammograms. However, where mandated by law the breast density information communicated to the subject/patient is based on radiologist’s interpretation of breast density from mammograms. Several studies have reported on the concordance among radiologists in interpreting mammographic breast density. In this work, we investigated the accuracy of radiologist’s interpretation of breast density. Methods: Volumetric breast density (VBD) determined from 134 unilateral dedicated breast CT scans from 134 subjects was considered the truth. An MQSA-qualified study radiologist with more than 20 years of breast imaging experience reviewed the DICOM “for presentation” standard 2-view mammograms of the corresponding breasts and assigned BIRADS breast density categories. For statistical analysis, the breast density categories were dichotomized in two ways; fatty vs. dense breasts where “fatty” corresponds to BIRADS breast density categories A/B, and “dense” corresponds to BIRADS breast density categories C/D, and extremely dense vs. fatty to heterogeneously dense breasts, where extremely dense corresponds to BIRADS breast density category D and BIRADS breast density categories A through C were grouped as fatty to heterogeneously dense breasts. Logistic regression models (SAS 9.3) were used to determine the association between radiologist’s interpretation of breast density and VBD from breast CT, from which the area under the ROC (AUC) was determined. Results: Both logistic regression models were statistically significant (Likelihood Ratio test, p<0.0001). The accuracy (AUC) of the study radiologist for classification of fatty vs. dense breasts was 88.4% (95% CI: 83–94%) and for classification of extremely dense breast was 94.3% (95% CI: 90–98%). Conclusion: The accuracy of the radiologist in classifying dense and extremely dense breasts is high. Considering the variability in VBD estimates from commercial software, the breast density information communicated to the patient should be based on radiologist’s interpretation. This work was supported in part by NIH R21 CA176470 and R21 CA134128. The contents are solely the responsibility of the authors and do not reflect the official views of the NIH or NCI.

60 APPLIED LIFE SCIENCES↗

Different CT slice thickness and contrast‐enhancement phase in radiomics models on the differential performance of lung adenocarcinoma

Abstract Background To investigate the effects of computed tomography (CT) reconstruction slice thickness and contrast‐enhancement phase on the differential diagnosis performance of radiomic signature in lung adenocarcinoma. Methods A total of 187 patients who had been pathologically confirmed with lung adenocarcinoma and nonadenocarcinoma were divided into a training cohort ( n = 149) and validation cohort ( n = 38). All the patients underwent contrast‐enhanced CT and the images were reconstructed with different slice thickness. The radiomic features were extracted from different slice thickness and scan phase. The logistic regression (LR) algorithm was used to build a machine learning model for each group. The area under the curve (AUC) obtained from the receiver operating characteristic (ROC) curve and DeLong test was used to evaluate its discriminating performance. Results Finally, 34 image features and five semantic features were selected to establish a radiomics model. Based on the three contrast‐enhanced CT phases and four reconstruction slice thickness, 12 groups of radiomics models showed good discrimination ability with the AUCs range from 0.9287 to 0.9631, sensitivity range from 0.8349 to 0.9083, specificity range from 0.825 to 0.925 in the training group. Similar results were observed in the validation group. However, there was no statistical significance between the different CT scan phase groups and different slice thickness ( p > 0.05). Conclusions The radiomic analysis of contrast‐enhanced CT can be used for the differential diagnosis of lung adenocarcinoma. Moreover, different slice thickness and contrast‐enhanced scan phase did not affect the discriminating ability in the radiomics models.

Wang, Yang↗

Detecting gravitational waves from inspiraling binaries with a network of geographically separated detectors: Coherent versus coincident strategies

We compare two strategies of multidetector detection of compact binary inspiral signals, namely, the coincidence and the coherent for the realistic case of geographically separated detectors. The naive coincident strategy treats the detectors as if they are isolated - compares individual detector statistics with their respective thresholds while the coherent strategy combines the detector network data coherently to obtain a single detection statistic which is then compared with a single threshold. We also consider an enhanced coincidence strategy which is intermediate in the sense that though the individual statistics are added in quadrature and the sum compared with a single threshold, the estimated parameters are also checked for consistency. For simplicity, we consider detector pairs having the same power spectral density of noise, as that of initial LIGO and also assume the noise to be stationary and Gaussian. Further, since we consider the detectors to be widely separated on Earth, we take the instrumental noises to be uncorrelated; the wide separation implicitly means that since the detector arms must lie parallel to the Earth's surface, the detectors necessarily have different orientations. We compare the performances of the methods by plotting the receiver operating characteristics for the strategies. Several results are derived analytically in order to gain insight. Simulations are performed in order to plot the receiver operating characteristic (ROC) curves. A single astrophysical source as well as a distribution of sources is considered. We assume a 1 yr data train and a mass range of 1-40M{sub {center_dot}} for the case of astrophysically distributed sources. We find that the coherent strategy is superior to the two coincident strategies that we consider. Remarkably, the detection probability of the coherent strategy is 50% better than the naive coincident strategy. One the other hand, the difference in performance between the coherent strategy and enhanced coincident strategy is not very large. Even in this situation, it is not difficult to perform the real data analysis with the coherent strategy. The bottom line is that the coherent strategy is a good detection strategy.

99 GENERAL AND MISCELLANEOUS↗

NASA Ares I Launch Vehicle First Stage Roll Control System Cold Flow Development Test Program Overview

The Ares I launch vehicle is the selected design, chosen to return humans to the moon, Mars, and beyond. It is configured in two inline stages: the First Stage is a Space Shuttle derived five-segment Solid Rocket Booster and the Upper Stage is powered by a Saturn V derived J-2X engine. During launch, roll control for the First Stage (FS) is handled by a dedicated Roll Control System (RoCS) located on the connecting Interstage. That system will provide the Ares I with the ability to counteract induced roll torque while any induced yaw or pitch moments are handled by vectoring of the booster nozzle. This paper provides an overview of NASA s Ares I FS RoCS cold flow development test program including detailed test objectives, types of tests run to meet those objectives, an overview of the results, and applicable lessons learned. The test article was built and tested at the NASA Marshall Space Flight Center in Huntsville, AL. The FS RoCS System Development Test Article (SDTA) is a full scale, flight representative water flow test article whose primary objective was to obtain fluid system performance data to evaluate integrated system level performance characteristics and verify analytical models. Development testing and model correlation was deemed necessary as there is little historical precedent for similar large flow, pulsing systems such as the FS RoCS. The cold flow development test program consisted of flight-similar tanks, pressure regulators, and thruster valves, as well as plumbing simulating flight geometries, combined with other facility grade components and structure. Orifices downstream of the thruster valves were used to simulate the pressure drop through the thrusters. Additional primary objectives of this test program were to: evaluate system surge pressure (waterhammer) characteristics due to thruster valve operation over a range of mission duty cycles at various feed system pressures, evaluate temperature transients and heat transfer in the pressurization system, including regulator blowdown and propellant ullage performance, measure system pressure drops for comparison to analysis of tubing and components, and validate system activation and re-activation procedures for the helium pressurant system. Secondary objectives included: validating system processes for loading, unloading, and purging, validating procedures and system response for multiple failure scenarios, including relief valve operation, and evaluating system performance for contingency scenarios. The test results of the cold flow development test program are essential in validating the performance and interaction of the Roll Control System and anchoring analysis tools and results to a Critical Design Review level of fidelity.

Butt, Adam↗

New and Improved T-wave Morphology Parameters to Differentiate Healthy Individuals from those with Cardiomyopathy and Coronary Artery Disease

We investigated the ability of several known as well as new ECG repolarization parameters to differentiate healthy individuals from patients with obstructive coronary artery disease (CAD) and cardiomyopathy (CM). Advanced high-fidelity 12-lead ECG tests (approx. 5-min supine) were first performed on a "training set" of 99 individuals: 33 with ischemic or dilated CM and low ejection fraction (EF less than 40%); 33 with catheterization-proven obstructive CAD but normal EF; and 33 age-/gender-matched healthy controls. The following multiple parameters of T-wave morphology (TWM) were derived via signal averaging and singular value decomposition (SVD, which yields 8 eigenvalues, rho(sub 1) greater than rho(sub 2)...greater than rho(sub 8) and studied for their retrospective accuracy in detecting underlying disease: 1) Principal component analysis ratio of the T wave (T-PCA) = 100*rho(sub 2)/rho(sub 1); 2) Relative T-wave residuum (rTWR) = 100* SIGMA (rho(sub 4)(sup 2) +...+ rho(sub 8)(sup 2)); 3) Modified complexity ratio of the T wave (T-mCR) = 100*SIGMA(rho(sub 3)(sup 2) +...+rho(sb 8) (sup 2)); and 4) Normalized 3-dimensional volume of the T wave (nTV) = 100*(rho(sub 2)*rho(sub 3)/rho(sub 1)(sup 2). All TWM parameters significantly differentiated CAD from controls (p less than 0.0001), and also CM from controls (p less than 0.0001). Retrospective areas under the ROC curve were 0.77, 0.81, 0.82, and 0.83 (CAD vs. controls) and 0.93, 0.89, 0.95 and 0.96 (CM vs. controls) for T-PCA, rTWR, T-mCR and nTV respectively. The newer TWM parameters (T-mCR and nTV) thus outperformed the more established parameters (T-PCA and rTWR), presumably by putting a greater emphasis on the third T-wave eigenvalue, which in most healthy subjects has little energy compared to the first two eigenvalues. Subsequent prospective analyses have also yielded similar results, such that we conclude that diagnostic differentiation of pathology from non-pathology may be especially aided by detecting the transference of energy from the first and second T-wave eigenvalues into the third T-wave eigenvalue.

Greco, E. C.↗

NEOWISE-R observation of the coolest known brown dwarf

The Wide-field Infrared Survey Explorer (WISE) spacecraft has been reactivated as NEOWISE-R to characterize and search for near-Earth objects. The brown dwarf WISE J085510.83–071442.5 has now been re-observed by NEOWISE-R, and we confirm the results of Luhman, who found a very low effective temperature (≈250 K), a very high proper motion (8.''1 ± 0.''1 yr{sup –1}), and a large parallax (454 ± 45 mas). The large proper motion has separated the brown dwarf from the background sources that influenced the 2010 WISE data, allowing a measurement of a very red WISE color of W1 – W2 >3.9 mag. A re-analysis of the 2010 WISE astrometry using only the W2 band, combined with the new NEOWISE-R 2014 position, gives an improved parallax of 448 ± 33 mas and a proper motion of 8.''08 ± 0.''05 yr{sup –1}. These are all consistent with values from Luhman.

79 ASTRONOMY AND ASTROPHYSICS↗

A comparison of machine learning methods to classify radioactive elements using prompt-gamma-ray neutron activation data

The detection of illicit radiological materials is critical to establishing a robust second line of defence in nuclear security. Neutron-capture prompt-gamma activation analysis (PGAA) can be used to detect multiple radioactive materials across the entire Periodic Table. However, long detection times and a high rate of false positives pose a significant hindrance in the deployment of PGAA-based systems to identify the presence of illicit substances in nuclear forensics. In the present work, six different machine-learning algorithms were developed to classify radioactive elements based on the PGAA energy spectra. The model performance was evaluated using standard classification metrics and trend curves with an emphasis on comparing the effectiveness of algorithms that are best suited for classifying imbalanced datasets. We analyse the classification performance based on Precision, Recall, F1-score, Specificity, Confusion matrix, ROC-AUC curves, and Geometric Mean Score (GMS) measures. The tree-based algorithms (Decision Trees, Random Forest and AdaBoost) have consistently outperformed Support Vector Machine and K-Nearest Neighbours. Based on the results presented, AdaBoost is the preferred classifier to analyse data containing PGAA spectral information due to the high recall and minimal false negatives reported in the minority class.

97 MATHEMATICS AND COMPUTING↗

WE-G-207-05: Relationship Between CT Image Quality, Segmentation Performance, and Quantitative Image Feature Analysis

Purpose: Segmentation quality can affect quantitative image feature analysis. The objective of this study is to examine the relationship between computed tomography (CT) image quality, segmentation performance, and quantitative image feature analysis. Methods: A total of 90 pathology proven breast lesions in 87 dedicated breast CT images were considered. An iterative image reconstruction (IIR) algorithm was used to obtain CT images with different quality. With different combinations of 4 variables in the algorithm, this study obtained a total of 28 different qualities of CT images. Two imaging tasks/objectives were considered: 1) segmentation and 2) classification of the lesion as benign or malignant. Twenty-three image features were extracted after segmentation using a semi-automated algorithm and 5 of them were selected via a feature selection technique. Logistic regression was trained and tested using leave-one-out-cross-validation and its area under the ROC curve (AUC) was recorded. The standard deviation of a homogeneous portion and the gradient of a parenchymal portion of an example breast were used as an estimate of image noise and sharpness. The DICE coefficient was computed using a radiologist’s drawing on the lesion. Mean DICE and AUC were used as performance metrics for each of the 28 reconstructions. The relationship between segmentation and classification performance under different reconstructions were compared. Distributions (median, 95% confidence interval) of DICE and AUC for each reconstruction were also compared. Results: Moderate correlation (Pearson’s rho = 0.43, p-value = 0.02) between DICE and AUC values was found. However, the variation between DICE and AUC values for each reconstruction increased as the image sharpness increased. There was a combination of IIR parameters that resulted in the best segmentation with the worst classification performance. Conclusion: There are certain images that yield better segmentation or classification performance. The best segmentation Result does not necessarily lead to the best classification Result. This work has been supported in part by grants from the NIH R21-EB015053. R Nishikawa is receives royalties form Hologic, Inc.

60 APPLIED LIFE SCIENCES↗

Predictive analytics of selections of russet potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato (Solanum tuberosum L.) clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013 to 2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a feedforward neural network classifier (Neural Net), a histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conducted a simulation study using the aims, data-generating mechanisms, estimands, methods, and performance measures (ADEMP) framework, simulating different data-generating scenarios to assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression, thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

60 APPLIED LIFE SCIENCES↗

Analysis and prediction of intersection traffic violations using automated enforcement system data

We report that the automated enforcement system (AES) is an effective way of supplementing traditional traffic enforcement, and the traffic violation data from AES can also be effectively used for safety research. In this study, traffic violation data were used to analyze the influencing factors associated with traffic violations and to predict the probability of violations at intersections. The potential factors influencing violations include 24 independent factors related to time, space, traffic and weather. Results from a logistic model showed that the midday period, weekends, residential districts, collector roads, congested traffic conditions, high traffic flow, lower wind speed and low temperature would increase the probability of traffic violations. The probability of violations was predicted by the random forest algorithm, which was proven to be the best traffic violation prediction model among logistic regression, Gaussian naive Bayes, and support vector machine. Moreover, the proximity weighted synthetic oversampling technique (ProWSyn) method was applied to reduce the impact of the imbalance ratio (IR) and improve the model’s prediction performance. The receiver operating characteristics (ROC) curves and Precision-Recall (PR) curves illustrated that the random forest algorithm using oversampling data had the best classifier prediction performance than undersampling data. The area under curve (AUC) and out-of-bag (OOB) error with IR = 1 reached 0.914 and 0.0787, which showed the better performance of the random forest algorithm using ProWSyn in dealing with imbalanced traffic violation data.

42 ENGINEERING↗