Emergence and distinction of classes in XRD data via machine learning

Royse, Camen; Wolter, Scott D.; Greenberg, Joel A.

doi:10.1117/12.2519500

Cited by 3 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We considered both rule‐based and ML‐based approaches for performing classification on the measured XRD spectra. While rule‐based approaches can take advantage of previously known differences (in the form of a database of XRD spectra that can be used for matched filtering 48 or simple unmixing approaches 49 ), ML approaches have the capability to learn additional relevant features 50–52 . Each XRD spectrum in this study is composed of 43 intensity values sampled from a q range of 0.09–0.3 Å –1 , providing a sufficient number of features for the ML training process.…”

Section: Methodsmentioning

confidence: 99%

Application of machine learning classifiers to X‐ray diffraction imaging with medically relevant phantoms

2021

Self Cite

View full text Add to dashboard Cite

Recent studies have demonstrated the ability to rapidly produce large field of view X-ray diffraction (XRD) images, which provide rich new data relevant to the understanding and analysis of disease. However, work has only just begun on developing algorithms that maximize the performance toward decision-making and diagnostic tasks. In this study, we present the implementation of and comparison between rules-based and machine learning (ML) classifiers on XRD images of medically relevant phantoms to explore the potential for increased classification performance. Methods: Medically relevant phantoms were utilized to provide wellcharacterized ground-truths for comparing classifier performance. Water and polylactic acid (PLA) plastic were used as surrogates for cancerous and healthy tissue, respectively, and phantoms were created with varying levels of spatial complexity and biologically relevant features for quantitative testing of classifier performance. Our previously developed X-ray scanner was used to acquire co-registered X-ray transmission and diffraction images of the phantoms. For classification algorithms, we explored and compared two rules-based classifiers (cross-correlation, or matched-filter, and linear least-squares unmixing) and two ML classifiers (support vector machines and shallow neural networks). Reference XRD spectra (measured by a commercial diffractometer) were provided to the rules-based algorithms, while 60% of the measured XRD pixels were used for training of the ML algorithms. The area under the receiver operating characteristic curve (AUC) was used as a comparative metric between the classification algorithms, along with the accuracy performance at the midpoint threshold for each classifier. Results:The AUC values for material classification were 0.994 (crosscorrelation [CC]), 0.994 (least-squares [LS]), 0.995 (support vector machine [SVM]), and 0.999 (shallow neural network [SNN]). Setting the classification threshold to the midpoint for each classifier resulted in accuracy values of CC = 96.48%, LS = 96.48%, SVM = 97.36%, and SNN = 98.94%. If only considering pixels ±3 mm from water-PLA boundaries (where partial volume effects could occur due to imaging resolution limits), the classification accuracies were CC = 89.32%, LS = 89.32%, SVM = 92.03%, and SNN = 96.79%, demonstrating an even larger improvement produced by the machine-learned algorithms in spatial regions critical for imaging tasks. Classification by transmission data alone produced an AUC of 0.773 and accuracy of 85.45%, well below the performance levels of any of the classifiers applied to XRD image data. Conclusions: We demonstrated that ML-based classifiers outperformed rulesbased approaches in terms of overall classification accuracy and improved the spatially resolved classification performance on XRD images of medical phantoms. In particular, the ML algorithms demonstrated considerably improved 532

show abstract

Section: Methodsmentioning

confidence: 99%

Application of machine learning classifiers to X‐ray diffraction imaging with medically relevant phantoms

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…This can then be used to produce a material-specific XRD form factor that can be used for identification. This additional information can prove incredibly useful when attempting to classify materials [1,6].…”

Section: Orthogonality and Physicsmentioning

confidence: 99%

Performance of a high-throughput full-tunnel XRD checked baggage scanning system

Coccarelli¹,

Dudley²,

Pike³

et al. 2023

Anomaly Detection and Imaging With X-Rays (ADIX) VIII

View full text Add to dashboard Cite

X-ray diffraction imaging (XRDI) offers the potential for reduced false alarm rates, increased throughputs, and more sensitive explosives detection performance in aviation security applications. The deployment of computed tomography (CT) systems across carry-on and checked baggage screening lanes has both reinforced the need for orthogonal detection technologies and created an exciting new opportunity for the implementation of XRDI. Our team at Quadridox built a novel XRDI system that, when combined with a CT system, realizes full-tunnel assessment of checked bags at a belt speed of 20 cm/s. We integrated our XRDI system with a Smiths CTX 5800 explosives detection system (EDS) and collected bag data containing both benign and threat objects. We describe the XRDI system, show examples of the resulting hybrid CT and XRD dataset, and present performance results for the hybrid system.

show abstract

“…PES visualisation can be viewed as a data science task in which we would like to project a high-dimensional source data-set (consisting of vectors describing structures in the configuration space of interest) into one, two or three Euclidean dimensions. We base our approach on state-of-the-art algorithms for dimensionality reduction for visualisation, such as t-Distributed Stochastic Neighbour Embedding (t-SNE) [28] and Uniform Manifold Approximation and Projection (UMAP) [29,30], drawing inspiration from their increasing application to data-sets arising in physics [31][32][33], materials science [34,35], and cell biology [36][37][38][39]. We call this approach SHEAP -Stochastic Hyperspace Embedding And Projection.…”

Section: Introductionmentioning

confidence: 99%

Visualising energy landscapes through manifold learning

Shires,

Pickard

2021

Preprint

View full text Add to dashboard Cite

Energy landscapes provide a conceptual framework for structure prediction, and a detailed understanding of their topological features is necessary to develop efficient methods for their exploration. The ability to visualise these surfaces is essential, but the high dimensionality of the corresponding configuration spaces makes this difficult. Here we present Stochastic Hyperspace Embedding and Projection (SHEAP), a method for energy landscape visualisation inspired by state-of-theart algorithms for dimensionality reduction through manifold learning, such as t-SNE and UMAP. The performance of SHEAP is demonstrated through its application to the energy landscapes of Lennard-Jones clusters, solid-state carbon, and the quaternary system C+H+N+O. It produces meaningful and interpretable low-dimensional representations of these landscapes, reproducing well known topological features such as funnels, and providing fresh insight into their layouts. In particular, an intrinsic low dimensionality in the distribution of local minima across configuration space is revealed.

show abstract

Emergence and distinction of classes in XRD data via machine learning

Cited by 3 publications

References 6 publications

Application of machine learning classifiers to X‐ray diffraction imaging with medically relevant phantoms

Application of machine learning classifiers to X‐ray diffraction imaging with medically relevant phantoms

Performance of a high-throughput full-tunnel XRD checked baggage scanning system

Visualising energy landscapes through manifold learning

Contact Info

Product

Resources

About