Stefan Stryker1, Anuj J Kapadia1,2, Joel A Greenberg1,3. 1. Medical Physics Graduate Program, Duke University, Durham, North Carolina, USA. 2. Carl E. Ravin Advanced Imaging Laboratories, Department of Radiology, Duke University, Durham, North Carolina, USA. 3. Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina, USA.
Abstract
PURPOSE: 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 well-characterized 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 (cross-correlation [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 rules-based 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 performance whenever multiple materials existed in a single voxel. The quantitative performance gains demonstrate an avenue to extract and harness XRD imaging data to improve material analysis for research, industrial, and clinical applications.
PURPOSE: 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 well-characterized 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 (cross-correlation [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 rules-based 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 performance whenever multiple materials existed in a single voxel. The quantitative performance gains demonstrate an avenue to extract and harness XRD imaging data to improve material analysis for research, industrial, and clinical applications.