Detecting anomalies in X-ray diffraction images using convolutional neural networks. (15th July 2021)

• Record Type: Journal Article
• Authors: Czyzewski, Adam; Krawiec, Faustyna; Brzezinski, Dariusz; Porebski, Przemyslaw Jerzy; Minor, Wladek
• Is Part Of: Expert systems with applications. Volume 174(2021)
• Publication Date: 2021-07-15
• Subjects: X-ray diffraction image -- Multi-label classification -- Convolutional neural network -- Image recognition -- Crystallography; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.114740
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: End-to-end anomaly detection system for X-ray diffraction images. Beam center detection algorithm. Comparison of three alternative image representation approaches. Open multi-label classification dataset of 6, 311 diffraction images. Abstract: Our understanding of life is based upon the interpretation of macromolecular structures and their dynamics. Almost 90% of currently known macromolecular models originated from electron density maps constructed using X-ray diffraction images. Even though diffraction images are critical for structure determination, due to their vast amounts and noisy, non-intuitive nature, their quality is rarely inspected. In this paper, we use recent advances in machine learning to automatically detect seven types of anomalies in X-ray diffraction images. For this purpose, we utilize a novel X-ray beam center detection algorithm, propose three different image representations, and compare the predictive performance of general-purpose classifiers and deep convolutional neural networks (CNNs). In benchmark tests on a set of 6, 311 X-ray diffraction images, the proposed CNN achieved between 87% and 99% accuracy depending on the type of anomaly. Experimental results show that the proposed anomaly detection system can be considered suitable for early detection of sub-optimal data collection conditions and malfunctions at X-ray experimental stations.