Abstract
Motion artifacts detection is essential for computed tomography (CT) imaging, and it can be concerned as a binary classification problem where images with artifacts are positive samples and images without artifacts are negative samples. However, there are two main challenges for this problem: (a) how to extract features of motion artifacts from CT images, and (b) with limited labeled data, how to ensure high sensitivity and generality of the training model. To address these challenges, we first develop a preprocessing procedure, the Motion Artifacts Enhancement Method (MAEM), to extract features effectively. Subsequently, a Motion Artifacts Detection Algorithm based on Convolutional Neural Network (MADA-CNN) is presented to construct the classification model. Performance is evaluated by the area under the receiver operation characteristics curve (AUC). Compared with traditional preprocessing method on single classifier, the MAEM shows the AUC of 0.9570 (improved +1.96%) and sensitivity of 92.66% (improved +3.59%). To validate the generality of the proposed method, the ensemble model shows the AUC of 0.9665 and sensitivity of 94.50%. Experimental results have demonstrated the effectiveness and generality of our method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Larson, D.B., Johnson, L.W., Schnell, B.M., et al.: National trends in CT use in the emergency department. Radiology 258(1), 164–173 (2011)
Boas, F.E., Fleischmann, D.: CT artifacts: causes and reduction techniques. Imaging Med. 4(2), 229–240 (2012)
Sara, U., Akter, M., Uddin, M.S., Fleischmann, D.: Image quality assessment through FSIM, SSIM, MSE and PSNRA comparative study. J. Comput. Commun. 7(3), 8–18 (2019)
Lee, J.G., Jun, S., Cho, Y.W., et al.: Deep learning in medical imaging: general overview. Korean J. Radiol. 18(4), 570–584 (2017)
Haskins, G., Kruger, U., Yan, P.: Deep learning in medical image registration: a survey. Mach. Vision Appl. 31(1), 1–18 (2020). https://doi.org/10.1007/s00138-020-01060-x
Stoeve, M., et al.: Motion artifact detection in confocal laser endomicroscopy images. Bildverarbeitung für die Medizin 2018. I, pp. 328–333. Springer, Heidelberg (2018). https://doi.org/10.1007/978-3-662-56537-7_85
Wei, L., Rosen, B., Vallires, M., et al.: Automatic recognition and analysis of metal streak artifacts in head and neck computed tomography for radiomics modeling. Phys. Imaging Radiat. Oncol. 10, 49–54 (2019)
Welch, M.L., McIntosh, C., Purdie, T.G., et al.: Automatic classification of dental artifact status for efficient image veracity checks: effects of image resolution and convolutional neural network depth. Phys. Med. Biol. 65(1), 015005 (2020)
Armanious, K., Jiang, C., Fischer, M., et al.: MedGAN: medical image translation using GANs. Comput. Med. Imaging Graph. 79, 101684 (2020)
Lossau, T., Nickisch, H., Wissel, T., et al.: Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks. Med. Image Anal. 52, 68–79 (2019)
Prakash, P., Dutta, S.: Deep learning-based artifact detection for diagnostic CT images. In: Medical Imaging 2019: Physics of Medical Imaging, pp. 109484C. International Society for Optics and Photonics (2019)
Zhang, Z., Zhu, Q., et al.: Discriminative margin-sensitive autoencoder for collective multi-view disease analysis. Neural Netw. 123, 94–107 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, X. et al. (2020). Motion Artifacts Detection from Computed Tomography Images. In: Yang, X., Wang, CD., Islam, M.S., Zhang, Z. (eds) Advanced Data Mining and Applications. ADMA 2020. Lecture Notes in Computer Science(), vol 12447. Springer, Cham. https://doi.org/10.1007/978-3-030-65390-3_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-65390-3_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65389-7
Online ISBN: 978-3-030-65390-3
eBook Packages: Computer ScienceComputer Science (R0)