A two-dimensional feasibility study of deep learning-based feature detection and characterization directly from CT sinograms.
computed tomography
deep learning
machine learning
sinogram
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Dec 2019
Dec 2019
Historique:
received:
23
10
2018
revised:
27
05
2019
accepted:
27
05
2019
entrez:
8
12
2019
pubmed:
8
12
2019
medline:
15
4
2020
Statut:
ppublish
Résumé
Machine Learning, especially deep learning, has been used in typical x-ray computed tomography (CT) applications, including image reconstruction, image enhancement, image domain feature detection and image domain feature characterization. To our knowledge, this is the first study on machine learning for feature detection and analysis directly based on CT projection data. Specifically, we present neural network methods for blood vessel detection and characterization in the sinogram domain avoiding any partial volume, beam hardening, or motion artifacts introduced during reconstruction. First, we estimate sinogram domain vessel maps using a residual encoder-decoder convolutional neural network (REDCNN). Next, we estimate the vessel centerline and we extract the vessel-only sinogram from the original sinogram, eliminating any background information. Finally, we use a fully connected neural network to estimate the vessel lumen cross-sectional area from the vessel-only sinogram. We trained and tested the proposed methods using CatSim simulations, real CT measurements of vessel phantoms, and clinical data from the NIH CT image database. We achieved encouraging initial results showing the feasibility of CT analysis in the sinogram domain. In principle, sinogram domain analysis should be possible for many other and more complicated clinical CT analysis tasks. Further studies are needed for this sinogram domain analysis approach to become practical for clinical applications.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e790-e800Informations de copyright
© 2019 American Association of Physicists in Medicine.
Références
Wang G. A perspective on deep imaging. IEEE Access. 2016;4:8914-8924.
Wang G, Ye JC, Mueller K, Fessler JA. Image reconstruction is a new frontier of machine learning. IEEE Trans Med Imaging. 2018;37:1289-1296.
Greenspan H, van Ginneken B, Summers RM. Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans Med Imaging. 2016;35:1153-1159.
Park HS, Lee SM, Kim HP, Seo JK, Chung YE. CT sinogram-consistency learning for metal-induced beam hardening correction. Med Phys. 2018;45:5376-5384.
Claus BE, Jin Y, Gjesteby LA, Wang G, De Man B. Metal-artifact reduction using deep-learning based Sinogram completion: Initial results. In: Proceedings of 14th International Meeting Fully Three-Dimensional Image Reconstruction Radiol. Nucl. Med; 2017:631-634.
Lee H, Lee J, Kim H, Cho B, Cho S. (2018). Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction. arXiv preprint arXiv:1803.00694.
Würfl T, Ghesu FC, Christlein V, Maier A. Deep learning computed tomography. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer: 432-440.
Cong W, Wang G. Monochromatic CT Image Reconstruction from Current-Integrating Data via Deep Learning. arXiv preprint arXiv:1710.03784; 2017.
Chen H, Zhang Y, Kalra MK, et al. Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging. 2017;36:2524-2535.
Zhang H, Li L, Qiao K, Wang L, Yan B, Li L, Hu G. Image prediction for limited-angle tomography via deep learning with convolutional neural network. arXiv preprint arXiv:1607.08707; 2016.
Yang H, Yu H, Wang G. Deep learning for the classification of lung nodules. arXiv preprint arXiv:1611.06651; 2016.
Haneda E, Claus B, FitzGerald P, Wang G, De Man B. CT Sinogram Analysis Using Deep Learning. In: Proceedings of 5th International Conference on Image Formation in X-Ray Computed Tomography, Salt Lake City, UT.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: 770-778.
Nair V, Hinton GE. Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on International Conference on Machine Learning: 807-814.
Chollet F. Keras; 2015. https://github.com/fchollet/keras
Abadi M, Barham P, Chen J, et al. TensorFlow: A System for Large-Scale Machine Learning. In: Proceedings of the 12th USENIX symposium on operating systems design and implementation: 265-283.
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics: 249-256.
He K, Zhang X, Ren S, Sun J.Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision: 1026-1034.
Cybenko G. Approximation by superpositions of a sigmoidal function. Math Control Sign Syst. 1989;2:303-314.
Ba J, Caruana R. Do deep nets really need to be deep? In: Advances in neural information processing systems: 2654-2662; 2014.
Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550; 2014.
Fan F, Wang G. Universal Approximation with Quadratic Deep Networks. arXiv preprint arXiv:1808.00098; 2018.
Eldan R, Shamir O. The power of depth for feedforward neural networks. In: Conference on Learning Theory: 907-940; 2016.
Lin HW, Tegmark M, Rolnick D. Why does deep and cheap learning work so well? J Stat Phys. 2017;168:1223-1247.
NIH Clinical Center releases dataset of 32,000 CT images. https://www.nih.gov/news-events/news-releases/nih-clinical-center-releases-dataset-32000-ct-images