Dynamic Volume Reconstruction from Multi-slice Abdominal MRI Using Manifold Alignment

详细信息    查看全文

• 关键词：Manifold alignment ; Respiratory motion estimation ; MRI ; Dynamic 3D volume reconstruction
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9902
• 期：1
• 页码：493-501
• 全文大小：1,724 KB
• 参考文献：1.Lustig, M., Donoho, D., Pauly, J.: Sparse MRI: the application of compressed sensing for rapid MR imaging. Mag. Res. Med. 58(6), 1182–1195 (2007)CrossRef
  2.Larson, A., White, R., Laub, G., McVeigh, E., Li, D., Simonetti, O.: Self-gated cardiac cine MRI. Mag. Res. Img. 51(1), 93–102 (2004)
  3.Baumgartner, C.F., Gomez, A., Koch, L.M., Housden, J.R., Kolbitsch, C., McClelland, J.R., Rueckert, D., King, A.P.: Self-aligning manifolds for matching disparate medical image datasets. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M. (eds.) IPMI 2015. LNCS, vol. 9123, pp. 363–374. Springer, Heidelberg (2015)CrossRef
  4.Baumgartner, C., Kolbitsch, C., Balfour, D., Marsden, P., McClelland, J., Rueckert, D., King, A.: High-resolution dynamic MR imaging of the thorax for respiratory motion correction of PET using groupwise manifold alignment. Med. Img. Anal. 18, 939–952 (2014)CrossRef
  5.Bhatia, K.K., Caballero, J., Price, A.N., Sun, Y., Hajnal, J.V., Rueckert, D.: Fast reconstruction of accelerated dynamic MRI using manifold kernel regression. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 510–518. Springer, Heidelberg (2015). doi:10.​1007/​978-3-319-24574-4_​61 CrossRef
  6.Usman, M., Atkinson, D., Kolbitsch, C., Schaeffter, T., Prieto, C.: Manifold learning based ECG-Free free
  eathing cardiac CINE MRI. Mag. Res. Img. 41, 1521–1527 (2015)CrossRef
  7.Usman, M., Vaillant, G., Atkinson, D., Schaeffter, T., Prieto, C.: Compressive manifold learning: estimating one-dimensional respiratory motion directly from undersampled k-space data. Mag. Res. Med. 72, 1130–1140 (2014)CrossRef
  8.Winkelmann, S., Schaeffter, T., Koehler, T., Eggers, H., Doessel, O.: An optimal radial profile order based on the golden ratio for time-resolved MRI. IEEE Trans. Med. Img. 26(1), 68–76 (2007)CrossRef
  9.Greengard, L., Lee, J.-Y.: Accelerating the nonuniform fast fourier transform. SIAM Rev. 46(3), 443–454 (2006)MathSciNet CrossRef MATH
  10.Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRef
  11.Rueckert, D., Sonoda, L., Hayes, C., Hill, D., Leach, M., Hawkes, D.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Img. 18(8), 712–721 (1999)CrossRef
  
• 作者单位：Xin Chen (18)
  Muhammad Usman (18)
  Daniel R. Balfour (18)
  Paul K. Marsden (18)
  Andrew J. Reader (18)
  Claudia Prieto (18)
  Andrew P. King (18)
  
  18. Division of Imaging Sciences and Biomedical Engineering, King’s College London, London, UK
  
• 丛书名：Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2016
• ISBN：978-3-319-46726-9
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9902

文摘

We present a novel framework for retrospective dynamic 3D volume reconstruction from a multi-slice MRI acquisition using manifold alignment. K-space data are continuously acquired under free breathing using a radial golden-angle trajectory in a slice-by-slice manner. Non-overlapping consecutive profiles that were acquired within a short time window are grouped together. All grouped profiles from all slices are then simultaneously embedded using manifold alignment into a common manifold space (MS), in which profiles that were acquired at similar respiratory states are close together. Subsequently, a 3D volume can be reconstructed at each of the grouped profile MS positions by combining profiles that are close in the MS. This enables the original multi-slice dataset to be used to reconstruct a dynamic 3D sequence based on the respiratory state correspondences established in the MS. Our method was evaluated on both synthetic and in vivo datasets. For the synthetic datasets, the reconstructed dynamic sequence achieved a normalised cross correlation of 0.98 and peak signal to noise ratio of 26.64 dB compared with the ground truth. For the in vivo datasets, based on sharpness measurements and visual comparison, our method performed better than reconstruction using an adapted central k-space gating method.