Skip to main content

2022 | OriginalPaper | Buchkapitel

Unsupervised Deep Non-rigid Alignment by Low-Rank Loss and Multi-input Attention

verfasst von : Takanori Asanomi, Kazuya Nishimura, Heon Song, Junya Hayashida, Hiroyuki Sekiguchi, Takayuki Yagi, Imari Sato, Ryoma Bise

Erschienen in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2022

Verlag: Springer Nature Switzerland

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We propose a deep low-rank alignment network that can simultaneously perform non-rigid alignment and noise decomposition for multiple images despite severe noise and sparse corruptions. To address this challenging task, we introduce a low-rank loss in deep learning under the assumption that a set of well-aligned, well-denoised images should be linearly correlated, and thus, that a matrix consisting of the images should be low-rank. This allows us to remove the noise and corruption from input images in a self-supervised learning manner (i.e., without requiring supervised data). In addition, we introduce multi-input attention modules into Siamese U-nets in order to aggregate the corruption information from the set of images. To the best of our knowledge, this is the first attempt to introduce a low-rank loss for deep learning-based non-rigid alignment. Experiments using both synthetic data and real medical image data demonstrate the effectiveness of the proposed method. The code will be publicly available in https://​github.​com/​asanomitakanori/​Unsupervised-Deep-Non-Rigid-Alignment-by-Low-Rank-Loss-and-Multi-Input-Attention.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: An unsupervised learning model for deformable medical image registration. In: CVPR, pp. 9252–9260 (2018) Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: An unsupervised learning model for deformable medical image registration. In: CVPR, pp. 9252–9260 (2018)
2.
Zurück zum Zitat Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38(8), 1788–1800 (2019) CrossRef Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38(8), 1788–1800 (2019) CrossRef
3.
6.
Zurück zum Zitat Ding, L., Bawany, M., Kuriyan, A., Ramchandran, R., Wykoff, C., Sharma, G.: Recovery-fa19: Ultra-widefield fluorescein angiography vessel detection dataset. In: IEEE Dataport (2019) Ding, L., Bawany, M., Kuriyan, A., Ramchandran, R., Wykoff, C., Sharma, G.: Recovery-fa19: Ultra-widefield fluorescein angiography vessel detection dataset. In: IEEE Dataport (2019)
8.
Zurück zum Zitat Eppenhof, K.A., Pluim, J.P.: Pulmonary CT registration through supervised learning with convolutional neural networks. IEEE Trans. Med. Imaging 38(5), 1097–1105 (2018) CrossRef Eppenhof, K.A., Pluim, J.P.: Pulmonary CT registration through supervised learning with convolutional neural networks. IEEE Trans. Med. Imaging 38(5), 1097–1105 (2018) CrossRef
9.
Zurück zum Zitat Gao, Y., Zhou, M., Metaxas, D.: UTnet: a hybrid transformer architecture for medical image segmentation. arXiv preprint arXiv:​2107.​00781 (2021) Gao, Y., Zhou, M., Metaxas, D.: UTnet: a hybrid transformer architecture for medical image segmentation. arXiv preprint arXiv:​2107.​00781 (2021)
10.
Zurück zum Zitat Idelbayev, Y., Carreira-Perpinán, M.A.: Low-rank compression of neural nets: learning the rank of each layer. In: CVPR, pp. 8049–8059 (2020) Idelbayev, Y., Carreira-Perpinán, M.A.: Low-rank compression of neural nets: learning the rank of each layer. In: CVPR, pp. 8049–8059 (2020)
12.
Zurück zum Zitat Li, C., Wang, L.V.: Photoacoustic tomography and sensing in biomedicine. Phys. Med. Biol. 54(19), R59 (2009) CrossRef Li, C., Wang, L.V.: Photoacoustic tomography and sensing in biomedicine. Phys. Med. Biol. 54(19), R59 (2009) CrossRef
13.
Zurück zum Zitat Li, H., Fan, Y.: Non-rigid image registration using fully convolutional networks with deep self-supervision. arXiv preprint arXiv:​1709.​00799 (2017) Li, H., Fan, Y.: Non-rigid image registration using fully convolutional networks with deep self-supervision. arXiv preprint arXiv:​1709.​00799 (2017)
15.
Zurück zum Zitat Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS, pp. 8026–8037 (2019) Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS, pp. 8026–8037 (2019)
16.
Zurück zum Zitat Peng, Y., Ganesh, A., Wright, J., Xu, W., Ma, Y.: RASL: robust alignment by sparse and low-rank decomposition for linearly correlated images. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2233–2246 (2012) CrossRef Peng, Y., Ganesh, A., Wright, J., Xu, W., Ma, Y.: RASL: robust alignment by sparse and low-rank decomposition for linearly correlated images. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2233–2246 (2012) CrossRef
17.
Zurück zum Zitat Petit, O., Thome, N., Rambour, C., Soler, L.: U-net transformer: self and cross attention for medical image segmentation. arXiv preprint arXiv:​2103.​06104 (2021) Petit, O., Thome, N., Rambour, C., Soler, L.: U-net transformer: self and cross attention for medical image segmentation. arXiv preprint arXiv:​2103.​06104 (2021)
20.
Zurück zum Zitat Sotiras, A., Davatzikos, C., Paragios, N.: Deformable medical image registration: a survey. IEEE Trans. Med. Imaging 32(7), 1153–1190 (2013) CrossRef Sotiras, A., Davatzikos, C., Paragios, N.: Deformable medical image registration: a survey. IEEE Trans. Med. Imaging 32(7), 1153–1190 (2013) CrossRef
22.
Zurück zum Zitat Treeby, B.E., Cox, B.T.: k-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields. J. Biomed. Optics 15(2), 1–12 (2010) CrossRef Treeby, B.E., Cox, B.T.: k-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields. J. Biomed. Optics 15(2), 1–12 (2010) CrossRef
24.
Zurück zum Zitat de Vos, B.D., Berendsen, F.F., Viergever, M.A., Sokooti, H., Staring, M., Išgum, I.: A deep learning framework for unsupervised affine and deformable image registration. Med. Image Anal. 52, 128–143 (2019) CrossRef de Vos, B.D., Berendsen, F.F., Viergever, M.A., Sokooti, H., Staring, M., Išgum, I.: A deep learning framework for unsupervised affine and deformable image registration. Med. Image Anal. 52, 128–143 (2019) CrossRef
26.
Zurück zum Zitat Wu, Y., Shen, B., Ling, H.: Online robust image alignment via iterative convex optimization. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1808–1814. IEEE (2012) Wu, Y., Shen, B., Ling, H.: Online robust image alignment via iterative convex optimization. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1808–1814. IEEE (2012)
27.
Zurück zum Zitat Yu, X., Liu, T., Wang, X., Tao, D.: On compressing deep models by low rank and sparse decomposition. In: CVPR, pp. 7370–7379 (2017) Yu, X., Liu, T., Wang, X., Tao, D.: On compressing deep models by low rank and sparse decomposition. In: CVPR, pp. 7370–7379 (2017)
28.
Zurück zum Zitat Zhao, S., et al.: Recursive cascaded networks for unsupervised medical image registration. In: ICCV, pp. 10600–10610 (2019) Zhao, S., et al.: Recursive cascaded networks for unsupervised medical image registration. In: ICCV, pp. 10600–10610 (2019)
Metadaten
Titel
Unsupervised Deep Non-rigid Alignment by Low-Rank Loss and Multi-input Attention
verfasst von
Takanori Asanomi
Kazuya Nishimura
Heon Song
Junya Hayashida
Hiroyuki Sekiguchi
Takayuki Yagi
Imari Sato
Ryoma Bise
Copyright-Jahr
2022
DOI
https://doi.org/10.1007/978-3-031-16446-0_18