Skip to main content

2020 | OriginalPaper | Buchkapitel

Self-supervised Denoising via Diffeomorphic Template Estimation: Application to Optical Coherence Tomography

verfasst von : Guillaume Gisbert, Neel Dey, Hiroshi Ishikawa, Joel Schuman, James Fishbaugh, Guido Gerig

Erschienen in: Ophthalmic Medical Image Analysis

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

Optical Coherence Tomography (OCT) is pervasive in both the research and clinical practice of Ophthalmology. However, OCT images are strongly corrupted by noise, limiting their interpretation. Current OCT denoisers leverage assumptions on noise distributions or generate targets for training deep supervised denoisers via averaging of repeat acquisitions. However, recent self-supervised advances allow the training of deep denoising networks using only repeat acquisitions without clean targets as ground truth, reducing the burden of supervised learning. Despite the clear advantages of self-supervised methods, their use is precluded as OCT shows strong structural deformations even between sequential scans of the same subject due to involuntary eye motion. Further, direct nonlinear alignment of repeats induces correlation of the noise between images. In this paper, we propose a joint diffeomorphic template estimation and denoising framework which enables the use of self-supervised denoising for motion deformed repeat acquisitions, without empirically registering their noise realizations. Strong qualitative and quantitative improvements are achieved in denoising OCT images, with generic utility in any imaging modality amenable to multiple exposures.

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!

Fußnoten
4
For [18], Algorithm 1 in the paper suggests that lower is better. However, their code negates the final correlation value, thus making higher better. We do the same to maintain consistency with their convention.
 
Literatur
1.
Zurück zum Zitat Avants, B., Gee, J.C.: Geodesic estimation for large deformation anatomical shape averaging and interpolation. Neuroimage 23, S139–S150 (2004)CrossRef Avants, B., Gee, J.C.: Geodesic estimation for large deformation anatomical shape averaging and interpolation. Neuroimage 23, S139–S150 (2004)CrossRef
2.
Zurück zum Zitat Avants, B.B., et al.: The optimal template effect in hippocampus studies of diseased populations. Neuroimage 49(3), 2457–2466 (2010)CrossRef Avants, B.B., et al.: The optimal template effect in hippocampus studies of diseased populations. Neuroimage 49(3), 2457–2466 (2010)CrossRef
3.
Zurück zum Zitat Bashkirova, D., Usman, B., Saenko, K.: Adversarial self-defense for cycle-consistent GANs. In: Advances in Neural Information Processing Systems, pp. 637–647 (2019) Bashkirova, D., Usman, B., Saenko, K.: Adversarial self-defense for cycle-consistent GANs. In: Advances in Neural Information Processing Systems, pp. 637–647 (2019)
4.
Zurück zum Zitat Batson, J., Royer, L.: Noise2self: blind denoising by self-supervision. In: International Conference on Machine Learning, pp. 524–533 (2019) Batson, J., Royer, L.: Noise2self: blind denoising by self-supervision. In: International Conference on Machine Learning, pp. 524–533 (2019)
5.
Zurück zum Zitat Broaddus, C., Krull, A., Weigert, M., Schmidt, U., Myers, G.: Removing structured noise with self-supervised blind-spot networks. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 159–163. IEEE (2020) Broaddus, C., Krull, A., Weigert, M., Schmidt, U., Myers, G.: Removing structured noise with self-supervised blind-spot networks. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 159–163. IEEE (2020)
6.
Zurück zum Zitat Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 2, pp. 60–65. IEEE (2005) Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 2, pp. 60–65. IEEE (2005)
7.
Zurück zum Zitat Buchholz, T.O., Jordan, M., Pigino, G., Jug, F.: Cryo-CARE: content-aware image restoration for cryo-transmission electron microscopy data. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 502–506. IEEE (2019) Buchholz, T.O., Jordan, M., Pigino, G., Jug, F.: Cryo-CARE: content-aware image restoration for cryo-transmission electron microscopy data. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 502–506. IEEE (2019)
9.
Zurück zum Zitat Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)MathSciNetCrossRef Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)MathSciNetCrossRef
10.
Zurück zum Zitat Devalla, S.K., et al.: A deep learning approach to denoise optical coherence tomography images of the optic nerve head. Sci. Rep. 9(1), 1–13 (2019)CrossRef Devalla, S.K., et al.: A deep learning approach to denoise optical coherence tomography images of the optic nerve head. Sci. Rep. 9(1), 1–13 (2019)CrossRef
11.
Zurück zum Zitat Dey, N., Messinger, J., Smith, R.T., Curcio, C.A., Gerig, G.: Robust non-negative tensor factorization, diffeomorphic motion correction, and functional statistics to understand fixation in fluorescence microscopy. In: Shen, D., et al. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Lecture Notes in Computer Science, vol. 11764, pp. 658–666. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_73CrossRef Dey, N., Messinger, J., Smith, R.T., Curcio, C.A., Gerig, G.: Robust non-negative tensor factorization, diffeomorphic motion correction, and functional statistics to understand fixation in fluorescence microscopy. In: Shen, D., et al. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Lecture Notes in Computer Science, vol. 11764, pp. 658–666. Springer, Cham (2019). https://​doi.​org/​10.​1007/​978-3-030-32239-7_​73CrossRef
12.
Zurück zum Zitat Gisbert, G., Dey, N., Ishikawa, H., Schuman, J., Fishbaugh, J., Gerig, G.: Improved denoising of optical coherence tomography via repeated acquisitions and unsupervised deep learning. Invest. Ophthalmol. Vis. Sci. 61(9), PB0035 (2020) Gisbert, G., Dey, N., Ishikawa, H., Schuman, J., Fishbaugh, J., Gerig, G.: Improved denoising of optical coherence tomography via repeated acquisitions and unsupervised deep learning. Invest. Ophthalmol. Vis. Sci. 61(9), PB0035 (2020)
13.
Zurück zum Zitat Halupka, K.J., et al.: Retinal optical coherence tomography image enhancement via deep learning. Biomed. Opt. Exp. 9(12), 6205–6221 (2018)CrossRef Halupka, K.J., et al.: Retinal optical coherence tomography image enhancement via deep learning. Biomed. Opt. Exp. 9(12), 6205–6221 (2018)CrossRef
14.
Zurück zum Zitat Hendriksen, A.A., Pelt, D.M., Batenburg, K.J.: Noise2inverse: self-supervised deep convolutional denoising for linear inverse problems in imaging. arXiv preprint arXiv:2001.11801 (2020) Hendriksen, A.A., Pelt, D.M., Batenburg, K.J.: Noise2inverse: self-supervised deep convolutional denoising for linear inverse problems in imaging. arXiv preprint arXiv:​2001.​11801 (2020)
15.
Zurück zum Zitat Joshi, S., Davis, B., Jomier, M., Gerig, G.: Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage 23, S151–S160 (2004)CrossRef Joshi, S., Davis, B., Jomier, M., Gerig, G.: Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage 23, S151–S160 (2004)CrossRef
16.
Zurück zum Zitat Kafieh, R., Rabbani, H., Selesnick, I.: Three dimensional data-driven multi scale atomic representation of optical coherence tomography. IEEE Trans. Med. Imaging 34(5), 1042–1062 (2014)CrossRef Kafieh, R., Rabbani, H., Selesnick, I.: Three dimensional data-driven multi scale atomic representation of optical coherence tomography. IEEE Trans. Med. Imaging 34(5), 1042–1062 (2014)CrossRef
18.
Zurück zum Zitat Kong, X., Li, K., Yang, Q., Wenyin, L., Yang, M.H.: A new image quality metric for image auto-denoising. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2888–2895 (2013) Kong, X., Li, K., Yang, Q., Wenyin, L., Yang, M.H.: A new image quality metric for image auto-denoising. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2888–2895 (2013)
19.
Zurück zum Zitat Krull, A., Buchholz, T.O., Jug, F.: Noise2void-learning denoising from single noisy images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2129–2137 (2019) Krull, A., Buchholz, T.O., Jug, F.: Noise2void-learning denoising from single noisy images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2129–2137 (2019)
20.
Zurück zum Zitat Laine, S., Karras, T., Lehtinen, J., Aila, T.: High-quality self-supervised deep image denoising. In: Advances in Neural Information Processing Systems, pp. 6970–6980 (2019) Laine, S., Karras, T., Lehtinen, J., Aila, T.: High-quality self-supervised deep image denoising. In: Advances in Neural Information Processing Systems, pp. 6970–6980 (2019)
21.
Zurück zum Zitat Lehtinen, J., et al.: Noise2Noise: learning image restoration without clean data. In: ICML, pp. 2971–2980 (2018) Lehtinen, J., et al.: Noise2Noise: learning image restoration without clean data. In: ICML, pp. 2971–2980 (2018)
22.
Zurück zum Zitat Maggioni, M., Katkovnik, V., Egiazarian, K., Foi, A.: Nonlocal transform-domain filter for volumetric data denoising and reconstruction. IEEE Trans. Image Process. 22(1), 119–133 (2012)MathSciNetCrossRef Maggioni, M., Katkovnik, V., Egiazarian, K., Foi, A.: Nonlocal transform-domain filter for volumetric data denoising and reconstruction. IEEE Trans. Image Process. 22(1), 119–133 (2012)MathSciNetCrossRef
23.
Zurück zum Zitat Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21(12), 4695–4708 (2012)MathSciNetCrossRef Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21(12), 4695–4708 (2012)MathSciNetCrossRef
24.
Zurück zum Zitat Qiu, B., et al.: Noise reduction in optical coherence tomography images using a deep neural network with perceptually-sensitive loss function. Biomed. Opt. Exp. 11(2), 817–830 (2020)CrossRef Qiu, B., et al.: Noise reduction in optical coherence tomography images using a deep neural network with perceptually-sensitive loss function. Biomed. Opt. Exp. 11(2), 817–830 (2020)CrossRef
25.
Zurück zum Zitat Ravier, M., et al.: Analysis of morphological changes of lamina cribrosa under acute intraocular pressure change. In: Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) Medical Image Computing and Computer Assisted Intervention – ICCAI 2018. Lecture Notes in Computer Science, vol. 11071, pp. 364–371. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_41CrossRef Ravier, M., et al.: Analysis of morphological changes of lamina cribrosa under acute intraocular pressure change. In: Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) Medical Image Computing and Computer Assisted Intervention – ICCAI 2018. Lecture Notes in Computer Science, vol. 11071, pp. 364–371. Springer, Cham (2018). https://​doi.​org/​10.​1007/​978-3-030-00934-2_​41CrossRef
26.
Zurück zum Zitat Romo-Bucheli, D., et al.: Reducing image variability across OCT devices with unsupervised unpaired learning for improved segmentation of retina. Biomed. Opt. Exp. 11(1), 346–363 (2020)CrossRef Romo-Bucheli, D., et al.: Reducing image variability across OCT devices with unsupervised unpaired learning for improved segmentation of retina. Biomed. Opt. Exp. 11(1), 346–363 (2020)CrossRef
27.
Zurück zum Zitat Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Lecture Notes in Computer Science, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28CrossRef Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Lecture Notes in Computer Science, vol. 9351, pp. 234–241. Springer, Cham (2015). https://​doi.​org/​10.​1007/​978-3-319-24574-4_​28CrossRef
28.
Zurück zum Zitat Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRef Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRef
29.
Zurück zum Zitat Zhang, Y., et al.: A poisson-gaussian denoising dataset with real fluorescence microscopy images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11710–11718 (2019) Zhang, Y., et al.: A poisson-gaussian denoising dataset with real fluorescence microscopy images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11710–11718 (2019)
30.
Zurück zum Zitat Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017) Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
31.
Zurück zum Zitat Zhu, X., Milanfar, P.: Automatic parameter selection for denoising algorithms using a no-reference measure of image content. IEEE Trans. Image Process. 19(12), 3116–3132 (2010)MathSciNetCrossRef Zhu, X., Milanfar, P.: Automatic parameter selection for denoising algorithms using a no-reference measure of image content. IEEE Trans. Image Process. 19(12), 3116–3132 (2010)MathSciNetCrossRef
Metadaten
Titel
Self-supervised Denoising via Diffeomorphic Template Estimation: Application to Optical Coherence Tomography
verfasst von
Guillaume Gisbert
Neel Dey
Hiroshi Ishikawa
Joel Schuman
James Fishbaugh
Guido Gerig
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-63419-3_8