{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:59:06Z","timestamp":1778003946827,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,9,13]],"date-time":"2019-09-13T00:00:00Z","timestamp":1568332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,9,13]],"date-time":"2019-09-13T00:00:00Z","timestamp":1568332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005877","name":"Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta","doi-asserted-by":"publisher","award":["312123"],"award-info":[{"award-number":["312123"]}],"id":[{"id":"10.13039\/501100005877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000274","name":"British Heart Foundation","doi-asserted-by":"publisher","award":["NH\/18\/1\/33511"],"award-info":[{"award-number":["NH\/18\/1\/33511"]}],"id":[{"id":"10.13039\/501100000274","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/M020533\/1"],"award-info":[{"award-number":["EP\/M020533\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["WT1019572"],"award-info":[{"award-number":["WT1019572"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Math Imaging Vis"],"published-print":{"date-parts":[[2020,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n<jats:p>A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for applications where it is not apparent that convolutions are suited to capture the underlying physics. In this work, we develop a network architecture based on nonlinear diffusion processes, named <jats:italic>DiffNet<\/jats:italic>. By design, we obtain a nonlinear network architecture that is well suited for diffusion-related problems in imaging. Furthermore, the performed updates are explicit, by which we obtain better interpretability and generalisability compared to classical convolutional neural network architectures. The performance of DiffNet is tested on the inverse problem of nonlinear diffusion with the Perona\u2013Malik filter on the STL-10 image dataset. We obtain competitive results to the established U-Net architecture, with a fraction of parameters and necessary training data.<\/jats:p>","DOI":"10.1007\/s10851-019-00901-3","type":"journal-article","created":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T08:41:03Z","timestamp":1568709663000},"page":"471-487","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Networks for Nonlinear Diffusion Problems in Imaging"],"prefix":"10.1007","volume":"62","author":[{"given":"S.","family":"Arridge","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3756-8121","authenticated-orcid":false,"given":"A.","family":"Hauptmann","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,13]]},"reference":[{"key":"901_CR1","unstructured":"Abadi, M., et\u00a0al.: TensorFlow: large-scale machine learning on heterogeneous systems. Software available from \nhttps:\/\/www.tensorflow.org\/\n\n (2015)"},{"issue":"12","key":"901_CR2","doi-asserted-by":"publisher","first-page":"124007","DOI":"10.1088\/1361-6420\/aa9581","volume":"33","author":"J Adler","year":"2017","unstructured":"Adler, J., \u00d6ktem, O.: Solving ill-posed inverse problems using iterative deep neural networks. Inverse Prob. 33(12), 124007 (2017)","journal-title":"Inverse Prob."},{"key":"901_CR3","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1080\/17415977.2018.1518444","volume":"27","author":"S Antholzer","year":"2019","unstructured":"Antholzer, S., Haltmeier, M., Schwab, J.: Deep learning for photoacoustic tomography from sparse data. Inverse Probl. Sci. Eng. 27, 987\u20131005 (2019)","journal-title":"Inverse Probl. Sci. Eng."},{"key":"901_CR4","unstructured":"Bergerhoff, L., C\u00e1rdenas, M., Weickert, J., Welk, M.: Stable backward diffusion models that minimise convex energies. ArXiv preprint \narXiv:1903.03491\n\n (2019)"},{"key":"901_CR5","doi-asserted-by":"publisher","first-page":"034013","DOI":"10.1088\/0266-5611\/24\/3\/034013","volume":"24","author":"D Calvetti","year":"2008","unstructured":"Calvetti, D., Somersalo, E.: Hypermodels in the Bayesian imaging framework. Inverse Probl. 24, 034013 (2008)","journal-title":"Inverse Probl."},{"key":"901_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5261\u20135269 (2015)","DOI":"10.1109\/CVPR.2015.7299163"},{"key":"901_CR7","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223 (2011)"},{"issue":"18","key":"901_CR8","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1364\/OL.30.002439","volume":"30","author":"A Douiri","year":"2005","unstructured":"Douiri, A., Schweiger, M., Riley, J., Arridge, S.: Local diffusion regularization method for optical tomography reconstruction by using robust statistics. Opt. Lett. 30(18), 2439\u20132441 (2005)","journal-title":"Opt. Lett."},{"issue":"1","key":"901_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/TIP.2013.2277775","volume":"23","author":"MJ Ehrhardt","year":"2013","unstructured":"Ehrhardt, M.J., Arridge, S.R.: Vector-valued image processing by parallel level sets. IEEE Trans. Image Process. 23(1), 9\u201318 (2013)","journal-title":"IEEE Trans. Image Process."},{"key":"901_CR10","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press. \nhttp:\/\/www.deeplearningbook.org\n\n (2016)"},{"issue":"1","key":"901_CR11","doi-asserted-by":"publisher","first-page":"014004","DOI":"10.1088\/1361-6420\/aa9a90","volume":"34","author":"E Haber","year":"2017","unstructured":"Haber, E., Ruthotto, L.: Stable architectures for deep neural networks. Inverse Probl. 34(1), 014004 (2017)","journal-title":"Inverse Probl."},{"key":"901_CR12","doi-asserted-by":"publisher","first-page":"2367","DOI":"10.1109\/TMI.2018.2828303","volume":"37","author":"SJ Hamilton","year":"2018","unstructured":"Hamilton, S.J., Hauptmann, A.: Deep d-bar: real time electrical impedance tomography imaging with deep neural networks. IEEE Trans. Med. Imaging 37, 2367\u20132377 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"4","key":"901_CR13","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.3934\/ipi.2014.8.1053","volume":"8","author":"SJ Hamilton","year":"2014","unstructured":"Hamilton, S.J., Hauptmann, A., Siltanen, S.: A data-driven edge-preserving D-bar method for electrical impedance tomography. Inverse Probl. Imaging 8(4), 1053\u20131072 (2014)","journal-title":"Inverse Probl. Imaging"},{"issue":"6","key":"901_CR14","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1002\/mrm.26977","volume":"79","author":"K Hammernik","year":"2018","unstructured":"Hammernik, K., Klatzer, T., Kobler, E., Recht, M.P., Sodickson, D.K., Pock, T., Knoll, F.: Learning a variational network for reconstruction of accelerated MRI data. Magn. Reson. Med. 79(6), 3055\u20133071 (2018)","journal-title":"Magn. Reson. Med."},{"issue":"1","key":"901_CR15","doi-asserted-by":"publisher","first-page":"015008","DOI":"10.1088\/0266-5611\/32\/1\/015008","volume":"32","author":"A Hannukainen","year":"2015","unstructured":"Hannukainen, A., Harhanen, L., Hyv\u00f6nen, N., Majander, H.: Edge-promoting reconstruction of absorption and diffusivity in optical tomography. Inverse Probl. 32(1), 015008 (2015)","journal-title":"Inverse Probl."},{"key":"901_CR16","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1002\/mrm.27480","volume":"81","author":"A Hauptmann","year":"2019","unstructured":"Hauptmann, A., Arridge, S., Lucka, F., Muthurangu, V., Steeden, J.: Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease. Magn. Reson. Med. 81, 1143\u20131156 (2019)","journal-title":"Magn. Reson. Med."},{"issue":"6","key":"901_CR17","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1109\/TMI.2018.2820382","volume":"37","author":"A Hauptmann","year":"2018","unstructured":"Hauptmann, A., Lucka, F., Betcke, M., Huynh, N., Adler, J., Cox, B., Beard, P., Ourselin, S., Arridge, S.: Model-based learning for accelerated, limited-view 3-d photoacoustic tomography. IEEE Trans. Med. Imaging 37(6), 1382\u20131393 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"901_CR18","doi-asserted-by":"crossref","unstructured":"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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"901_CR19","doi-asserted-by":"publisher","first-page":"015008","DOI":"10.1088\/0266-5611\/27\/1\/015008","volume":"27","author":"T Helin","year":"2010","unstructured":"Helin, T., Lassas, M.: Hierarchical models in statistical inverse problems and the Mumford\u2013Shah functional. Inverse Probl. 27(1), 015008 (2010)","journal-title":"Inverse Probl."},{"key":"901_CR20","unstructured":"Hofer, C., Kwitt, R., Niethammer, M., Uhl, A.: Deep learning with topological signatures. In: Advances in Neural Information Processing Systems, pp. 1634\u20131644 (2017)"},{"issue":"9","key":"901_CR21","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","volume":"26","author":"KH Jin","year":"2017","unstructured":"Jin, K.H., McCann, M.T., Froustey, E., Unser, M.: Deep convolutional neural network for inverse problems in imaging. IEEE Trans. Image Process. 26(9), 4509\u20134522 (2017)","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"901_CR22","doi-asserted-by":"publisher","first-page":"e360","DOI":"10.1002\/mp.12344","volume":"44","author":"E Kang","year":"2017","unstructured":"Kang, E., Min, J., Ye, J.C.: A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Med. Phys. 44(10), e360\u2013e375 (2017)","journal-title":"Med. Phys."},{"key":"901_CR23","unstructured":"Khoo, Y., Lu, J., Ying, L.: Solving parametric PDE problems with artificial neural networks. \narxiv:1707.03351v2\n\n (2017)"},{"key":"901_CR24","unstructured":"Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., et\u00a0al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (tcav). In: International Conference on Machine Learning, pp. 2673\u20132682 (2018)"},{"key":"901_CR25","volume-title":"Numerical Geometry of Images: Theory, Algorithms, and Applications","author":"R Kimmel","year":"2003","unstructured":"Kimmel, R.: Numerical Geometry of Images: Theory, Algorithms, and Applications. Springer, Berlin (2003)"},{"key":"901_CR26","doi-asserted-by":"crossref","unstructured":"Liu, R., Lin, Z., Zhang, W., Su, Z.: Learning pdes for image restoration via optimal control. In: European Conference on Computer Vision, pp. 115\u2013128. Springer (2010)","DOI":"10.1007\/978-3-642-15549-9_9"},{"key":"901_CR27","doi-asserted-by":"crossref","unstructured":"Long, Z., Lu, Y., Dong, B.: Pde-net 2.0: learning pdes from data with a numeric-symbolic hybrid deep network. ArXiv preprint \narXiv:1812.04426\n\n (2018)","DOI":"10.1016\/j.jcp.2019.108925"},{"key":"901_CR28","unstructured":"Long, Z., Lu, Y., Ma, X., Dong, B.: Pde-net: Learning pdes from data. In: Proceedings of the 35th International Conference on Machine Learning (ICML 2018) (2018)"},{"key":"901_CR29","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Moeller, M., Hazirbad, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: International Conference on Computer Vision, pp. 1781\u20131790 (2017)","DOI":"10.1109\/ICCV.2017.198"},{"issue":"7","key":"901_CR30","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/34.56205","volume":"12","author":"P Perona","year":"1990","unstructured":"Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629\u2013639 (1990)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"901_CR31","unstructured":"Raissi, M., Karniadakis, G.E.: Hidden physics models: machine learning of nonlinear partial differential equations. \narxiv:1708.00588v2\n\n (2017)"},{"key":"901_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"901_CR33","unstructured":"Ruthotto, L., Haber, E.: Deep neural networks motivated by partial differential equations. ArXiv preprint \narXiv:1804.04272\n\n (2018)"},{"key":"901_CR34","volume-title":"Geometric Partial Differential Equations and Image Analysis","author":"G Sapiro","year":"2006","unstructured":"Sapiro, G.: Geometric Partial Differential Equations and Image Analysis. Cambridge University Press, Cambridge (2006)"},{"key":"901_CR35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019","volume-title":"Understanding Machine Learning: From Theory to Algorithms","author":"S Shalev-Shwartz","year":"2014","unstructured":"Shalev-Shwartz, S., Ben-David, S.: Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, Cambridge (2014)"},{"key":"901_CR36","unstructured":"Sirignano, J., Spiliopoulos, K.: DGM: A deep learning algorithm for solving partial differential equations. \narxiv:1708.07469v1\n\n (2017)"},{"key":"901_CR37","unstructured":"Tompson, J., Schlachter, K., Sprechmann, P., Perlin, K.: Accelerating Eulerian fluid simulation with convolutional networks. \narxiv:1607.03597v6\n\n (2017)"},{"key":"901_CR38","volume-title":"Anisotropic Diffusion in Image Processing","author":"J Weickert","year":"1998","unstructured":"Weickert, J.: Anisotropic Diffusion in Image Processing. Teubner, Stuttgart (1998)"},{"issue":"3","key":"901_CR39","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/83.661190","volume":"7","author":"J Weickert","year":"1998","unstructured":"Weickert, J., Romeny, B.T.H., Viergever, M.A.: Efficient and reliable schemes for nonlinear diffusion filtering. IEEE Trans. Image Process. 7(3), 398\u2013410 (1998)","journal-title":"IEEE Trans. Image Process."},{"key":"901_CR40","unstructured":"Weinan, E., Jiequn, H., Arnulf, J.: Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. \narxiv:1706.04702v1\n\n (2017)"},{"key":"901_CR41","unstructured":"Wu, Y., Zhang, P., Shen, H., , Zhai, H.: Visualizing neural network developing perturbation theory. \narxiv:1802.03930v2\n\n (2018)"},{"key":"901_CR42","unstructured":"Xu, L., Ren, J.S., Liu, C., Jia, J.: Deep convolutional neural network for image deconvolution. In: Advances in Neural Information Processing Systems, pp. 1790\u20131798 (2014)"},{"issue":"2","key":"901_CR43","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1137\/17M1141771","volume":"11","author":"JC Ye","year":"2018","unstructured":"Ye, J.C., Han, Y., Cha, E.: Deep convolutional framelets: a general deep learning framework for inverse problems. SIAM J. Imaging Sci. 11(2), 991\u20131048 (2018)","journal-title":"SIAM J. Imaging Sci."},{"key":"901_CR44","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/nature25988","volume":"555","author":"B Zhu","year":"2018","unstructured":"Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555, 487\u2013489 (2018)","journal-title":"Nature"}],"container-title":["Journal of Mathematical Imaging and Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-019-00901-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10851-019-00901-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-019-00901-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,11]],"date-time":"2020-09-11T23:26:27Z","timestamp":1599866787000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10851-019-00901-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,13]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["901"],"URL":"https:\/\/doi.org\/10.1007\/s10851-019-00901-3","relation":{},"ISSN":["0924-9907","1573-7683"],"issn-type":[{"value":"0924-9907","type":"print"},{"value":"1573-7683","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,13]]},"assertion":[{"value":"29 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}