{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T04:34:25Z","timestamp":1726806865210},"reference-count":44,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T00:00:00Z","timestamp":1648080000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008307","name":"Promedica Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008307","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["CRSII5 183568"],"award-info":[{"award-number":["CRSII5 183568"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Breast cancer is the most common malignancy in women. Unfortunately, current breast imaging techniques all suffer from certain limitations: they are either not fully three dimensional, have an insufficient resolution or low soft\u2010tissue contrast. Grating interferometry breast computed tomography (GI\u2010BCT) is a promising X\u2010ray phase contrast modality that could overcome these limitations by offering high soft\u2010tissue contrast and excellent three\u2010dimensional resolution. To enable the transition of this technology to clinical practice, dedicated data\u2010processing algorithms must be developed in order to effectively retrieve the signals of interest from the measured raw\u00a0data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This article proposes a novel denoising algorithm that can cope with the high\u2010noise amplitudes and heteroscedasticity which arise in GI\u2010BCT when operated in a low\u2010dose regime to effectively regularize the ill\u2010conditioned GI\u2010BCT inverse problem. We present a data\u2010driven algorithm called INSIDEnet, which combines different ideas such as multiscale image processing, transform\u2010domain filtering, transform learning, and explicit orthogonality to build an Interpretable NonexpanSIve Data\u2010Efficient network (INSIDEnet).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We apply the method to simulated breast phantom datasets and to real data acquired on a GI\u2010BCT prototype and show that the proposed algorithm outperforms traditional state\u2010of\u2010the\u2010art filters and is competitive with deep neural networks. The strong inductive bias given by the proposed model's architecture allows to reliably train the algorithm with very limited data while providing high model interpretability, thus offering a great advantage over classical convolutional neural networks (CNNs).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The proposed INSIDEnet is highly data\u2010efficient, interpretable, and outperforms state\u2010of\u2010the\u2010art CNNs when trained on very limited training data. We expect the proposed method to become an important tool as part of a dedicated plug\u2010and\u2010play GI\u2010BCT reconstruction framework, needed to translate this promising technology to the\u00a0clinics.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15595","type":"journal-article","created":{"date-parts":[[2022,3,8]],"date-time":"2022-03-08T05:48:46Z","timestamp":1646718526000},"page":"3729-3748","update-policy":"http:\/\/dx.doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["INSIDEnet: Interpretable NonexpanSIve Data\u2010Efficient network for denoising in grating interferometry breast CT"],"prefix":"10.1002","volume":"49","author":[{"given":"Stefano","family":"van Gogh","sequence":"first","affiliation":[{"name":"Photon Science Division X\u2010Ray Tomography Group Paul Scherrer Institute Villigen PSI Switzerland"},{"name":"Department for Electrical Engineering and Information Technology X\u2010Ray Tomography Group ETH Z\u00fcrich Z\u00fcrich Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhentian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Engineering Physics Tsinghua University Haidian District Beijing China"},{"name":"Key Laboratory of Particle &amp; Radiation Imaging (Tsinghua University) of Ministry of Education Haidian District Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Micha\u0142","family":"Rawlik","sequence":"additional","affiliation":[{"name":"Photon Science Division X\u2010Ray Tomography Group Paul Scherrer Institute Villigen PSI Switzerland"},{"name":"Department for Electrical Engineering and Information Technology X\u2010Ray Tomography Group ETH Z\u00fcrich Z\u00fcrich Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Etmann","sequence":"additional","affiliation":[{"name":"Cambridge Image Analysis Group Centre for Mathematical Sciences University of Cambridge Cambridge United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhadip","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Cambridge Image Analysis Group Centre for Mathematical Sciences University of Cambridge Cambridge United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carola\u2010Bibiane","family":"Sch\u00f6nlieb","sequence":"additional","affiliation":[{"name":"Cambridge Image Analysis Group Centre for Mathematical Sciences University of Cambridge Cambridge United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Angst","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology University Hospital Z\u00fcrich Z\u00fcrich Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Boss","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology University Hospital Z\u00fcrich Z\u00fcrich Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Stampanoni","sequence":"additional","affiliation":[{"name":"Photon Science Division X\u2010Ray Tomography Group Paul Scherrer Institute Villigen PSI Switzerland"},{"name":"Department for Electrical Engineering and Information Technology X\u2010Ray Tomography Group ETH Z\u00fcrich Z\u00fcrich Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2022,3,24]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)31891-8"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13058-015-0525-z"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-016-4459-3"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1097\/RLI.0000000000000662","article-title":"Lesion detectability and radiation dose in spiral breast CT with photon\u2010counting detector technology: a phantom study","volume":"55","author":"Shim S","year":"2020","journal-title":"Invest Radiol"},{"volume-title":"ACR BI\u2010RADS Atlas, Breast Imaging Reporting and Data System","year":"2013","author":"D'Orsi CJ","key":"e_1_2_9_6_1"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2008.05.006"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.414174"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1107\/S1600577519005502"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1364\/OPEX.13.006296"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4736529"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/7\/020"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901238"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"BuadesA CollB MorelJM.A non\u2010local algorithm for image denoising. In:2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).Piscataway NJ:IEEE Press;2005:Vol.2;60\u201065.","DOI":"10.1109\/CVPR.2005.38"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"LempitskyV VedaldiA UlyanovD.Deep image prior. In:2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.Piscataway NJ:IEEE Press;2018:9446\u20109454.","DOI":"10.1109\/CVPR.2018.00984"},{"key":"e_1_2_9_16_1","unstructured":"LehtinenJ MunkbergJ HasselgremJ et\u00a0al.Noise2Noise: Learning image restoration without clean data. In:35th International Conference on Machine Learning ICML 2018.Red Hook NY:Curran Associates;2018:Vol.80;2965\u20102974."},{"key":"e_1_2_9_17_1","unstructured":"BatsonJ&RoyerLNoise2Self: Blind denoising by self\u2010supervision. In: 36th International Conference on Machine Learning. Red Hook NY Curran Associates; 2019:524\u2010533."},{"key":"e_1_2_9_18_1","unstructured":"AbdelhamedA TimofteR BrownMS et\u00a0al.NTIRE 2019 challenge on real image denoising: methods and results. In:2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Los Alamitos CA:IEEE Computer Society;2019:2197\u20102210."},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2020.3011119"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1146073"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1754212"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.13.001193"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/499\/1\/012006"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/nphys265"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.2772193"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/14786443608649032"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1143\/JJAP.42.L866"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.22.015447"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.2723064"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.3465334"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-06729-4"},{"key":"e_1_2_9_32_1","unstructured":"ReehorstET SchniterP.Regularization by denoising: clarifications and new interpretations.CoRR.2018;abs\/1806.02296."},{"key":"e_1_2_9_33_1","unstructured":"BergerM HubbellJH SeltzerSM et\u00a0al.NIST Standard Reference Database 8 (XGAM).NIST PML Radiation Physics Division;2010."},{"key":"e_1_2_9_34_1","unstructured":"DABAX library.http:\/\/ftp.esrf.eu\/pub\/scisoft\/xop2.3\/DabaxFiles."},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"WhiteDR GriffithRV WilsonIJ.ICRU Report 46.J Int Comm Radiat Units Meas.1992;os24.","DOI":"10.1093\/jicru\/os24.1.Report46"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultramic.2015.05.002"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.2219405"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2226449"},{"key":"e_1_2_9_39_1","unstructured":"TrockmanA KolterJZ.Orthogonalizing convolutional layers with the Cayley transform. Paper presented atNinth International Conference on Learning Representations 2021."},{"key":"e_1_2_9_40_1","doi-asserted-by":"crossref","unstructured":"ChangJR LiC\u2010L P\u00f3czosB Vijaya KumarB SankaranarayananAC.One network to solve them all \u2013 solving linear inverse problems using deep projection models. In:2017 IEEE International Conference on Computer Vision (ICCV).Piscataway NJ:IEEE Press;2017:5889\u20105898.","DOI":"10.1109\/ICCV.2017.627"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2274384"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: Convolutional networks for biomedical image segmentation. In:NavabN HorneggerJ WellsW FrangiA editors.Medical Image Computing and Computer\u2010Assisted Intervention \u2013 MICCAI. Lecture Notes in Computer Science vol9351.Cham Switzerland:Springer;2015;234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23123-0_21"},{"key":"e_1_2_9_44_1","unstructured":"KingmaDP BaJL.Adam: a method for stochastic optimization.Proceedings of the Third International Conference on Learning Representations ICLR 2015 \u2010 Conference Track Proceedings; ICLR 2015 San Diego California.2015:1\u201015."},{"key":"e_1_2_9_45_1","unstructured":"AbadiM BarhamP ChenJ et\u00a0al.TensorFlow: Large\u2010scale machine learning on heterogeneous distributed systems. Software available from tensorflow.org;2015."}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15595","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15595","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T22:11:30Z","timestamp":1726783890000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,24]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10.1002\/mp.15595"],"URL":"https:\/\/doi.org\/10.1002\/mp.15595","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"type":"print","value":"0094-2405"},{"type":"electronic","value":"2473-4209"}],"subject":[],"published":{"date-parts":[[2022,3,24]]},"assertion":[{"value":"2021-08-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-07","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}