{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T23:43:25Z","timestamp":1775691805127,"version":"3.50.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T00:00:00Z","timestamp":1679616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T00:00:00Z","timestamp":1679616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["WT203148\/Z\/16\/Z"],"award-info":[{"award-number":["WT203148\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["NS\/A000049\/1"],"award-info":[{"award-number":["NS\/A000049\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["No 101016985"],"award-info":[{"award-number":["No 101016985"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["NIHR202114"],"award-info":[{"award-number":["NIHR202114"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>Hyperspectral imaging has the potential to improve intraoperative decision making if tissue characterisation is performed in real-time and with high-resolution. Hyperspectral snapshot mosaic sensors offer a promising approach due to their fast acquisition speed and compact size. However, a demosaicking algorithm is required to fully recover the spatial and spectral information of the snapshot images. Most state-of-the-art demosaicking algorithms require ground-truth training data with paired snapshot and high-resolution hyperspectral images, but such imagery pairs with the exact same scene are physically impossible to acquire in intraoperative settings. In this work, we present a fully unsupervised hyperspectral image demosaicking algorithm which only requires exemplar snapshot images for training purposes.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We regard hyperspectral demosaicking as an ill-posed linear inverse problem which we solve using a deep neural network. We take advantage of the spectral correlation occurring in natural scenes to design a novel inter spectral band regularisation term based on spatial gradient consistency. By combining our proposed term with standard regularisation techniques and exploiting a standard data fidelity term, we obtain an unsupervised loss function for training deep neural networks, which allows us to achieve real-time hyperspectral image demosaicking.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Quantitative results on hyperspetral image datasets show that our unsupervised demosaicking approach can achieve similar performance to its supervised counter-part, and significantly outperform linear demosaicking. A qualitative user study on real snapshot hyperspectral surgical images confirms the results from the quantitative analysis.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Our results suggest that the proposed unsupervised algorithm can achieve promising hyperspectral demosaicking in real-time thus advancing the suitability of the modality for intraoperative use.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-023-02865-7","type":"journal-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T07:02:56Z","timestamp":1679641376000},"page":"981-988","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Spatial gradient consistency for unsupervised learning of hyperspectral demosaicking: application to surgical imaging"],"prefix":"10.1007","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3344-0294","authenticated-orcid":false,"given":"Peichao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Asad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Conor","family":"Horgan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"MacCormac","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Shapey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Vercauteren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,24]]},"reference":[{"issue":"1","key":"2865_CR1","doi-asserted-by":"publisher","first-page":"010901","DOI":"10.1117\/1.JBO.19.1.010901","volume":"19","author":"G Lu","year":"2014","unstructured":"Lu G, Fei B (2014) Medical hyperspectral imaging: a review. J Biomed Opt 19(1):010901","journal-title":"J Biomed Opt"},{"issue":"9","key":"2865_CR2","doi-asserted-by":"publisher","first-page":"201800455","DOI":"10.1002\/jbio.201800455","volume":"12","author":"J Shapey","year":"2019","unstructured":"Shapey J, Xie Y, Nabavi E, Bradford R, Saeed SR, Ourselin S, Vercauteren T (2019) Intraoperative multispectral and hyperspectral label-free imaging: A systematic review of in vivo clinical studies. J Biophotonics 12(9):201800455","journal-title":"J Biophotonics"},{"key":"2865_CR3","doi-asserted-by":"publisher","first-page":"101699","DOI":"10.1016\/j.media.2020.101699","volume":"63","author":"NT Clancy","year":"2020","unstructured":"Clancy NT, Jones G, Maier-Hein L, Elson DS, Stoyanov D (2020) Surgical spectral imaging. Med Image Anal 63:101699","journal-title":"Med Image Anal"},{"issue":"5","key":"2865_CR4","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1515\/bmt-2017-0155","volume":"63","author":"A Holmer","year":"2018","unstructured":"Holmer A, Marotz J, Wahl P, Dau M, K\u00e4mmerer PW (2018) Hyperspectral imaging in perfusion and wound diagnostics - methods and algorithms for the determination of tissue parameters. Biomed Eng Biomed Tech 63(5):547\u2013556. https:\/\/doi.org\/10.1515\/bmt-2017-0155","journal-title":"Biomed Eng Biomed Tech"},{"issue":"4","key":"2865_CR5","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1080\/21681163.2021.1997646","volume":"10","author":"P Li","year":"2022","unstructured":"Li P, Ebner M, Noonan P, Horgan C, Bahl A, Ourselin S, Shapey J, Vercauteren T (2022) Deep learning approach for hyperspectral image demosaicking, spectral correction and high-resolution RGB reconstruction. Comput Methods Biomech Biomed Eng Imaging Vis 10(4):409\u2013417. https:\/\/doi.org\/10.1080\/21681163.2021.1997646","journal-title":"Comput Methods Biomech Biomed Eng Imaging Vis"},{"key":"2865_CR6","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1049\/ip-vis:20050281","volume":"153","author":"W Yu","year":"2006","unstructured":"Yu W (2006) Colour demosaicking method using adaptive cubic convolution interpolation with sequential averaging. Vis Image Signal Process 153:666\u2013676. https:\/\/doi.org\/10.1049\/ip-vis:20050281","journal-title":"Vis Image Signal Process"},{"issue":"9","key":"2865_CR7","doi-asserted-by":"publisher","first-page":"1924","DOI":"10.1109\/TGRS.2004.830644","volume":"42","author":"MT Eismann","year":"2004","unstructured":"Eismann MT, Hardie RC (2004) Application of the stochastic mixing model to hyperspectral resolution enhancement. IEEE Trans Geosci Remote Sens 42(9):1924\u20131933. https:\/\/doi.org\/10.1109\/TGRS.2004.830644","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2865_CR8","first-page":"184","volume-title":"ECCV 2014","author":"C Dong","year":"2014","unstructured":"Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) ECCV 2014. Springer, Cham, pp 184\u2013199"},{"key":"2865_CR9","doi-asserted-by":"publisher","unstructured":"Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: CVPR Workshops 2017, pp. 1132\u20131140. https:\/\/doi.org\/10.1109\/CVPRW.2017.151","DOI":"10.1109\/CVPRW.2017.151"},{"key":"2865_CR10","unstructured":"Zhang Y, Li K, Li K, Zhong B, Fu Y (2019) Residual non-local attention networks for image restoration. In: ICLR 2019. OpenReview"},{"key":"2865_CR11","doi-asserted-by":"publisher","DOI":"10.3390\/rs9111139","author":"S Mei","year":"2017","unstructured":"Mei S, Yuan X, Ji J, Zhang Y, Wan S, Du Q (2017) Hyperspectral image spatial super-resolution via 3d full convolutional neural network. Remote Sens. https:\/\/doi.org\/10.3390\/rs9111139","journal-title":"Remote Sens"},{"issue":"1","key":"2865_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-018-0965-4","volume":"30","author":"K Dijkstra","year":"2019","unstructured":"Dijkstra K, van de Loosdrecht J, Schomaker L, Wiering MA (2019) Hyperspectral demosaicking and crosstalk correction using deep learning. Mach Vis Appl 30(1):1\u201321","journal-title":"Mach Vis Appl"},{"key":"2865_CR13","doi-asserted-by":"publisher","unstructured":"Arad B, Timofte R, Yahel R, Morag N, Bernat A, Wu Y, Wu X, Fan Z, Xia C, Zhang F, Liu S, Li Y, Feng C, Lei L, Zhang M, Feng K, Zhang X, Yao J, Zhao Y, Ma S, He F, Dong Y, Yu S, Qiu D, Liu J, Bi M, Song B, Sun W, Zheng J, Zhao B, Cao Y, Yang J, Cao Y, Kong X, Yu J, Xue Y, Xie Z (2022) NTIRE 2022 spectral demosaicing challenge and data set. In: 2022 IEEE\/CVF CVPR Workshops, pp. 881\u2013895. https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00103","DOI":"10.1109\/CVPRW56347.2022.00103"},{"key":"2865_CR14","first-page":"191","volume-title":"ECCV 2020","author":"B Niu","year":"2020","unstructured":"Niu B, Wen W, Ren W, Zhang X, Yang L, Wang S, Zhang K, Cao X, Shen H (2020) Single image super-resolution via a holistic attention network. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) ECCV 2020. Springer, Cham, pp 191\u2013207"},{"issue":"13","key":"2865_CR15","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.37188\/OPE.2021.0433","volume":"30","author":"B Song","year":"2022","unstructured":"Song B, Ma S, He F, Sun W (2022) Hyperspectral reconstruction from RGB images based on Res2-Unet deep learning network. Opt Precis Eng 30(13):1606","journal-title":"Opt Precis Eng"},{"key":"2865_CR16","doi-asserted-by":"publisher","first-page":"39098","DOI":"10.1109\/ACCESS.2019.2904788","volume":"7","author":"H Fabelo","year":"2019","unstructured":"Fabelo H, Ortega S, Szolna A, Bulters D, Pi\u00f1eiro JF, Kabwama S, Ohanahan A, Bulstrode H, Bisshopp S, Kiran BR, Ravi D, Lazcano R, Madro\u00f1al D, Sosa C, Espino C, Marquez M, De La Luz Plaza M, Camacho R, Carrera D, Hern\u00e1ndez M, Callic\u00f3 GM, Morera Molina J, Stanciulescu B, Yang G-Z, Salvador R, Ju\u00e1rez E, Sanz C, Sarmiento R (2019) In-vivo hyperspectral human brain image database for brain cancer detection. IEEE Access 7:39098\u201339116. https:\/\/doi.org\/10.1109\/ACCESS.2019.2904788","journal-title":"IEEE Access"},{"key":"2865_CR17","doi-asserted-by":"publisher","DOI":"10.3390\/app10207246","author":"J Hyttinen","year":"2020","unstructured":"Hyttinen J, F\u00e4lt P, J\u00e4sberg H, Kullaa A, Hauta-Kasari M (2020) Oral and dental spectral image database-odsi-db. Appl Sci. https:\/\/doi.org\/10.3390\/app10207246","journal-title":"Appl Sci"},{"issue":"29","key":"2865_CR18","doi-asserted-by":"publisher","first-page":"294003","DOI":"10.1088\/1361-6463\/abfbf6","volume":"54","author":"M Ebner","year":"2021","unstructured":"Ebner M, Nabavi E, Shapey J, Xie Y, Liebmann F, Spirig JM, Hoch A, Farshad M, Saeed SR, Bradford R, Yardley I, Ourselin S, Edwards AD, F\u00fchrnstahl P, Vercauteren T (2021) Intraoperative hyperspectral label-free imaging: from system design to first-in-patient translation. J Phys D Appl Phys 54(29):294003. https:\/\/doi.org\/10.1088\/1361-6463\/abfbf6","journal-title":"J Phys D Appl Phys"},{"issue":"9","key":"2865_CR19","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1109\/TIP.2002.801121","volume":"11","author":"BK Gunturk","year":"2002","unstructured":"Gunturk BK, Altunbasak Y, Mersereau RM (2002) Color plane interpolation using alternating projections. IEEE Trans Image Process 11(9):997\u20131013. https:\/\/doi.org\/10.1109\/TIP.2002.801121","journal-title":"IEEE Trans Image Process"},{"key":"2865_CR20","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1007\/11866763_89","volume-title":"Medical image computing and computer-assisted intervention - MICCAI 2006","author":"E Haber","year":"2006","unstructured":"Haber E, Modersitzki J (2006) Intensity gradient based registration and fusion of multi-modal images. In: Larsen R, Nielsen M, Sporring J (eds) Medical image computing and computer-assisted intervention - MICCAI 2006. Springer, Berlin, Heidelberg, pp 726\u2013733"},{"key":"2865_CR21","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: MICCAI 2015, pp. 234\u2013241. Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2865_CR22","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/0034-4257(93)90013-N","volume":"44","author":"FA Kruse","year":"1993","unstructured":"Kruse FA, Lefkoff AB, Boardman JW, Heidebrecht KB, Shapiro A, Barloon PJ, Goetz AFH (1993) The spectral image processing system (sips) interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ 44:145\u2013163","journal-title":"Remote Sens Environ"},{"issue":"8","key":"2865_CR23","doi-asserted-by":"publisher","first-page":"2478","DOI":"10.1111\/j.1467-8659.2012.03188.x","volume":"31","author":"RK Mantiuk","year":"2012","unstructured":"Mantiuk RK, Tomaszewska A, Mantiuk R (2012) Comparison of four subjective methods for image quality assessment. Comput Gr Forum 31(8):2478\u20132491. https:\/\/doi.org\/10.1111\/j.1467-8659.2012.03188.x","journal-title":"Comput Gr Forum"},{"key":"2865_CR24","first-page":"324","volume":"39","author":"RA Bradley","year":"1952","unstructured":"Bradley RA, Terry ME (1952) Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika 39:324\u2013345","journal-title":"Biometrika"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02865-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-023-02865-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02865-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T14:40:07Z","timestamp":1687358407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-023-02865-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,24]]},"references-count":24,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["2865"],"URL":"https:\/\/doi.org\/10.1007\/s11548-023-02865-7","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,24]]},"assertion":[{"value":"9 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"TV is supported by a Medtronic \/ RAEng Research Chair [RCSRF1819\\7\\34]. PL is funded by China Scholarship Council. CH is supported by an InnovateUK Secondment Scholars Grant (Project Number 75124). TV and JS are co-founders and shareholders of Hypervision Surgical.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All procedures within this study involving human subjects were in accordance with both the institutional and regional ethical committee (REC reference 22\/LO\/0046, IRAS 284230) and with the 1964 Helsinki Declaration and its later amendments.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The authors affirm that human research participants provided informed consent for publication of the images in Fig.\u00a0.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Informed consent was obtained from all individual participants involved in the study.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}