{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T19:02:45Z","timestamp":1771614165260,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T00:00:00Z","timestamp":1635811200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T00:00:00Z","timestamp":1635811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11042-021-11699-x","type":"journal-article","created":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T03:02:27Z","timestamp":1635822147000},"page":"2603-2620","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Optimizing a medical image registration algorithm based on profiling data for real-time performance"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5000-497X","authenticated-orcid":false,"given":"Carlos A. S. J.","family":"Gulo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4337-514X","authenticated-orcid":false,"given":"Antonio C.","family":"Sementille","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7603-6526","authenticated-orcid":false,"given":"Jo\u00e3o Manuel R. S.","family":"Tavares","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,2]]},"reference":[{"issue":"4","key":"11699_CR1","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1145\/183432.183527","volume":"16","author":"T Ball","year":"1994","unstructured":"Ball T, Larus JR (1994) Optimally profiling and tracing programs. ACM Transactions on Programming Languages and Systems 16(4):1319\u20131360. https:\/\/doi.org\/10.1145\/183432.183527","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"11699_CR2","doi-asserted-by":"publisher","unstructured":"Bezemer CP, Pouwelse J, Gregg B (2015) Understanding software performance regressions using differential flame graphs. In: 22nd International conference on software analysis, evolution, and reengineering (SANER), pp 535\u2013539 https:\/\/doi.org\/10.1109\/SANER.2015.7081872","DOI":"10.1109\/SANER.2015.7081872"},{"key":"11699_CR3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.neuroimage.2016.12.064","volume":"148","author":"A Carass","year":"2017","unstructured":"Carass A, Roy S, Jog A, Cuzzocreo JL, Magrath E, Gherman A, Button J et al (2017) Longitudinal multiple sclerosis lesion segmentation: Resource and challenge. NeuroImage 148:77\u2013102. https:\/\/doi.org\/10.1016\/j.neuroimage.2016.12.064","journal-title":"NeuroImage"},{"key":"11699_CR4","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1016\/S0167-8191(98)00062-3","volume":"24","author":"GE Christensen","year":"1998","unstructured":"Christensen GE (1998) MIMD vs. SIMD parallel processing: A case study in 3D medical image registration. Parallel Computing 24:1369\u20131383. https:\/\/doi.org\/10.1016\/S0167-8191(98)00062-3","journal-title":"Parallel Computing"},{"issue":"2","key":"11699_CR5","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TBCAS.2007.909023","volume":"1","author":"O Dandekar","year":"2007","unstructured":"Dandekar O, Shekhar R (2007) FPGA-accelerated deformable image registration for improved target-delineation during CT-guided interventions. IEEE Transactions on Biomedical Circuits and Systems 1(2):116\u2013127. https:\/\/doi.org\/10.1109\/TBCAS.2007.909023","journal-title":"IEEE Transactions on Biomedical Circuits and Systems"},{"key":"11699_CR6","doi-asserted-by":"crossref","unstructured":"Dimakopoulou M, Eranian S, Koziris N, Bambos N (2016) Reliable and efficient performance monitoring in Linux. In: Proceedings of the international conference for high performance computing, networking, storage and analysis, IEEE Press, pp 1\u201313","DOI":"10.1109\/SC.2016.33"},{"issue":"8","key":"11699_CR7","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1016\/j.media.2013.05.008","volume":"17","author":"A Eklund","year":"2013","unstructured":"Eklund A, Dufort P, Forsberg D, LaConte SM (2013) Medical image processing on the GPU - past, present and future. Medical Image Analysis 17(8):1073\u20131094. https:\/\/doi.org\/10.1016\/j.media.2013.05.008","journal-title":"Medical Image Analysis"},{"issue":"1","key":"11699_CR8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.eij.2015.09.002","volume":"17","author":"FEZA El-Gamal","year":"2016","unstructured":"El-Gamal FEZA, Elmogy M, Atwan A (2016) Current trends in medical image registration and fusion. Egyptian Informatics Journal 17(1):99\u2013124. https:\/\/doi.org\/10.1016\/j.eij.2015.09.002","journal-title":"Egyptian Informatics Journal"},{"key":"11699_CR9","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.cmpb.2015.12.018","volume":"127","author":"ND Ellingwood","year":"2016","unstructured":"Ellingwood ND, Yin Y, Smith M, Lin CL (2016) Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs. Computer Methods and Programs in Biomedicine 127:290\u2013300. https:\/\/doi.org\/10.1016\/j.cmpb.2015.12.018","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"11699_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/9780470932025","volume-title":"Algorithms and parallel computing","author":"F Gebali","year":"2011","unstructured":"Gebali F (2011) Algorithms and parallel computing. John Wiley & Sons, New York. https:\/\/doi.org\/10.1002\/9780470932025"},{"issue":"3","key":"11699_CR11","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1055\/s-0038-1627043","volume":"51","author":"L Gong","year":"2012","unstructured":"Gong L, Kulikowski CA (2012) High-performance medical imaging informatics. Methods of Information in Medicine 51(3):258\u2013259","journal-title":"Methods of Information in Medicine"},{"issue":"4","key":"11699_CR12","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/989393.989401","volume":"39","author":"SL Graham","year":"2004","unstructured":"Graham SL, Kessler PB, McKusick MK (2004) gprof: A call graph execution profiler. ACM SIGPLAN Notes 39(4):49\u201357. https:\/\/doi.org\/10.1145\/989393.989401","journal-title":"ACM SIGPLAN Notes"},{"issue":"2","key":"11699_CR13","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1145\/2927299.2927301","volume":"14","author":"B Gregg","year":"2016","unstructured":"Gregg B (2016) The flame graph: This visualization of software execution is a new necessity for performance profiling and debugging. ACM Queue Magazine 14(2):91\u2013110. https:\/\/doi.org\/10.1145\/2927299.2927301","journal-title":"ACM Queue Magazine"},{"issue":"7","key":"11699_CR14","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MC.2008.209","volume":"41","author":"MD Hill","year":"2008","unstructured":"Hill MD, Marty MR (2008) Amdahl\u2019s law in the multicore era. Computer 41(7):33\u201338. https:\/\/doi.org\/10.1109\/MC.2008.209","journal-title":"Computer"},{"key":"11699_CR15","volume-title":"Programming massively parallel processors: A hands-on approach","author":"D Kirk","year":"2010","unstructured":"Kirk D, Hwu WM (2010) Programming massively parallel processors: A hands-on approach. Elsevier, Amsterdam"},{"issue":"2","key":"11699_CR16","doi-asserted-by":"publisher","first-page":"162","DOI":"10.2307\/2685881","volume":"37","author":"JB Kruskal","year":"1983","unstructured":"Kruskal JB, Landwehr JM (1983) Icicle plots: Better displays for hierarchical clustering. The American Statistician 37(2):162\u2013168. https:\/\/doi.org\/10.2307\/2685881","journal-title":"The American Statistician"},{"issue":"1","key":"11699_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compbiomed.2009.10.002","volume":"40","author":"RJ Lapeer","year":"2010","unstructured":"Lapeer RJ, Shah SK, Rowland RS (2010) An optimised radial basis function algorithm for fast non-rigid registration of medical images. Computers in Biology and Medicine 40(1):1\u20137. https:\/\/doi.org\/10.1016\/j.compbiomed.2009.10.002","journal-title":"Computers in Biology and Medicine"},{"issue":"8","key":"11699_CR18","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1016\/j.micpro.2015.04.002","volume":"39","author":"A Li","year":"2015","unstructured":"Li A, Kumar A, Ha Y, Corporaal H (2015) Correlation ratio based volume image registration on GPUs. Microprocessors and Microsystems 39(8):998\u20131011. https:\/\/doi.org\/10.1016\/j.micpro.2015.04.002","journal-title":"Microprocessors and Microsystems"},{"key":"11699_CR19","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.jss.2016.03.045","volume":"117","author":"Z Li","year":"2016","unstructured":"Li Z, Atre R, Huda Z, Jannesari A, Wolf F (2016) Unveiling parallelization opportunities in sequential programs. Journal of Systems and Software 117:282\u2013295. https:\/\/doi.org\/10.1016\/j.jss.2016.03.045","journal-title":"Journal of Systems and Software"},{"issue":"3","key":"11699_CR20","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1002\/cnm.2607","volume":"30","author":"R Mafi","year":"2014","unstructured":"Mafi R, Sirouspour S (2014) GPU-based acceleration of computations in nonlinear finite element deformation analysis. International Journal for Numerical Methods in Biomedical Engineering 30(3):365\u2013381. https:\/\/doi.org\/10.1002\/cnm.2607","journal-title":"International Journal for Numerical Methods in Biomedical Engineering"},{"issue":"2","key":"11699_CR21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/S1361-8415(96)80007-7","volume":"1","author":"T McInerney","year":"1996","unstructured":"McInerney T, Terzopoulos D (1996) Deformable models in medical image analysis: a survey. Medical Image Analysis 1(2):91\u2013108. https:\/\/doi.org\/10.1016\/S1361-8415(96)80007-7","journal-title":"Medical Image Analysis"},{"issue":"1","key":"11699_CR22","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.3233\/BME-130910","volume":"24","author":"L Meng","year":"2014","unstructured":"Meng L (2014) Acceleration method of 3D medical images registration based on compute unified device architecture. Bio-Medical Materials and Engineering 24(1):1109\u20131116. https:\/\/doi.org\/10.3233\/BME-130910","journal-title":"Bio-Medical Materials and Engineering"},{"issue":"4","key":"11699_CR23","doi-asserted-by":"publisher","first-page":"69:1","DOI":"10.1145\/2788396","volume":"47","author":"S Mittal","year":"2015","unstructured":"Mittal S, Vetter JS (2015) A survey of CPU-GPU heterogeneous computing techniques. ACM Computing Surveys 47(4):69:1-69:35. https:\/\/doi.org\/10.1145\/2788396","journal-title":"ACM Computing Surveys"},{"issue":"3","key":"11699_CR24","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.cmpb.2009.09.002","volume":"98","author":"M Modat","year":"2010","unstructured":"Modat M, Ridgway GR, Taylor ZA, Lehmann M, Barnes J, Hawkes DJ, Fox NC, Ourselin S (2010) Fast free-form deformation using graphics processing units. Computer Methods and Programs in Biomedicine 98(3):278\u2013284. https:\/\/doi.org\/10.1016\/j.cmpb.2009.09.002","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"2","key":"11699_CR25","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1080\/10255842.2012.670855","volume":"17","author":"FP Oliveira","year":"2014","unstructured":"Oliveira FP, Tavares JMR (2014) Medical image registration: a review. Computer Methods in Biomechanics and Biomedical Engineering 17(2):73\u201393. https:\/\/doi.org\/10.1080\/10255842.2012.670855","journal-title":"Computer Methods in Biomechanics and Biomedical Engineering"},{"key":"11699_CR26","doi-asserted-by":"publisher","unstructured":"Palomar R, G\u00f3mez-Luna J, Cheikh FA, Olivares-Bueno J, Elle OJ (2017) High-performance computation of b\u00e9zier surfaces on parallel and heterogeneous platforms. Int J Parallel Program. https:\/\/doi.org\/10.1007\/s10766-017-0506-1","DOI":"10.1007\/s10766-017-0506-1"},{"key":"11699_CR27","unstructured":"Parraguez SPP (2015) Fast and robust methods for non-rigid registration of medical images. PhD thesis, Imperial College of Science"},{"issue":"6","key":"11699_CR28","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1016\/j.media.2008.10.008","volume":"13","author":"T Rehman","year":"2009","unstructured":"Rehman T, Haber E, Pryor G, Melonakos J, Tannenbaum A (2009) 3Dnonrigid registration via optimal mass transport on the GPU. Medical Image Analysis 13(6):931\u2013940. https:\/\/doi.org\/10.1016\/j.media.2008.10.008","journal-title":"Medical Image Analysis"},{"issue":"1","key":"11699_CR29","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TITB.2003.808506","volume":"7","author":"T Rohlfing","year":"2003","unstructured":"Rohlfing T, Maurer CR (2003) Nonrigid image registration in shared-memory multiprocessor environments with application to brains, breasts, and bees. IEEE Transactions on Information Technology in Biomedicine 7(1):16\u201325. https:\/\/doi.org\/10.1109\/TITB.2003.808506","journal-title":"IEEE Transactions on Information Technology in Biomedicine"},{"key":"11699_CR30","doi-asserted-by":"publisher","unstructured":"Rohou E (2012) Tiptop: Hardware performance counters for the masses. In: 41st international conference on parallel processing workshops, pp 404\u2013413 https:\/\/doi.org\/10.1109\/ICPPW.2012.58","DOI":"10.1109\/ICPPW.2012.58"},{"key":"11699_CR31","doi-asserted-by":"publisher","unstructured":"Rohrer J, Gong L (2009) Accelerating 3D nonrigid registration using the cell broadband engine processor. IBM J R Dev 53(5) https:\/\/doi.org\/10.1147\/JRD.2009.5429078","DOI":"10.1147\/JRD.2009.5429078"},{"issue":"8","key":"11699_CR32","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1109\/42.796284","volume":"18","author":"D Rueckert","year":"1999","unstructured":"Rueckert D, Sonoda LI, Hayes C, Hill DLG, Leach MO, Hawkes DJ (1999) Nonrigid registration using free-form deformations: application to breast MR images. IEEE Transactions on Medical Imaging 18(8):712\u2013721. https:\/\/doi.org\/10.1109\/42.796284","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"9","key":"11699_CR33","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/j.parco.2010.05.006","volume":"36","author":"S Rul","year":"2010","unstructured":"Rul S, Vandierendonck H, Bosschere KD (2010) A profile-based tool for finding pipeline parallelism in sequential programs. Parallel Computing 36(9):531\u2013551. https:\/\/doi.org\/10.1016\/j.parco.2010.05.006","journal-title":"Parallel Computing"},{"issue":"1","key":"11699_CR34","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.parco.2004.12.003","volume":"31","author":"M Salomon","year":"2005","unstructured":"Salomon M, Heitz F, Perrin GR, Armspach JP (2005) A massively parallel approach to deformable matching of 3D medical images via stochastic differential equations. Parallel Computing 31(1):45\u201371. https:\/\/doi.org\/10.1016\/j.parco.2004.12.003","journal-title":"Parallel Computing"},{"key":"11699_CR35","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-3-540-74466-5_12","volume-title":"Practical differential Profiling","author":"M Schulz","year":"2007","unstructured":"Schulz M, de Supinski BR (2007) Practical differential Profiling. Springer, Berlin, pp 97\u2013106. https:\/\/doi.org\/10.1007\/978-3-540-74466-5_12"},{"key":"11699_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-407741-6.00007-4","volume-title":"High performance deformable image registration algorithms for manycore processors","author":"J Shackleford","year":"2013","unstructured":"Shackleford J, Kandasamy N, Sharp G (2013) High performance deformable image registration algorithms for manycore processors. Morgan Kaufmann Publishers Inc., San Mateo. https:\/\/doi.org\/10.1016\/B978-0-12-407741-6.00007-4"},{"issue":"2","key":"11699_CR37","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.2009.935387","volume":"27","author":"R Shams","year":"2010","unstructured":"Shams R, Sadeghi P, Kennedy RA, Hartley RI (2010) A survey of medical image registration on multicore and the GPU. IEEE Signal Processing Magazine 27(2):50\u201360. https:\/\/doi.org\/10.1109\/MSP.2009.935387","journal-title":"IEEE Signal Processing Magazine"},{"issue":"2","key":"11699_CR38","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.cmpb.2009.11.004","volume":"99","author":"R Shams","year":"2010","unstructured":"Shams R, Sadeghi P, Kennedy R, Hartley R (2010) Parallel computation of mutual information on the GPU with application to real-time registration of 3D medical images. Computer Methods and Programs in Biomedicine 99(2):133\u2013146. https:\/\/doi.org\/10.1016\/j.cmpb.2009.11.004","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"11699_CR39","unstructured":"Shi L, Liu W, Zhang H, Xie Y, Wang D, Shi L, Liu W, Zhang H, Xie Y, Wang D (2012) A survey of GPU-based medical image computing techniques. Quant Imaging Med Surg 2(3)"},{"issue":"C","key":"11699_CR40","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.imavis.2016.05.006","volume":"52","author":"P Snape","year":"2016","unstructured":"Snape P, Pszczolkowski S, Zafeiriou S, Tzimiropoulos G, Ledig C, Rueckert D (2016) A robust similarity measure for volumetric image registration with outliers. Image and Vision Computing 52(C):97\u2013113. https:\/\/doi.org\/10.1016\/j.imavis.2016.05.006","journal-title":"Image and Vision Computing"},{"issue":"3","key":"11699_CR41","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1002\/spe.562","volume":"34","author":"JM Spivey","year":"2004","unstructured":"Spivey JM (2004) Fast, accurate call graph profiling. Software: Practice and Experience 34(3):249\u2013264. https:\/\/doi.org\/10.1002\/spe.562","journal-title":"Software: Practice and Experience"},{"key":"11699_CR42","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9739-5","volume-title":"Programming many-core chip","author":"A Vadja","year":"2011","unstructured":"Vadja A (2011) Programming many-core chip. Springer, Berlin. https:\/\/doi.org\/10.1007\/978-1-4419-9739-5"},{"key":"11699_CR43","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1016\/S0167-8191(98)00061-1","volume":"24","author":"SK Warfield","year":"1998","unstructured":"Warfield SK, Jolesz FA, Kikinis R (1998) A high performance computing approach to the registration of medical imaging data. Parallel Computing 24:1345\u20131368. https:\/\/doi.org\/10.1016\/S0167-8191(98)00061-1","journal-title":"Parallel Computing"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11699-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11699-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11699-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T09:30:29Z","timestamp":1643448629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11699-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,2]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["11699"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11699-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,2]]},"assertion":[{"value":"14 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}