{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:43:00Z","timestamp":1782963780417,"version":"3.54.5"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012550","name":"Nemzeti Kutat\u00e1si, Fejleszt\u00e9si \u00e9s Innovaci\u00f3s Alap","doi-asserted-by":"publisher","award":["2019-1.3.1-KK-2019-00011"],"award-info":[{"award-number":["2019-1.3.1-KK-2019-00011"]}],"id":[{"id":"10.13039\/501100012550","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009934","name":"E\u00f6tv\u00f6s Lor\u00e1nd University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009934","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EJNMMI Phys"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Purpose<\/jats:bold>\n            <\/jats:title>\n            <jats:p>Various specialized and general collimators are used for myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT) to assess different types of coronary artery disease (CAD). Alongside the wide variability in imaging characteristics, the apriori \u201clearnt\u201d information of left ventricular (LV) shape can affect the final diagnosis of the imaging protocol. This study evaluates the effect of prior information incorporation into the segmentation process, compared to deep learning (DL) approaches, as well as the differences of 4 collimation techniques on 5 different datasets.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Methods<\/jats:bold>\n            <\/jats:title>\n            <jats:p>This study was implemented on 80 patients database. 40 patients were coming from mixed black-box collimators, 10 each, from multi-pinhole (MPH), low energy high resolution (LEHR), CardioC and CardioD collimators. The testing was evaluated on a new continuous graph-based approach, which automatically segments the left ventricular volume with prior information on the cardiac geometry. The technique is based on the continuous max-flow (CMF) min-cut algorithm, which performance was evaluated in precision, recall, IoU and Dice score metrics.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Results<\/jats:bold>\n            <\/jats:title>\n            <jats:p>In the testing it was shown that, the developed method showed a good improvement over deep learning reaching higher scores in most of the evaluation metrics. Further investigating the different collimation techniques, the evaluation of receiver operating characterstic (ROC) curves showed different stabilities on the various collimators. Running Wilcoxon signed-rank test on the outlines of the LVs showed differentiability between the collimation procedures. To further investigate these phenomena the model parameters of the LVs were reconstructed and evaluated by the uniform manifold approximation and projection (UMAP) method, which further proved that collimators can be differentiated based on the projected LV shapes alone.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>\n              <jats:bold>Conclusions<\/jats:bold>\n            <\/jats:title>\n            <jats:p>The results show that prior information incorporation can enhance the performance of segmentation methods and collimation strategies have a high effect on the projected cardiac geometry.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s40658-025-00728-5","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T04:08:51Z","timestamp":1741579731000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Myocardial perfusion imaging SPECT left ventricle segmentation with graphs"],"prefix":"10.1186","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7984-4542","authenticated-orcid":false,"given":"\u00c1d\u00e1m Istv\u00e1n","family":"Sz\u0171cs","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B\u00e9la","family":"K\u00e1ri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oszk\u00e1r","family":"P\u00e1rtos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"728_CR1","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2017.2471","author":"I Danad","year":"2017","unstructured":"Danad I, Raijmakers PG, Driessen RS, Leipsic J, Raju R, Naoum C, Knuuti J, M\u00e4ki M, Underwood RS, Min JK, Elmore K, Stuijfzand WJ, Van Royen N, Tulevski II, Somsen AG, Huisman MC, Van Lingen AA, Heymans MW, Van De Ven PM, Van Kuijk C, Lammertsma AA, Van Rossum AC, Knaapen P. Comparison of coronary CT angiography, SPECT, PET, and hybrid imaging for diagnosis of ischemic heart disease determined by fractional flow reserve. JAMA Cardiol. 2017. https:\/\/doi.org\/10.1001\/jamacardio.2017.2471.","journal-title":"JAMA Cardiol"},{"key":"728_CR2","doi-asserted-by":"publisher","unstructured":"Elizabeth Oates M, Sorrell V. Myocardial perfusion imaging\u2014beyond the left ventricle. Springer, Berlin, Germany; 2017. p. 385. https:\/\/doi.org\/10.1007\/978-3-319-25436-4. https:\/\/www.springer.com\/gp\/book\/9783319254340.","DOI":"10.1007\/978-3-319-25436-4"},{"key":"728_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s12350-018-1294-8","author":"RD Rosenberg","year":"2018","unstructured":"Rosenberg RD, Patil PV. Multimodality imaging of the left ventricle: choosing soundly. J Nucl Cardiol. 2018. https:\/\/doi.org\/10.1007\/s12350-018-1294-8.","journal-title":"J Nucl Cardiol"},{"issue":"2","key":"728_CR4","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/s12350-016-0726-6","volume":"24","author":"H Malek","year":"2017","unstructured":"Malek H, Yaghoobi N, Hedayati R. Artifacts in quantitative analysis of myocardial perfusion SPECT, using Cedars\u2013Sinai QPS Software. J Nucl Cardiol. 2017;24(2):534\u201342. https:\/\/doi.org\/10.1007\/s12350-016-0726-6.","journal-title":"J Nucl Cardiol"},{"issue":"4 SPEC. ISS.","key":"728_CR5","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.nuclcard.2007.06.006","volume":"14","author":"EP Ficaro","year":"2007","unstructured":"Ficaro EP, Lee BC, Kritzman JN, Corbett JR. Corridor4DM: the Michigan method for quantitative nuclear cardiology. J Nucl Cardiol. 2007;14(4 SPEC. ISS.):455\u201365. https:\/\/doi.org\/10.1016\/j.nuclcard.2007.06.006.","journal-title":"J Nucl Cardiol"},{"issue":"4 SPEC. ISS.","key":"728_CR6","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1016\/j.nuclcard.2007.06.008","volume":"14","author":"G Germano","year":"2007","unstructured":"Germano G, Kavanagh PB, Slomka PJ, Van Kriekinge SD, Pollard G, Berman DS. Quantitation in gated perfusion SPECT imaging: the Cedars\u2013Sinai approach. J Nucl Cardiol. 2007;14(4 SPEC. ISS.):433\u201354. https:\/\/doi.org\/10.1016\/j.nuclcard.2007.06.008.","journal-title":"J Nucl Cardiol"},{"issue":"4 SPEC. ISS.","key":"728_CR7","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/j.nuclcard.2007.06.009","volume":"14","author":"EV Garcia","year":"2007","unstructured":"Garcia EV, Faber TL, Cooke CD, Folks RD, Chen J, Santana C. The increasing role of quantification in clinical nuclear cardiology: the Emory approach. J Nucl Cardiol. 2007;14(4 SPEC. ISS.):420\u201332. https:\/\/doi.org\/10.1016\/j.nuclcard.2007.06.009.","journal-title":"J Nucl Cardiol"},{"issue":"4 SPEC. ISS.","key":"728_CR8","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.nuclcard.2007.06.005","volume":"14","author":"YH Liu","year":"2007","unstructured":"Liu YH. Quantification of nuclear cardiac images: the Yale approach. J Nucl Cardiol. 2007;14(4 SPEC. ISS.):483\u201391. https:\/\/doi.org\/10.1016\/j.nuclcard.2007.06.005.","journal-title":"J Nucl Cardiol"},{"issue":"9","key":"728_CR9","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.2967\/jnumed.108.061333","volume":"50","author":"Y Xu","year":"2009","unstructured":"Xu Y, Kavanagh P, Fish M, Gerlach J, Ramesh A, Lemley M, Hayes S, Berman DS, Germano G, Slomka PJ. Automated quality control for segmentation of myocardial perfusion SPECT. J Nucl Med. 2009;50(9):1418\u201326. https:\/\/doi.org\/10.2967\/jnumed.108.061333.","journal-title":"J Nucl Med"},{"key":"728_CR10","doi-asserted-by":"crossref","unstructured":"Yuan J, Bae E, Tai X-C. A study on continuous max-flow and min-cut approaches. In: 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE; 2010. pp. 2217\u20132224.","DOI":"10.1109\/CVPR.2010.5539903"},{"key":"728_CR11","unstructured":"Sun H, Tai X, Yuan J. Efficient ADMM and splitting methods for continuous min-cut and max-flow problems; 2020. arXiv preprint arXiv:2004.11227."},{"key":"728_CR12","doi-asserted-by":"crossref","unstructured":"MkADRY A. Gradients and flows: continuous optimization approaches to the maximum flow problem. In: Proceedings of the international congress of mathematicians: Rio de Janeiro 2018. World Scientific; 2018. pp. 3361\u20133387.","DOI":"10.1142\/9789813272880_0185"},{"key":"728_CR13","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1002\/cpa.3160420503","volume":"42","author":"DB Mumford","year":"1989","unstructured":"Mumford DB, Shah J. Optimal approximations by piecewise smooth functions and associated variational problems. Commun Pure Appl Math. 1989;42:577\u2013685.","journal-title":"Commun Pure Appl Math"},{"issue":"5","key":"728_CR14","doi-asserted-by":"publisher","first-page":"1632","DOI":"10.1137\/040615286","volume":"66","author":"TF Chan","year":"2006","unstructured":"Chan TF, Esedoglu S, Nikolova M. Algorithms for finding global minimizers of image segmentation and denoising models. SIAM J Appl Math. 2006;66(5):1632\u201348.","journal-title":"SIAM J Appl Math"},{"key":"728_CR15","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1023\/B:JMIV.0000011321.19549.88","volume":"20","author":"A Chambolle","year":"2004","unstructured":"Chambolle A. An algorithm for total variation minimization and applications. J Math Imaging Vis. 2004;20:89\u201397.","journal-title":"J Math Imaging Vis"},{"key":"728_CR16","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1007\/978-1-4939-0790-8_40","volume":"2","author":"D Cremers","year":"2015","unstructured":"Cremers D. Image segmentation with shape priors: explicit versus implicit representations. Handb Math Methods Imaging. 2015;2:1909\u201344.","journal-title":"Handb Math Methods Imaging"},{"key":"728_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069634","author":"G Valvano","year":"2021","unstructured":"Valvano G, Leo A, Tsaftaris SA. Learning to segment from scribbles using multi-scale adversarial attention gates. IEEE Trans Med Imaging. 2021. https:\/\/doi.org\/10.1109\/TMI.2021.3069634.","journal-title":"IEEE Trans Med Imaging"},{"issue":"11","key":"728_CR18","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard O, Lalande A, Zotti C, Cervenansky F, Yang X, Heng P-A, Cetin I, Lekadir K, Camara O, Ballester MAG, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans Med Imaging. 2018;37(11):2514\u201325.","journal-title":"IEEE Trans Med Imaging"},{"key":"728_CR19","doi-asserted-by":"crossref","unstructured":"Overgaard NC, Fundana K, Heyden A. Pose invariant shape prior segmentation using continuous cuts and gradient descent on lie groups. In: Scale space and variational methods in computer vision: second international conference, SSVM 2009, Voss, Norway, June 1\u20135, 2009. Proceedings 2; 2009. Springer. pp. 684\u2013695","DOI":"10.1007\/978-3-642-02256-2_57"},{"key":"728_CR20","unstructured":"Kvile MA. Continuous max-flow for image segmentation with shape priors. Master\u2019s thesis, The University of Bergen; 2014."},{"issue":"9","key":"728_CR21","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1016\/S0031-3203(03)00056-6","volume":"36","author":"D Cremers","year":"2003","unstructured":"Cremers D, Kohlberger T, Schn\u00f6rr C. Shape statistics in kernel space for variational image segmentation. Pattern Recogn. 2003;36(9):1929\u201343.","journal-title":"Pattern Recogn"},{"issue":"9","key":"728_CR22","doi-asserted-by":"publisher","first-page":"093001","DOI":"10.1088\/0266-5611\/32\/9\/093001","volume":"32","author":"T Hohage","year":"2016","unstructured":"Hohage T, Werner F. Inverse problems with Poisson data: statistical regularization theory, applications and algorithms. Inverse Prob. 2016;32(9):093001.","journal-title":"Inverse Prob"},{"issue":"5","key":"728_CR23","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1016\/j.compbiomed.2013.01.002","volume":"43","author":"Q Zheng","year":"2013","unstructured":"Zheng Q, Lu Z, Yang W, Zhang M, Feng Q, Chen W. A robust medical image segmentation method using KL distance and local neighborhood information. Comput Biol Med. 2013;43(5):459\u201370.","journal-title":"Comput Biol Med"},{"key":"728_CR24","first-page":"8024","volume-title":"Pytorch: an imperative style, high-performance deep learning library","author":"A Paszke","year":"2019","unstructured":"Paszke A, et al. Pytorch: an imperative style, high-performance deep learning library. New York: Curran Associates, Inc.; 2019. p. 8024\u201335."},{"issue":"2","key":"728_CR25","doi-asserted-by":"publisher","first-page":"128","DOI":"10.22503\/inftars.XXII.2022.2.8","volume":"22","author":"M H\u00e9der","year":"2022","unstructured":"H\u00e9der M, Rig\u00f3 E, Medgyesi D, Lovas R, Tenczer S, Farkas A, Em\u0151di MB, Kadlecsik J, Kacsuk P. The past, present and future of the ELKH cloud. Inform\u00e1ci\u00f3s T\u00e1rsadalom: T\u00e1rsadalomtudom\u00e1nyi Foly\u00f3irat. 2022;22(2):128\u201337.","journal-title":"Inform\u00e1ci\u00f3s T\u00e1rsadalom: T\u00e1rsadalomtudom\u00e1nyi Foly\u00f3irat"},{"key":"728_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106236","author":"F P\u00e9rez-Garc\u00eda","year":"2021","unstructured":"P\u00e9rez-Garc\u00eda F, Sparks R, Ourselin S. Torchio: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput Methods Programs Biomed. 2021. https:\/\/doi.org\/10.1016\/j.cmpb.2021.106236.","journal-title":"Comput Methods Programs Biomed"},{"key":"728_CR27","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"728_CR28","unstructured":"Williams F. Point cloud utils; 2022. https:\/\/www.github.com\/fwilliams\/point-cloud-utils."},{"key":"728_CR29","unstructured":"Feydy J, S\u00e9journ\u00e9 T, Vialard F-X, Amari S-i, Trouve A, Peyr\u00e9 G. Interpolating between optimal transport and mmd using Sinkhorn divergences. In: The 22nd international conference on artificial intelligence and statistics; 2019. pp. 2681\u20132690."},{"issue":"9","key":"728_CR30","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.1118\/1.3480985","volume":"37","author":"WP Segars","year":"2010","unstructured":"Segars WP, Sturgeon G, Mendonca S, Grimes J, Tsui BMW. 4d xcat phantom for multimodality imaging research. Med Phys. 2010;37(9):4902\u201315. https:\/\/doi.org\/10.1118\/1.3480985.","journal-title":"Med Phys"},{"issue":"1","key":"728_CR31","doi-asserted-by":"publisher","first-page":"6195","DOI":"10.3182\/20110828-6-IT-1002.02896","volume":"44","author":"A Szl\u00e1vecz","year":"2011","unstructured":"Szl\u00e1vecz A, Hesz G, B\u00fckki T, K\u00e1ri B, Beny\u00f3 B. GPU-based acceleration of the MLEM algorithm for SPECT parallel imaging with attenuation correction and compensation for detector response. IFAC Proc Vol. 2011;44(1):6195\u2013200.","journal-title":"IFAC Proc Vol"},{"issue":"4","key":"728_CR32","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/42.363108","volume":"13","author":"HM Hudson","year":"1994","unstructured":"Hudson HM, Larkin RS. Accelerated image reconstruction using ordered subsets of projection data. IEEE Trans Med Imaging. 1994;13(4):601\u20139.","journal-title":"IEEE Trans Med Imaging"},{"key":"728_CR33","doi-asserted-by":"publisher","unstructured":"Kikinis R, Pieper SD, Vosburgh KG. In: Jolesz, F.A. (ed.) 3D slicer: a platform for subject-specific image analysis, visualization, and clinical support. Springer, New York, NY; 2014. pp. 277\u2013289. https:\/\/doi.org\/10.1007\/978-1-4614-7657-3_19.","DOI":"10.1007\/978-1-4614-7657-3_19"},{"key":"728_CR34","doi-asserted-by":"publisher","unstructured":"Szucs AI, et al. Self-supervised segmentation of myocardial perfusion imaging spect left ventricles. In: 2023 the 10th international conference on bioinformatics research and applications (ICBRA) (ICBRA 2023), September 22\u201324, 2023, Barcelona, Spain; 2023. https:\/\/doi.org\/10.1145\/3632047.3632078. ACM.","DOI":"10.1145\/3632047.3632078"},{"key":"728_CR35","doi-asserted-by":"publisher","first-page":"106954","DOI":"10.1016\/j.compbiomed.2023.106954","volume":"160","author":"F Zhu","year":"2023","unstructured":"Zhu F, Li L, Zhao J, Zhao C, Tang S, Nan J, Li Y, Zhao Z, Shi J, Chen Z, Han C, Jiang Z, Zhou W. A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion spect images. Comput Biol Med. 2023;160:106954. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.106954.","journal-title":"Comput Biol Med"},{"issue":"11","key":"728_CR36","first-page":"2881","volume":"33","author":"T Sainburg","year":"2021","unstructured":"Sainburg T, McInnes L, Gentner TQ. Parametric UMAP embeddings for representation and semisupervised learning. Neural Comput. 2021;33(11):2881\u2013907.","journal-title":"Neural Comput"}],"container-title":["EJNMMI Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40658-025-00728-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40658-025-00728-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40658-025-00728-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T15:57:20Z","timestamp":1741622240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ejnmmiphys.springeropen.com\/articles\/10.1186\/s40658-025-00728-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["728"],"URL":"https:\/\/doi.org\/10.1186\/s40658-025-00728-5","relation":{},"ISSN":["2197-7364"],"issn-type":[{"value":"2197-7364","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"14 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of Semmelweis University. Informed consent was obtained from all individual participants included in the study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and Consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no Conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing of interests"}}],"article-number":"21"}}