{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T12:40:09Z","timestamp":1745325609138,"version":"3.40.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T00:00:00Z","timestamp":1736208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["447235146"],"award-info":[{"award-number":["447235146"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"Abstract<\/jats:title>\n \n Purpose<\/jats:title>\n Lung fissure segmentation on CT images often relies on 3D convolutional neural networks (CNNs). However, 3D-CNNs are inefficient for detecting thin structures like the fissures, which make up a tiny fraction of the entire image volume. We propose to make lung fissure segmentation more efficient by using geometric deep learning (GDL) on sparse point clouds.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We abstract image data with sparse keypoint (KP) clouds. We train GDL models to segment the point cloud, comparing three major paradigms of models (PointNets, graph convolutional networks (GCNs), and PointTransformers). From the sparse point segmentations, 3D meshes of the objects are reconstructed to obtain a dense surface. The state-of-the-art Poisson surface reconstruction (PSR) makes up most of the time in our pipeline. Therefore, we propose an efficient point cloud to mesh autoencoder (PC-AE) that deforms a template mesh to fit a point cloud in a single forward pass. Our pipeline is evaluated extensively and compared to the 3D-CNN gold standard nnU-Net on diverse clinical and pathological data.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n GCNs yield the best trade-off between inference time and accuracy, being \n \n $$21\\times $$<\/jats:tex-math>\n \n \n 21<\/mml:mn>\n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula> faster with only \n \n $$1.4\\times $$<\/jats:tex-math>\n \n \n 1.4<\/mml:mn>\n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula> increased error over the nnU-Net. Our PC-AE also achieves a favorable trade-off, being \n \n $$3\\times $$<\/jats:tex-math>\n \n \n 3<\/mml:mn>\n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula> faster at \n \n $$1.5\\times $$<\/jats:tex-math>\n \n \n 1.5<\/mml:mn>\n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula> the error compared to the PSR.<\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n We present a KP-based fissure segmentation pipeline that is more efficient than 3D-CNNs and can greatly speed up large-scale analyses. A novel PC-AE for efficient mesh reconstruction from sparse point clouds is introduced, showing promise not only for fissure segmentation. Source code is available on https:\/\/github.com\/kaftanski\/fissure-segmentation-IJCARS<\/jats:ext-link>\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1007\/s11548-024-03310-z","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T04:15:57Z","timestamp":1736223357000},"page":"465-473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sparse keypoint segmentation of lung fissures: efficient geometric deep learning for abstracting volumetric images"],"prefix":"10.1007","volume":"20","author":[{"given":"Paul","family":"Kaftan","sequence":"first","affiliation":[]},{"given":"Mattias P.","family":"Heinrich","sequence":"additional","affiliation":[]},{"given":"Lasse","family":"Hansen","sequence":"additional","affiliation":[]},{"given":"Volker","family":"Rasche","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4759-5254","authenticated-orcid":false,"given":"Hans A.","family":"Kestler","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Bigalke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"issue":"4","key":"3310_CR1","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/0899-7071(92)90001-P","volume":"16","author":"RM Sofranik","year":"1992","unstructured":"Sofranik RM, Gross BH, Spizarny DL (1992) Radiology of the pleural fissures. Clin Imaging 16(4):221\u2013229. https:\/\/doi.org\/10.1016\/0899-7071(92)90001-P","journal-title":"Clin Imaging"},{"issue":"2","key":"3310_CR2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, J\u00e4ger PF, Kohl SAA, Petersen J, Maier-Hein KH (2021) Automated design of deep learning methods for biomedical image segmentation. Nat Methods 18(2):203\u2013211. https:\/\/doi.org\/10.1038\/s41592-020-01008-z","journal-title":"Nat Methods"},{"key":"3310_CR3","doi-asserted-by":"crossref","unstructured":"Kaftan P, Heinrich MP, Hansen L, Rasche V, Kestler HA, Bigalke A (2024) Abstracting volumetric medical images with sparse Keypoints for efficient geometric segmentation of lung fissures with a graph CNN. In: Bildverarbeitung F\u00fcr Die Medizin 2024. Springer, Erlangen","DOI":"10.1007\/978-3-658-44037-4_19"},{"key":"3310_CR4","doi-asserted-by":"publisher","unstructured":"Charles RQ, Su H, Kaichun M, Guibas LJ (2017) Pointnet: deep learning on point sets for 3d classification and segmentation. In: 2017 IEEE Conf Comput Vis Pattern Recognit (CVPR), pp. 77\u201385. https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"issue":"5","key":"3310_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang Y, Sun Y, Liu Z, Sarma SE, Bronstein MM, Solomon JM (2019) Dynamic graph CNN for learning on point clouds. ACM Trans Graph 38(5):1\u20132","journal-title":"ACM Trans Graph"},{"key":"3310_CR6","doi-asserted-by":"publisher","unstructured":"Zhao H, Jiang L, Jia J, Torr P, Koltun V (2021) Point Transformer. In: 2021 IEEE\/CVF Int Conf Comput Vis (ICCV), pp. 16239\u201316248. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01595","DOI":"10.1109\/ICCV48922.2021.01595"},{"issue":"3","key":"3310_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2487228.2487237","volume":"32","author":"M Kazhdan","year":"2013","unstructured":"Kazhdan M, Hoppe H (2013) Screened poisson surface reconstruction. ACM Trans Graph 32(3):1\u201313. https:\/\/doi.org\/10.1145\/2487228.2487237","journal-title":"ACM Trans Graph"},{"key":"3310_CR8","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1016\/j.ics.2005.03.130","volume":"1281","author":"R Wiemker","year":"2005","unstructured":"Wiemker R, B\u00fclow T, Blaffert T (2005) Unsupervised extraction of the pulmonary interlobar fissures from high resolution thoracic CT data. Int Congr Ser 1281:1121\u20131126. https:\/\/doi.org\/10.1016\/j.ics.2005.03.130","journal-title":"Int Congr Ser"},{"issue":"12","key":"3310_CR9","doi-asserted-by":"publisher","DOI":"10.1118\/1.4828782","volume":"40","author":"JC Ross","year":"2013","unstructured":"Ross JC, Kindlmann GL, Okajima Y, Hatabu H, D\u00edaz AA, Silverman EK, Washko GR, Dy J, Est\u00e9par RSJ (2013) Pulmonary lobe segmentation based on ridge surface sampling and shape model fitting. Med Phys 40(12):121903. https:\/\/doi.org\/10.1118\/1.4828782","journal-title":"Med Phys"},{"issue":"1","key":"3310_CR10","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TMI.2018.2858202","volume":"38","author":"SE Gerard","year":"2019","unstructured":"Gerard SE, Patton TJ, Christensen GE, Bayouth JE, Reinhardt JM (2019) FissureNet: a deep learning approach for pulmonary fissure detection in CT images. IEEE Trans Med Imaging 38(1):156\u2013166. https:\/\/doi.org\/10.1109\/TMI.2018.2858202","journal-title":"IEEE Trans Med Imaging"},{"issue":"8","key":"3310_CR11","doi-asserted-by":"publisher","first-page":"2664","DOI":"10.1109\/TMI.2020.2995108","volume":"39","author":"W Xie","year":"2020","unstructured":"Xie W, Jacobs C, Charbonnier J-P, van Ginneken B (2020) Relational modeling for robust and efficient pulmonary lobe segmentation in CT scans. IEEE Trans Med Imaging 39(8):2664\u20132675. https:\/\/doi.org\/10.1109\/TMI.2020.2995108","journal-title":"IEEE Trans Med Imaging"},{"key":"3310_CR12","doi-asserted-by":"crossref","unstructured":"Wickramasinghe U, Remelli E, Knott G, Fua P (2020) Voxel2Mesh: 3D mesh model generation from volumetric data. In: Med Image Comput Comput-Assist Interv (MICCAI 2020), pp. 299\u2013308. Springer, Cham","DOI":"10.1007\/978-3-030-59719-1_30"},{"key":"3310_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102222","volume":"74","author":"F Kong","year":"2021","unstructured":"Kong F, Wilson N, Shadden S (2021) A deep-learning approach for direct whole-heart mesh reconstruction. Med Image Anal 74:102222. https:\/\/doi.org\/10.1016\/j.media.2021.102222","journal-title":"Med Image Anal"},{"key":"3310_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_31","author":"F Balsiger","year":"2019","unstructured":"Balsiger F, Soom Y, Scheidegger O, Reyes M (2019) Learning shape representation on sparse point clouds for volumetric image segmentation. Med Image Comput Comput-Assist Interv (MICCAI 2019). https:\/\/doi.org\/10.1007\/978-3-030-32245-8_31","journal-title":"Med Image Comput Comput-Assist Interv (MICCAI 2019)"},{"issue":"10","key":"3310_CR15","doi-asserted-by":"publisher","first-page":"263","DOI":"10.3390\/a13100263","volume":"13","author":"X Chen","year":"2020","unstructured":"Chen X, Zhao H, Zhou P (2020) Lung lobe segmentation based on lung fissure surface classification using a point cloud region growing approach. Algorithms 13(10):263. https:\/\/doi.org\/10.3390\/a13100263","journal-title":"Algorithms"},{"key":"3310_CR16","unstructured":"F\u00f6rstner W, G\u00fclch E (1987) A fast operator for detection and precise location of distinct points, corners and centres of circular features. In: Proc. ISPRS Intercomm Conf Fast Proc Photogramm Data, Interlaken, pp. 281\u2013305"},{"key":"3310_CR17","doi-asserted-by":"publisher","unstructured":"Heinrich MP, Handels H, Simpson IJA (2015) Estimating Large Lung Motion in COPD Patients by Symmetric Regularised Correspondence Fields. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A. (eds.) Med Image Comput Comput-Assist Interv (MICCAI 2015). Lecture Notes in Computer Science, pp. 338\u2013345. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-24571-3_41","DOI":"10.1007\/978-3-319-24571-3_41"},{"key":"3310_CR18","doi-asserted-by":"publisher","unstructured":"Howard A, Sandler M, Chen B, Wang W, Chen L-C, Tan M, Chu G, Vasudevan V, Zhu Y, Pang R, Adam H, Le Q (2019) Searching for mobilenetv3. In: 2019 IEEE\/CVF Int Conf Comput Vis (ICCV), pp. 1314\u20131324.https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"3310_CR19","unstructured":"Zaheer M, Kottur S, Ravanbakhsh S, Poczos B, Salakhutdinov RR, Smola AJ (2017) Deep Sets. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Adv Neural Inf Process Syst, vol 30. Curran Associates Inc, Red Hook, NY"},{"key":"3310_CR20","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proc. arXiv:1412.6980"},{"key":"3310_CR21","unstructured":"Loshchilov I, Hutter F (2017) SGDR: stochastic gradient descent with warm restarts. In: 5th International Conference on Learning Representations, ICLR 2017, Conference Track Proc. https:\/\/openreview.net\/forum?id=Skq89Scxx"},{"issue":"2","key":"3310_CR22","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1109\/TMI.2017.2743464","volume":"37","author":"O Oktay","year":"2018","unstructured":"Oktay O, Ferrante E, Kamnitsas K, Heinrich M, Bai W, Caballero J, Cook SA, De Marvao A, Dawes T, O\u2019Regan DP, Kainz B, Glocker B, Rueckert D (2018) Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation. IEEE Trans Med Imaging 37(2):384\u2013395. https:\/\/doi.org\/10.1109\/TMI.2017.2743464","journal-title":"IEEE Trans Med Imaging"},{"key":"3310_CR23","doi-asserted-by":"publisher","unstructured":"Yang Y, Feng C, Shen Y, Tian D (2018) FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation. In: 2018 IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp. 206\u2013215. IEEE, Salt Lake City, UT. https:\/\/doi.org\/10.1109\/CVPR.2018.00029","DOI":"10.1109\/CVPR.2018.00029"},{"key":"3310_CR24","unstructured":"Tao A (2020) Unsupervised point cloud reconstruction for classific feature learning. GitHub Repository. https:\/\/github.com\/antao97\/UnsupervisedPointCloudReconstruction Accessed 15 Nov 2022"},{"issue":"5","key":"3310_CR25","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024","volume":"5","author":"J Wasserthal","year":"2023","unstructured":"Wasserthal J, Breit H-C, Meyer MT, Pradella M, Hinck D, Sauter AW, Heye T, Boll DT, Cyriac J, Yang S, Bach M, Segeroth M (2023) Totalsegmentator Robust segmentation of 104 anatomic structures in ct images. Radiol Artif Intell 5(5):230024. https:\/\/doi.org\/10.1148\/ryai.230024","journal-title":"Radiol Artif Intell"},{"key":"3310_CR26","volume-title":"Digital Image Processing","author":"RC Gonzalez","year":"2008","unstructured":"Gonzalez RC, Woods RE (2008) Digital Image Processing, 3rd edn. Pearson Prentice Hall, Upper Saddle River","edition":"3"},{"key":"3310_CR27","first-page":"33330","volume":"35","author":"X Wu","year":"2022","unstructured":"Wu X, Lao Y, Jiang L, Liu X, Zhao H (2022) Point transformer V2: grouped vector attention and partition-based pooling. Adv Neural Inf Process Syst 35:33330\u201333342","journal-title":"Adv Neural Inf Process Syst"},{"key":"3310_CR28","doi-asserted-by":"crossref","unstructured":"Wu X, Jiang L, Wang P-S, Liu Z, Liu X, Qiao Y, Ouyang W, He T, Zhao H (2024) Point transformer v3: Simpler faster stronger. In: Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR), pp. 4840\u20134851","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"3310_CR29","unstructured":"Peng S, Jiang C, Liao Y, Niemeyer M, Pollefeys M, Geiger A (2021) Shape as points: a differentiable poisson solver. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Vaughan JW (eds) Adv Neural Inf Process Syst (NeurIPS 2021), vol 34. Curran Associates Inc, Red Hook, NY, pp 13032\u201313044"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03310-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-024-03310-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03310-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T11:59:54Z","timestamp":1745323194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-024-03310-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,7]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["3310"],"URL":"https:\/\/doi.org\/10.1007\/s11548-024-03310-z","relation":{},"ISSN":["1861-6429"],"issn-type":[{"type":"electronic","value":"1861-6429"}],"subject":[],"published":{"date-parts":[[2025,1,7]]},"assertion":[{"value":"2 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Missing supplementary material has been updated","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}