{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-automatic-3d-shape-instantiation-for","title":"Towards Automatic 3D Shape Instantiation for Deployed Stent Grafts: 2D Multiple-class and Class-imbalance Marker Segmentation with Equally-weighted Focal U-Net","arxiv_id":"1711.01506","date":"2017-11-04","proceeding":null,"authors":["Xiao-Yun Zhou Celia Riga","Su-Lin Lee","Guang-Zhong Yang"],"abstract":"Robot-assisted Fenestrated Endovascular Aortic Repair (FEVAR) is currently\nnavigated by 2D fluoroscopy which is insufficiently informative. Previously, a\nsemi-automatic 3D shape instantiation method was developed to instantiate the\n3D shape of a main, deployed, and fenestrated stent graft from a single\nfluoroscopy projection in real-time, which could help 3D FEVAR navigation and\nrobotic path planning. This proposed semi-automatic method was based on the\nRobust Perspective-5-Point (RP5P) method, graft gap interpolation and\nsemi-automatic multiple-class marker center determination. In this paper, an\nautomatic 3D shape instantiation could be achieved by automatic multiple-class\nmarker segmentation and hence automatic multiple-class marker center\ndetermination. Firstly, the markers were designed into five different shapes.\nThen, Equally-weighted Focal U-Net was proposed to segment the fluoroscopy\nprojections of customized markers into five classes and hence to determine the\nmarker centers. The proposed Equally-weighted Focal U-Net utilized U-Net as the\nnetwork architecture, equally-weighted loss function for initial marker\nsegmentation, and then equally-weighted focal loss function for improving the\ninitial marker segmentation. This proposed network outperformed traditional\nWeighted U-Net on the class-imbalance segmentation in this paper with reducing\none hyper-parameter - the weight. An overall mean Intersection over Union\n(mIoU) of 0.6943 was achieved on 78 testing images, where 81.01% markers were\nsegmented with a center position error <1.6mm. Comparable accuracy of 3D shape\ninstantiation was also achieved and stated. The data, trained models and\nTensorFlow codes are available on-line.","url_abs":"http://arxiv.org/abs/1711.01506v4","url_pdf":"http://arxiv.org/pdf/1711.01506v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-automatic-3d-shape-instantiation-for","repo_url":"https://github.com/jmhuer/fcn-simple-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}