{"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/dense-volume-to-volume-vascular-boundary","title":"Dense Volume-to-Volume Vascular Boundary Detection","arxiv_id":"1605.08401","date":"2016-05-26","proceeding":null,"authors":["Jameson Merkow","David Kriegman","Alison Marsden","Zhuowen Tu"],"abstract":"In this work, we present a novel 3D-Convolutional Neural Network (CNN)\narchitecture called I2I-3D that predicts boundary location in volumetric data.\nOur fine-to-fine, deeply supervised framework addresses three critical issues\nto 3D boundary detection: (1) efficient, holistic, end-to-end volumetric label\ntraining and prediction (2) precise voxel-level prediction to capture fine\nscale structures prevalent in medical data and (3) directed multi-scale,\nmulti-level feature learning. We evaluate our approach on a dataset consisting\nof 93 medical image volumes with a wide variety of anatomical regions and\nvascular structures. In the process, we also introduce HED-3D, a 3D extension\nof the state-of-the-art 2D edge detector (HED). We show that our deep learning\napproach out-performs, the current state-of-the-art in 3D vascular boundary\ndetection (structured forests 3D), by a large margin, as well as HED applied to\nslices, and HED-3D while successfully localizing fine structures. With our\napproach, boundary detection takes about one minute on a typical 512x512x512\nvolume.","url_abs":"http://arxiv.org/abs/1605.08401v1","url_pdf":"http://arxiv.org/pdf/1605.08401v1.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":"dense-volume-to-volume-vascular-boundary","repo_url":"https://github.com/petteriTeikari/vesselNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}