{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/dynamic-deep-networks-for-retinal-vessel","title":"Dynamic Deep Networks for Retinal Vessel Segmentation","arxiv_id":"1903.07803","date":"2019-03-19","proceeding":null,"authors":["Aashis Khanal","Rolando Estrada"],"abstract":"Segmenting the retinal vasculature entails a trade-off between how much of\nthe overall vascular structure we identify vs. how precisely we segment\nindividual vessels. In particular, state-of-the-art methods tend to\nunder-segment faint vessels, as well as pixels that lie on the edges of thicker\nvessels. Thus, they underestimate the width of individual vessels, as well as\nthe ratio of large to small vessels. More generally, many crucial\nbio-markers---including the artery-vein (AV) ratio, branching angles, number of\nbifurcation, fractal dimension, tortuosity, vascular length-to-diameter ratio\nand wall-to-lumen length---require precise measurements of individual vessels.\nTo address this limitation, we propose a novel, stochastic training scheme for\ndeep neural networks that better classifies the faint, ambiguous regions of the\nimage. Our approach relies on two key innovations. First, we train our deep\nnetworks with dynamic weights that fluctuate during each training iteration.\nThis stochastic approach forces the network to learn a mapping that robustly\nbalances precision and recall. Second, we decouple the segmentation process\ninto two steps. In the first half of our pipeline, we estimate the likelihood\nof every pixel and then use these likelihoods to segment pixels that are\nclearly vessel or background. In the latter part of our pipeline, we use a\nsecond network to classify the ambiguous regions in the image. Our proposed\nmethod obtained state-of-the-art results on five retinal datasets---DRIVE,\nSTARE, CHASE-DB, AV-WIDE, and VEVIO---by learning a robust balance between\nfalse positive and false negative rates. In addition, we are the first to\nreport segmentation results on the AV-WIDE dataset, and we have made the\nground-truth annotations for this dataset publicly available.","url_abs":"http://arxiv.org/abs/1903.07803v2","url_pdf":"http://arxiv.org/pdf/1903.07803v2.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":"dynamic-deep-networks-for-retinal-vessel","repo_url":"https://github.com/sraashis/ature","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dynamic-deep-networks-for-retinal-vessel","repo_url":"https://github.com/sraashis/deepdyn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dynamic-deep-networks-for-retinal-vessel","repo_url":"https://github.com/sraashis/easytorchexample","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dynamic-deep-networks-for-retinal-vessel","repo_url":"https://github.com/sraashis/unet-vessel-segmentation-easytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"retinal-vessel-segmentation","task_name":"Retinal Vessel Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"sraashis/ature","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1505.04597"],"harvested_for_calls":[{"arxiv_id":"1505.04597","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.04597"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.04597\")"}]},{"repo":"sraashis/deepdyn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sraashis/easytorchexample","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sraashis/unet-vessel-segmentation-easytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1c0bd711e2b528733bd13240d52877c3ce2a0de99b70f9cf0a7a9fe6166d0a9f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}