{"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/segan-adversarial-network-with-multi-scale","title":"SegAN: Adversarial Network with Multi-scale $L_1$ Loss for Medical Image Segmentation","arxiv_id":"1706.01805","date":"2017-06-06","proceeding":null,"authors":["Yuan Xue","Tao Xu","Han Zhang","Rodney Long","Xiaolei Huang"],"abstract":"Inspired by classic generative adversarial networks (GAN), we propose a novel\nend-to-end adversarial neural network, called SegAN, for the task of medical\nimage segmentation. Since image segmentation requires dense, pixel-level\nlabeling, the single scalar real/fake output of a classic GAN's discriminator\nmay be ineffective in producing stable and sufficient gradient feedback to the\nnetworks. Instead, we use a fully convolutional neural network as the segmentor\nto generate segmentation label maps, and propose a novel adversarial critic\nnetwork with a multi-scale $L_1$ loss function to force the critic and\nsegmentor to learn both global and local features that capture long- and\nshort-range spatial relationships between pixels. In our SegAN framework, the\nsegmentor and critic networks are trained in an alternating fashion in a\nmin-max game: The critic takes as input a pair of images, (original_image $*$\npredicted_label_map, original_image $*$ ground_truth_label_map), and then is\ntrained by maximizing a multi-scale loss function; The segmentor is trained\nwith only gradients passed along by the critic, with the aim to minimize the\nmulti-scale loss function. We show that such a SegAN framework is more\neffective and stable for the segmentation task, and it leads to better\nperformance than the state-of-the-art U-net segmentation method. We tested our\nSegAN method using datasets from the MICCAI BRATS brain tumor segmentation\nchallenge. Extensive experimental results demonstrate the effectiveness of the\nproposed SegAN with multi-scale loss: on BRATS 2013 SegAN gives performance\ncomparable to the state-of-the-art for whole tumor and tumor core segmentation\nwhile achieves better precision and sensitivity for Gd-enhance tumor core\nsegmentation; on BRATS 2015 SegAN achieves better performance than the\nstate-of-the-art in both dice score and precision.","url_abs":"http://arxiv.org/abs/1706.01805v2","url_pdf":"http://arxiv.org/pdf/1706.01805v2.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":"segan-adversarial-network-with-multi-scale","repo_url":"https://github.com/YuanXue1993/SegAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"segan-adversarial-network-with-multi-scale","repo_url":"https://github.com/iNLyze/DeepLearning-SeGAN-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"brain-tumor-segmentation","task_name":"Brain Tumor Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"tumor-segmentation","task_name":"Tumor Segmentation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"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":[{"leaderboard":"/sota/brain-tumor-segmentation-on-brats-2013-1","task":"Brain Tumor Segmentation","dataset":"BRATS-2013 leaderboard","model":"SegAN","rank_in_archive_order":2,"of":2,"metrics":{"Dice Score":"0.84"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.01805","atlas_url":"https://app.syntology.ai/?focus=1706.01805","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1706.01805"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1706.01805\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1706.01805"},"call":"get_concepts_for_paper(arxiv_id=\"1706.01805\")"}],"by_repo":[{"repo":"YuanXue1993/SegAN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"iNLyze/DeepLearning-SeGAN-Segmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"a6a6a7c56fbd829cb3f897d4df13aa391bccb54ab46c7214cf2806ac392f990d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}