{"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/h-denseunet-hybrid-densely-connected-unet-for","title":"H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes","arxiv_id":"1709.07330","date":"2017-09-21","proceeding":null,"authors":["Xiaomeng Li","Hao Chen","Xiaojuan Qi","Qi Dou","Chi-Wing Fu","Pheng Ann Heng"],"abstract":"Liver cancer is one of the leading causes of cancer death. To assist doctors\nin hepatocellular carcinoma diagnosis and treatment planning, an accurate and\nautomatic liver and tumor segmentation method is highly demanded in the\nclinical practice. Recently, fully convolutional neural networks (FCNs),\nincluding 2D and 3D FCNs, serve as the back-bone in many volumetric image\nsegmentation. However, 2D convolutions can not fully leverage the spatial\ninformation along the third dimension while 3D convolutions suffer from high\ncomputational cost and GPU memory consumption. To address these issues, we\npropose a novel hybrid densely connected UNet (H-DenseUNet), which consists of\na 2D DenseUNet for efficiently extracting intra-slice features and a 3D\ncounterpart for hierarchically aggregating volumetric contexts under the spirit\nof the auto-context algorithm for liver and tumor segmentation. We formulate\nthe learning process of H-DenseUNet in an end-to-end manner, where the\nintra-slice representations and inter-slice features can be jointly optimized\nthrough a hybrid feature fusion (HFF) layer. We extensively evaluated our\nmethod on the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge\nand 3DIRCADb Dataset. Our method outperformed other state-of-the-arts on the\nsegmentation results of tumors and achieved very competitive performance for\nliver segmentation even with a single model.","url_abs":"http://arxiv.org/abs/1709.07330v3","url_pdf":"http://arxiv.org/pdf/1709.07330v3.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":"h-denseunet-hybrid-densely-connected-unet-for","repo_url":"https://github.com/xmengli999/H-DenseUNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"h-denseunet-hybrid-densely-connected-unet-for","repo_url":"https://github.com/code-implementation1/Code9/tree/main/Unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"automatic-liver-and-tumor-segmentation","task_name":"Automatic Liver And Tumor Segmentation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"liver-segmentation","task_name":"Liver Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"tumor-segmentation","task_name":"Tumor Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lesion-segmentation-on-anatomical-tracings-of-1","task":"Lesion Segmentation","dataset":"Anatomical Tracings of Lesions After Stroke (ATLAS)","model":"2D Dense-UNet","rank_in_archive_order":2,"of":5,"metrics":{"Dice":"0.4741","IoU":"0.3559","Precision":"0.5613","Recall":"0.4875"},"uses_additional_data":false},{"leaderboard":"/sota/liver-segmentation-on-lits2017","task":"Liver Segmentation","dataset":"LiTS2017","model":"H-DenseUnet Liver","rank_in_archive_order":6,"of":9,"metrics":{"Dice":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/liver-segmentation-on-lits2017","task":"Liver Segmentation","dataset":"LiTS2017","model":"H-DenseUnet Lession","rank_in_archive_order":9,"of":9,"metrics":{"Dice":"82.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}