{"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/ra-unet-a-hybrid-deep-attention-aware-network","title":"RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans","arxiv_id":"1811.01328","date":"2018-11-04","proceeding":null,"authors":["Qiangguo Jin","Zhaopeng Meng","Changming Sun","Leyi Wei","Ran Su"],"abstract":"Automatic extraction of liver and tumor from CT volumes is a challenging task\ndue to their heterogeneous and diffusive shapes. Recently, 2D and 3D deep\nconvolutional neural networks have become popular in medical image segmentation\ntasks because of the utilization of large labeled datasets to learn\nhierarchical features. However, 3D networks have some drawbacks due to their\nhigh cost on computational resources. In this paper, we propose a 3D hybrid\nresidual attention-aware segmentation method, named RA-UNet, to precisely\nextract the liver volume of interests (VOI) and segment tumors from the liver\nVOI. The proposed network has a basic architecture as a 3D U-Net which extracts\ncontextual information combining low-level feature maps with high-level ones.\nAttention modules are stacked so that the attention-aware features change\nadaptively as the network goes \"very deep\" and this is made possible by\nresidual learning. This is the first work that an attention residual mechanism\nis used to process medical volumetric images. We evaluated our framework on the\npublic MICCAI 2017 Liver Tumor Segmentation dataset and the 3DIRCADb dataset.\nThe results show that our architecture outperforms other state-of-the-art\nmethods. We also extend our RA-UNet to brain tumor segmentation on the\nBraTS2018 and BraTS2017 datasets, and the results indicate that RA-UNet\nachieves good performance on a brain tumor segmentation task as well.","url_abs":"http://arxiv.org/abs/1811.01328v1","url_pdf":"http://arxiv.org/pdf/1811.01328v1.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":"ra-unet-a-hybrid-deep-attention-aware-network","repo_url":"https://github.com/RanSuLab/RAUNet-tumor-segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"brain-tumor-segmentation","task_name":"Brain Tumor Segmentation"},{"task_slug":"deep-attention","task_name":"Deep Attention"},{"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":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}