{"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/voxresnet-deep-voxelwise-residual-networks","title":"VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation","arxiv_id":"1608.05895","date":"2016-08-21","proceeding":null,"authors":["Hao Chen","Qi Dou","Lequan Yu","Pheng-Ann Heng"],"abstract":"Recently deep residual learning with residual units for training very deep\nneural networks advanced the state-of-the-art performance on 2D image\nrecognition tasks, e.g., object detection and segmentation. However, how to\nfully leverage contextual representations for recognition tasks from volumetric\ndata has not been well studied, especially in the field of medical image\ncomputing, where a majority of image modalities are in volumetric format. In\nthis paper we explore the deep residual learning on the task of volumetric\nbrain segmentation. There are at least two main contributions in our work.\nFirst, we propose a deep voxelwise residual network, referred as VoxResNet,\nwhich borrows the spirit of deep residual learning in 2D image recognition\ntasks, and is extended into a 3D variant for handling volumetric data. Second,\nan auto-context version of VoxResNet is proposed by seamlessly integrating the\nlow-level image appearance features, implicit shape information and high-level\ncontext together for further improving the volumetric segmentation performance.\nExtensive experiments on the challenging benchmark of brain segmentation from\nmagnetic resonance (MR) images corroborated the efficacy of our proposed method\nin dealing with volumetric data. We believe this work unravels the potential of\n3D deep learning to advance the recognition performance on volumetric image\nsegmentation.","url_abs":"http://arxiv.org/abs/1608.05895v1","url_pdf":"http://arxiv.org/pdf/1608.05895v1.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":"voxresnet-deep-voxelwise-residual-networks","repo_url":"https://github.com/bo-10000/VoxResNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"voxresnet-deep-voxelwise-residual-networks","repo_url":"https://github.com/mediteamC/teamC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"voxresnet-deep-voxelwise-residual-networks","repo_url":"https://github.com/txin96/voxresnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"brain-segmentation","task_name":"Brain Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1608.05895","atlas_url":"https://app.syntology.ai/?focus=1608.05895","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}