{"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/combining-fully-convolutional-and-recurrent","title":"Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation","arxiv_id":"1609.01006","date":"2016-09-05","proceeding":"NeurIPS 2016 12","authors":["Jianxu Chen","Lin Yang","Yizhe Zhang","Mark Alber","Danny Z. Chen"],"abstract":"Segmentation of 3D images is a fundamental problem in biomedical image\nanalysis. Deep learning (DL) approaches have achieved state-of-the-art\nsegmentation perfor- mance. To exploit the 3D contexts using neural networks,\nknown DL segmentation methods, including 3D convolution, 2D convolution on\nplanes orthogonal to 2D image slices, and LSTM in multiple directions, all\nsuffer incompatibility with the highly anisotropic dimensions in common 3D\nbiomedical images. In this paper, we propose a new DL framework for 3D image\nsegmentation, based on a com- bination of a fully convolutional network (FCN)\nand a recurrent neural network (RNN), which are responsible for exploiting the\nintra-slice and inter-slice contexts, respectively. To our best knowledge, this\nis the first DL framework for 3D image segmentation that explicitly leverages\n3D image anisotropism. Evaluating using a dataset from the ISBI Neuronal\nStructure Segmentation Challenge and in-house image stacks for 3D fungus\nsegmentation, our approach achieves promising results comparing to the known\nDL-based 3D segmentation approaches.","url_abs":"http://arxiv.org/abs/1609.01006v2","url_pdf":"http://arxiv.org/pdf/1609.01006v2.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":"combining-fully-convolutional-and-recurrent","repo_url":"https://github.com/alvchn/fcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"combining-fully-convolutional-and-recurrent","repo_url":"https://github.com/shreyaspadhy/unet-zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-medical-imaging-segmentation","task_name":"3D Medical Imaging Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.01006","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}