{"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/ce-net-context-encoder-network-for-2d-medical","title":"CE-Net: Context Encoder Network for 2D Medical Image Segmentation","arxiv_id":"1903.02740","date":"2019-03-07","proceeding":null,"authors":["Zaiwang Gu","Jun Cheng","Huazhu Fu","Kang Zhou","Huaying Hao","Yitian Zhao","Tianyang Zhang","Shenghua Gao","Jiang Liu"],"abstract":"Medical image segmentation is an important step in medical image analysis.\nWith the rapid development of convolutional neural network in image processing,\ndeep learning has been used for medical image segmentation, such as optic disc\nsegmentation, blood vessel detection, lung segmentation, cell segmentation,\netc. Previously, U-net based approaches have been proposed. However, the\nconsecutive pooling and strided convolutional operations lead to the loss of\nsome spatial information. In this paper, we propose a context encoder network\n(referred to as CE-Net) to capture more high-level information and preserve\nspatial information for 2D medical image segmentation. CE-Net mainly contains\nthree major components: a feature encoder module, a context extractor and a\nfeature decoder module. We use pretrained ResNet block as the fixed feature\nextractor. The context extractor module is formed by a newly proposed dense\natrous convolution (DAC) block and residual multi-kernel pooling (RMP) block.\nWe applied the proposed CE-Net to different 2D medical image segmentation\ntasks. Comprehensive results show that the proposed method outperforms the\noriginal U-Net method and other state-of-the-art methods for optic disc\nsegmentation, vessel detection, lung segmentation, cell contour segmentation\nand retinal optical coherence tomography layer segmentation.","url_abs":"http://arxiv.org/abs/1903.02740v1","url_pdf":"http://arxiv.org/pdf/1903.02740v1.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":"ce-net-context-encoder-network-for-2d-medical","repo_url":"https://github.com/Guzaiwang/CE-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ce-net-context-encoder-network-for-2d-medical","repo_url":"https://github.com/David-zaiwang/Image_segmentation_framework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ce-net-context-encoder-network-for-2d-medical","repo_url":"https://github.com/HzFu/MNet_DeepCDR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cell-segmentation","task_name":"Cell Segmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"optic-disc-segmentation","task_name":"Optic Disc Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"vessel-detection","task_name":"Vessel Detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lung-nodule-segmentation-on-luna","task":"Lung Nodule Segmentation","dataset":"LUNA","model":"CE-Net","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"0.99"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-isbi-2012-em","task":"Medical Image Segmentation","dataset":"ISBI 2012 EM Segmentation","model":"CE-Net","rank_in_archive_order":2,"of":3,"metrics":{"VInfo":"0.9878","VRand":"0.9743"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-drive","task":"Retinal Vessel Segmentation","dataset":"DRIVE","model":"CE-Net","rank_in_archive_order":15,"of":22,"metrics":{"AUC":"0.9779","Accuracy":"0.9545"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-1-dvc","task":"Retinal Vessel Segmentation","dataset":"ROSE-1 DVC","model":"CE-Net","rank_in_archive_order":5,"of":5,"metrics":{"Dice Score":"57.83"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-1-svc","task":"Retinal Vessel Segmentation","dataset":"ROSE-1 SVC","model":"CE-Net","rank_in_archive_order":3,"of":5,"metrics":{"Dice Score":"75.11"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-1-svc-dvc","task":"Retinal Vessel Segmentation","dataset":"ROSE-1 SVC-DVC","model":"CE-Net","rank_in_archive_order":4,"of":5,"metrics":{"Dice Score":"73.00"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-2","task":"Retinal Vessel Segmentation","dataset":"ROSE-2","model":"CE-Net","rank_in_archive_order":3,"of":5,"metrics":{"Dice Score":"70.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.02740","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}