{"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/bi-directional-convlstm-u-net-with-densley","title":"Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions","arxiv_id":"1909.00166","date":"2019-08-31","proceeding":"In Proceedings of the IEEE/CVF international conference on computer vision workshops 2019 11","authors":["Reza Azad","Maryam Asadi-Aghbolaghi","Mahmood Fathy","Sergio Escalera"],"abstract":"In recent years, deep learning-based networks have achieved state-of-the-art performance in medical image segmentation. Among the existing networks, U-Net has been successfully applied on medical image segmentation. In this paper, we propose an extension of U-Net, Bi-directional ConvLSTM U-Net with Densely connected convolutions (BCDU-Net), for medical image segmentation, in which we take full advantages of U-Net, bi-directional ConvLSTM (BConvLSTM) and the mechanism of dense convolutions. Instead of a simple concatenation in the skip connection of U-Net, we employ BConvLSTM to combine the feature maps extracted from the corresponding encoding path and the previous decoding up-convolutional layer in a non-linear way. To strengthen feature propagation and encourage feature reuse, we use densely connected convolutions in the last convolutional layer of the encoding path. Finally, we can accelerate the convergence speed of the proposed network by employing batch normalization (BN). The proposed model is evaluated on three datasets of: retinal blood vessel segmentation, skin lesion segmentation, and lung nodule segmentation, achieving state-of-the-art performance.","url_abs":"https://arxiv.org/abs/1909.00166v1","url_pdf":"https://arxiv.org/pdf/1909.00166v1.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":"bi-directional-convlstm-u-net-with-densley","repo_url":"https://github.com/rezazad68/BCDU-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"bi-directional-convlstm-u-net-with-densley","repo_url":"https://github.com/CCChen19990820/Unet_Unetplusplus_BCDUnet_FRUnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"bi-directional-convlstm-u-net-with-densley","repo_url":"https://github.com/lyqcom/convlstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"bi-directional-convlstm-u-net-with-densley","repo_url":"https://github.com/mmheydari97/BCDU-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"lung-nodule-segmentation","task_name":"Lung Nodule 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":"skin-lesion-segmentation","task_name":"Skin Lesion Segmentation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convlstm","method_name":"ConvLSTM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lesion-segmentation-on-isic-2018","task":"Lesion Segmentation","dataset":"ISIC 2018","model":"BCDU-net","rank_in_archive_order":14,"of":17,"metrics":{"mean Dice":"0.847"},"uses_additional_data":false},{"leaderboard":"/sota/lesion-segmentation-on-isic-2018","task":"Lesion Segmentation","dataset":"ISIC 2018","model":"BCDU-Net (d=3)","rank_in_archive_order":17,"of":17,"metrics":{"F1-Score":"0.851"},"uses_additional_data":false},{"leaderboard":"/sota/lung-nodule-segmentation-on-luna","task":"Lung Nodule Segmentation","dataset":"LUNA","model":"BCDU-Net (d=3)","rank_in_archive_order":1,"of":5,"metrics":{"AUC":"0.9946","F1 score":"0.9904"},"uses_additional_data":false},{"leaderboard":"/sota/lung-nodule-segmentation-on-lung-nodule-1","task":"Lung Nodule Segmentation","dataset":"Lung Nodule","model":"BCDU-net","rank_in_archive_order":1,"of":1,"metrics":{"Dice Score":"0.994"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-drive-1","task":"Medical Image Segmentation","dataset":"DRIVE","model":"BCDU-net","rank_in_archive_order":5,"of":5,"metrics":{"F1 score":"0.8222"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-drive","task":"Retinal Vessel Segmentation","dataset":"DRIVE","model":"BCDU-Net (d=3)","rank_in_archive_order":13,"of":22,"metrics":{"AUC":"0.9789","F1 score":"0.8224"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}