Papers › Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions

Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions

31 Aug 2019In Proceedings of the IEEE/CVF international conference on computer vision workshops 2019 11arXiv:1909.00166archive 2025-07-28

Reza Azad, Maryam Asadi-Aghbolaghi, Mahmood Fathy, Sergio Escalera

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.

PaperPDFConference PDFCode

Code

rezazad68/BCDU-Net officialmentioned in papermentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image SegmentationLesion SegmentationLung Nodule SegmentationMedical Image SegmentationSegmentationSemantic SegmentationSkin Lesion Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation ISIC 2018 BCDU-net mean Dice 0.847 #14 of 17 Archive leaderboard report
Lesion Segmentation ISIC 2018 BCDU-Net (d=3) F1-Score 0.851 #17 of 17 Archive leaderboard report
Lung Nodule Segmentation LUNA BCDU-Net (d=3) AUC 0.9946 #1 of 5 Archive leaderboard report
Lung Nodule Segmentation LUNA BCDU-Net (d=3) F1 score 0.9904 #1 of 5 Archive leaderboard report
Lung Nodule Segmentation Lung Nodule BCDU-net Dice Score 0.994 #1 of 1 Archive leaderboard report
Medical Image Segmentation DRIVE BCDU-net F1 score 0.8222 #5 of 5 Archive leaderboard report
Retinal Vessel Segmentation DRIVE BCDU-Net (d=3) AUC 0.9789 #13 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE BCDU-Net (d=3) F1 score 0.8224 #13 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Batch NormalizationConcatenated Skip ConnectionConvLSTMConvolutionMax PoolingReLUSPEEDSigmoid ActivationTanh ActivationU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections