# Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation

arXiv: https://arxiv.org/abs/2003.05056 · HTML: https://mlsanity.com/paper/2003.05056/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2020.

## Built on by (most cited first, 23 of 23)

- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation](https://mlsanity.com/paper/2207.08518/) (2022)
- [TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation](https://mlsanity.com/paper/2208.00713/) (2022)
- [TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Model](https://mlsanity.com/paper/2207.13415/) (2022)
- [Contextual Attention Network: Transformer Meets U-Net](https://mlsanity.com/paper/2203.01932/) (2022)
- [SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities](https://mlsanity.com/paper/2204.02961/) (2022)
- [Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation](https://mlsanity.com/paper/2309.00121/) (2023)
- [DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2212.13504/) (2022)
- [Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation](https://mlsanity.com/paper/2210.16898/) (2022)
- [Medical Image Segmentation on MRI Images with Missing Modalities: A Review](https://mlsanity.com/paper/2203.06217/) (2022)
- [Multi-scale Regional Attention Deeplab3+: Multiple Myeloma Plasma Cells Segmentation in Microscopic Images](https://mlsanity.com/paper/2105.06238/) (2021)
- [Enhancing Medical Image Segmentation with TransCeption: A Multi-Scale Feature Fusion Approach](https://mlsanity.com/paper/2301.10847/) (2023)
- [SA2-Net: Scale-aware Attention Network for Microscopic Image Segmentation](https://mlsanity.com/paper/2309.16661/) (2023)
- [Small Lesion Segmentation in Brain MRIs with Subpixel Embedding](https://mlsanity.com/paper/2109.08791/) (2021)
- [LSSF-Net: Lightweight Segmentation with Self-Awareness, Spatial Attention, and Focal Modulation](https://mlsanity.com/paper/2409.01572/) (2024)
- [Intervertebral Disc Labeling With Learning Shape Information, A Look Once Approach](https://mlsanity.com/paper/2204.02943/) (2022)
- [Unlocking Fine-Grained Details with Wavelet-based High-Frequency Enhancement in Transformers](https://mlsanity.com/paper/2308.13442/) (2023)
- [Deep models for stroke segmentation: do complex architectures always perform better?](https://mlsanity.com/paper/2403.17177/) (2024)
- [RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation](https://mlsanity.com/paper/2307.06420/) (2023)
- [U-Net-based Models for Skin Lesion Segmentation: More Attention and Augmentation](https://mlsanity.com/paper/2210.16399/) (2022)
- [Only Positive Cases: 5-fold High-order Attention Interaction Model for Skin Segmentation Derived Classification](https://mlsanity.com/paper/2311.15625/) (2023)
- [A Region of Interest Focused Triple UNet Architecture for Skin Lesion Segmentation](https://mlsanity.com/paper/2311.12581/) (2023)
- [MDSkin-Net: Multi-Task Skin Lesion Analysis Driven by Pattern Analysis Priors and Spatial Alignment Regularization](https://mlsanity.com/paper/2609.30855/) (2026)

## Abstract (arXiv)

Medical image segmentation has been very challenging due to the large variation of anatomy across different cases. Recent advances in deep learning frameworks have exhibited faster and more accurate performance in 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 for medical image segmentation, in which we take full advantages of U-Net, Squeeze and Excitation (SE) block, bi-directional ConvLSTM (BConvLSTM), and the mechanism of dense convolutions. (I) We improve the segmentation performance by utilizing SE modules within the U-Net, with a minor effect on model complexity. These blocks adaptively recalibrate the channel-wise feature responses by utilizing a self-gating mechanism of the global information embedding of the feature maps. (II) To strengthen feature propagation and encourage feature reuse, we use densely connected convolutions in the last convolutional layer of the encoding path. (III) Instead of a simple concatenation in the skip connection of U-Net, we employ BConvLSTM in all levels of the network to combine the feature maps extracted from the corresponding encoding path and the previous decoding up-convolutional layer in a non-linear way. The proposed model is evaluated on six datasets DRIVE, ISIC 2017 and 2018, lung segmentation, PH2, and cell nuclei segmentation, achieving state-of-the-art performance.