SACNet: A Spatially Adaptive Convolution Network for 2D Multi-organ Medical Segmentation
Not on the map. Why?
Abstract (arXiv)
Multi-organ segmentation in medical image analysis is crucial for diagnosis and treatment planning. However, many factors complicate the task, including variability in different target categories and interference from complex backgrounds. In this paper, we utilize the knowledge of Deformable Convolution V3 (DCNv3) and multi-object segmentation to optimize our Spatially Adaptive Convolution Network (SACNet) in three aspects: feature extraction, model architecture, and loss constraint, simultaneously enhancing the perception of different segmentation targets. Firstly, we propose the Adaptive Receptive Field Module (ARFM), which combines DCNv3 with a series of customized block-level and architecture-level designs similar to transformers. This module can capture the unique features of different organs by adaptively adjusting the receptive field according to various targets. Secondly, we utilize ARFM as building blocks to construct the encoder-decoder of SACNet and partially share parameters between the encoder and decoder, making the network wider rather than deeper. This design achieves a shared lightweight decoder and a more parameter-efficient and effective framework. Lastly, we propose a novel continuity dynamic adjustment loss function, based on t-vMF dice loss and cross-entropy loss, to better balance easy and complex classes in segmentation. Experiments on 3D slice datasets from ACDC and Synapse demonstrate that SACNet delivers superior segmentation performance in multi-organ segmentation tasks compared to several existing methods.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 14 Jul 2024.
Builds on
25 of 33 references.
References · 25
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
- 2017Deformable Convolutional Networkscited by 1,488
- 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
- 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
- 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
- 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
- 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
- 2022Vision Transformer with Deformable Attentioncited by 295
- 2020clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentationcited by 294
- 2021UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformercited by 197
13 more
- 2019MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentationcited by 195
- 2020Medical Image Segmentation Using Deep Learning: A Surveycited by 164
- 2021Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformerscited by 159
- 2021Mixed Transformer U-Net For Medical Image Segmentationcited by 95
- 2021Go Wider Instead of Deepercited by 57
- 2022TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentationcited by 43
- 2022TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Modelcited by 34
- 2023Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentationcited by 34
- 2022DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentationcited by 27
- 2023DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentationcited by 16
- 2022Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentationcited by 7
- 2023DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable Convolutioncited by 5
- 2024AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentationcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.