Journal Article10.1016/j.knosys.2022.109512
ConvUNeXt: An efficient convolution neural network for medical image segmentation
185
TL;DR: Wang et al. as mentioned in this paper improved the convolution block of UNet by using large convolution kernels and depth-wise separable convolution to considerably decrease the number of parameters; residual connections in both encoder and decoder are added and pooling is abandoned via adopting convolution for down-sampling; during skip connection, a lightweight attention mechanism is designed to filter out noise in low-level semantic information and suppress irrelevant features, so that the network can pay more attention to the target area.
read more
Abstract: Recently, ConvNeXts constructing from standard ConvNet modules has produced competitive performance in various image applications. In this paper, an efficient model based on the classical UNet, which can achieve promising results with a low number of parameters, is proposed for medical image segmentation. Inspired by ConvNeXt, the designed model is called ConvUNeXt and towards reduction in the amount of parameters while retaining outstanding segmentation superiority. Specifically, we firstly improved the convolution block of UNet by using large convolution kernels and depth-wise separable convolution to considerably decrease the number of parameters; then residual connections in both encoder and decoder are added and pooling is abandoned via adopting convolution for down-sampling; during skip connection, a lightweight attention mechanism is designed to filter out noise in low-level semantic information and suppress irrelevant features, so that the network can pay more attention to the target area. Compared to the standard UNet, our model has 20% fewer parameters, meanwhile, experimental results on different datasets show that it exhibits superior segmentation performance when the amount of data is scarce or sufficient. Code will be available at https://github.com/1914669687/ConvUNeXt.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives
TL;DR: A comprehensive review of the state-of-the-art Transformer-based approaches for medical imaging is presented in this paper , where the Transformer's key defining properties are compared with CNNs and its type of architecture, which specifies the manner in which the Transformers and CNN are combined.
Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
TL;DR: Li et al. as mentioned in this paper proposed Dual-distribution Discrepancy for Anomaly Detection (DDAD) based on one-class semi-supervised learning (OC-SSL) to utilize known normal and unlabeled images for training.
3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
Ho Hin Lee,Shunxing Bao,Yuankai Huo,Bennett A. Landman +3 more
- 29 Sep 2022
TL;DR: This work proposes a lightweight volumetric ConvNet, termed 3D UX-Net, which adapts the hierarchical transformer using ConvNet modules for robustvolumetric segmentation, and substitutes the multi-layer per-ceptron in Swin Transformer blocks with pointwise depth convolutions and enhance model performances with fewer normalization and activation layers, thus reducing the number of model parameters.
Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives
Jun Li,Junyu Chen,Yucheng Tang,Bennett A. Landman,S. Kevin Zhou +4 more
- 02 Jun 2022
TL;DR: A comprehensive review of the state-of-the-art Transformer-based approaches for medical imaging is presented in this paper , where the Transformer's key defining properties are compared with CNNs and its type of architecture, which specifies the manner in which the Transformers and CNN are combined.
40
AMSUnet: A neural network using atrous multi-scale convolution for medical image segmentation
TL;DR: AMSUnet as mentioned in this paper proposes a convolutional attention block AMS using atrous and multi-scale convolution, and redesigns the downsampling encoder based on this block, called AMSE.
37
References
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger,Philipp Fischer,Thomas Brox +2 more
- 05 Oct 2015
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
- 07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Densely Connected Convolutional Networks
Gao Huang,Zhuang Liu,Laurens van der Maaten,Kilian Q. Weinberger +3 more
- 21 Jul 2017
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.