CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network

• URL: http://arxiv.org/abs/2210.13012v2
• Date: Wed, 26 Oct 2022 05:51:59 GMT
• Title: CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network
• Authors: Fenghe Tang, Lingtao Wang, Chunping Ning, Min Xian, Jianrui Ding
• Abstract summary: We propose a full convolutional segmentation network (CMU-Net) which incorporate hybrid convolution and multi-scale attention gate. Evaluations on open-source breast ultrasound images and private thyroid ultrasound image datasets show that CMU-Net achieves an average IOU of 73.27% and 84.75%.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: U-Net and its extended segmentation model have achieved great success in medical image segmentation tasks. However, due to the inherent local characteristics of ordinary convolution operations, the encoder cannot effectively extract the global context information. In addition, simple skip connection cannot capture salient features. In this work, we propose a full convolutional segmentation network (CMU-Net) which incorporate hybrid convolution and multi-scale attention gate. The ConvMixer module is to mix distant spatial locations for extracting the global context information. Moreover, the multi-scale attention gate can help to emphasize valuable features and achieve efficient skip connections. Evaluations on open-source breast ultrasound images and private thyroid ultrasound image datasets show that CMU-Net achieves an average IOU of 73.27% and 84.75%, F1-value is 84.16% and 91.71%. The code is available at https://github.com/FengheTan9/CMU-Net.

Related papers

• DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation [5.114118320876544]
  We introduce UBBS-Net, a dual-branch deep neural network that learns the relationship between body and boundary for improved segmentation. We also propose a feature fusion module to integrate body and boundary information.
  arXiv  Detail & Related papers  (2024-11-17T16:14:00Z)
• LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections [27.473573286685063]
  We propose a remote-sensing image semantic segmentation network named LKASeg. LKASeg combines Large Kernel Attention(LSKA) and Full-Scale Skip Connections(FSC) On the ISPRS Vaihingen dataset, the mF1 and mIoU scores achieved 90.33% and 82.77%.
  arXiv  Detail & Related papers  (2024-10-14T12:25:48Z)
• Modifying the U-Net's Encoder-Decoder Architecture for Segmentation of Tumors in Breast Ultrasound Images [0.0]
  We propose a Neural Network (NN) based on U-Net and an encoder-decoder architecture. Our network (CResU-Net) obtained 82.88%, 77.5%, 90.3%, and 98.4% in terms of Dice similarity coefficients.
  arXiv  Detail & Related papers  (2024-09-01T07:47:48Z)
• EUIS-Net: A Convolutional Neural Network for Efficient Ultrasound Image Segmentation [12.84851020291695]
  EUIS-Net is a CNN network designed to segment ultrasound images efficiently and precisely. Four encoder-decoder blocks result in a notable decrease in computational complexity. The proposed EUIS-Net achieves mean IoU and dice scores of 78. 12%, 85. 42% and 84. 73%, 89. 01% in the BUSI and DDTI datasets, respectively.
  arXiv  Detail & Related papers  (2024-08-22T11:57:59Z)
• A Mutual Inclusion Mechanism for Precise Boundary Segmentation in Medical Images [2.9137615132901704]
  We present a novel deep learning-based approach, MIPC-Net, for precise boundary segmentation in medical images. We introduce the MIPC module, which enhances the focus on channel information when extracting position features. We also propose the GL-MIPC-Residue, a global residual connection that enhances the integration of the encoder and decoder.
  arXiv  Detail & Related papers  (2024-04-12T02:14:35Z)
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation [66.15246197473897]
  Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. We propose a textbfMulti-textbfinteractive textbfFeature learning architecture for image fusion and textbfSegmentation.
  arXiv  Detail & Related papers  (2023-08-04T01:03:58Z)
• MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet [55.16833099336073]
  We propose to self-distill a Transformer-based UNet for medical image segmentation. It simultaneously learns global semantic information and local spatial-detailed features. Our MISSU achieves the best performance over previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-02T07:38:53Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation [82.61182037130406]
  This work deals with medical image segmentation and in particular with accurate polyp detection and segmentation during colonoscopy examinations. Basic architecture in image segmentation consists of an encoder and a decoder. We compare some variant of the DeepLab architecture obtained by varying the decoder backbone.
  arXiv  Detail & Related papers  (2021-04-02T02:07:37Z)
• CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation [95.51455777713092]
  Convolutional neural networks (CNNs) have been the de facto standard for nowadays 3D medical image segmentation. We propose a novel framework that efficiently bridges a bf Convolutional neural network and a bf Transformer bf (CoTr) for accurate 3D medical image segmentation.
  arXiv  Detail & Related papers  (2021-03-04T13:34:22Z)
• KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation [71.79090083883403]
  "Traditional" encoder-decoder based approaches perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. We propose KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. The proposed method achieves a better performance as compared to all the recent methods with an additional benefit of fewer parameters and faster convergence.
  arXiv  Detail & Related papers  (2020-10-04T19:23:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.