mlsanityData to 7 Oct 2026

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

arXiv 2210.13012 ↗First posted 24 Oct 2022eess.IV cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

U-Net and its extensions have achieved great success in medical image segmentation. However, due to the inherent local characteristics of ordinary convolution operations, U-Net encoder cannot effectively extract global context information. In addition, simple skip connections cannot capture salient features. In this work, we propose a fully convolutional segmentation network (CMU-Net) which incorporates hybrid convolutions and multi-scale attention gate. The ConvMixer module extracts global context information by mixing features at distant spatial locations. Moreover, the multi-scale attention gate emphasizes valuable features and achieves efficient skip connections. We evaluate the proposed method using both breast ultrasound datasets and a thyroid ultrasound image dataset; and CMU-Net achieves average Intersection over Union (IoU) values of 73.27% and 84.75%, and F1 scores of 84.81% and 91.71%. The code is available at https://github.com/FengheTan9/CMU-Net.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

13 of 17 references.

References · 13

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  8. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  9. 2020UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentationcited by 331
  10. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 319
  11. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  12. 2022Patches Are All You Need?cited by 201
1 more
  1. 2022UNeXt: MLP-based Rapid Medical Image Segmentation Networkcited by 185

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 6; 2025: 11; 2026: 7.

29 papers.

Sort:

By area:

  1. 2023CMUNeXt: An Efficient Medical Image Segmentation Network based on Large Kernel and Skip Fusioncited by 31
  2. 2024P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentationcited by 21
  3. 2024Spider: A Unified Framework for Context-dependent Concept Segmentationcited by 18
  4. 2023Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Modelcited by 8
  5. 2024Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenescited by 8
  6. 2026TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentationcited by 7
  7. 2025Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentationcited by 6
  8. 2025UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptationcited by 5
  9. 2023MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentationcited by 4
  10. 2023SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolutioncited by 4
  11. 2025Catheter Detection and Segmentation in X-ray Images via Multi-task Learningcited by 3
  12. 2024APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigationcited by 2
17 more
  1. 2025U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKVcited by 2
  2. 2025MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image Segmentationcited by 1
  3. 2025OWT: A Foundational Organ-Wise Tokenization Framework for Medical Imagingcited by 1
  4. 2025Is Exchangeability better than I.I.D to handle Data Distribution Shifts while Pooling Data for Data-scarce Medical image segmentation?cited by 1
  5. 2025CARE: Anti-entanglement Ultrasound Image Segmentation via Channel-Aware Region Extricationcited by 1
  6. 2025ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labelingcited by 1
  7. 2023Inspecting Model Fairness in Ultrasound Segmentation Taskscited by 0
  8. 2024Medical Visual Prompting (MVP): A Unified Framework for Versatile and High-Quality Medical Image Segmentationcited by 0
  9. 2024Vascular Segmentation of Functional Ultrasound Images using Deep Learningcited by 0
  10. 2025DCFFSNet: Deep Connectivity Feature Fusion Separation Network for Medical Image Segmentationcited by 0
  11. 20253D Reconstruction of Coronary Vessel Trees from Biplanar X-Ray Images Using a Geometric Approachcited by 0
  12. 2026Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentationcited by 0
  13. 2026PBE-UNet: A light weight Progressive Boundary-Enhanced U-Net with Scale-Aware Aggregation for Ultrasound Image Segmentationcited by 0
  14. 2026HTC-SGA Former: A Hybrid Transformer-CNN Network with Self-Guided Attention and a New Boundary-Weighted Adaptive Loss for Coronary DSA Vessel Segmentationcited by 0
  15. 2026APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigmscited by 0
  16. 2026Evolving Error States: Failure-Aware Progressive Repair for Ultrasound Lesion Segmentationcited by 0
  17. 2026LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decodercited by 0