# MA-Unet: An improved version of Unet based on multi-scale and attention mechanism for medical image segmentation

arXiv: https://arxiv.org/abs/2012.10952 · HTML: https://mlsanity.com/paper/2012.10952/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2107.05274/) (2021)
- [Contextual Attention Network: Transformer Meets U-Net](https://mlsanity.com/paper/2203.01932/) (2022)
- [MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder](https://mlsanity.com/paper/2310.19898/) (2023)
- [Channel prior convolutional attention for medical image segmentation](https://mlsanity.com/paper/2306.05196/) (2023)
- [Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain](https://mlsanity.com/paper/2402.06190/) (2024)
- [MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day](https://mlsanity.com/paper/2412.05888/) (2024)
- [Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention](https://mlsanity.com/paper/2506.18335/) (2025)
- [Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion](https://mlsanity.com/paper/2504.06158/) (2025)
- [Difference-Driven Gating: Adaptive Feature Fusion for U-Net Decoder](https://mlsanity.com/paper/2607.11096/) (2026)
- [Local-Global Temporal Fusion Network with an Attention Mechanism for Multiple and Multiclass Arrhythmia Classification](https://mlsanity.com/paper/2308.02416/) (2023)
- [Single Tensor Cell Segmentation using Scalar Field Representations](https://mlsanity.com/paper/2511.13947/) (2025)
- [HistoSeg++: Delving deeper with attention and multiscale feature fusion for biomarker segmentation](https://mlsanity.com/paper/2607.01675/) (2026)

## Abstract (arXiv)

Although convolutional neural networks (CNNs) are promoting the development of medical image semantic segmentation, the standard model still has some shortcomings. First, the feature mapping from the encoder and decoder sub-networks in the skip connection operation has a large semantic difference. Second, the remote feature dependence is not effectively modeled. Third, the global context information of different scales is ignored. In this paper, we try to eliminate semantic ambiguity in skip connection operations by adding attention gates (AGs), and use attention mechanisms to combine local features with their corresponding global dependencies, explicitly model the dependencies between channels and use multi-scale predictive fusion to utilize global information at different scales. Compared with other state-of-the-art segmentation networks, our model obtains better segmentation performance while introducing fewer parameters.