MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation
Abstract The UNet architecture, based on convolutional neural networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Re...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-12-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01671-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571140566941696 |
|---|---|
| author | Liang Xu Mingxiao Chen Yi Cheng Pengwu Song Pengfei Shao Shuwei Shen Peng Yao Ronald X. Xu |
| author_facet | Liang Xu Mingxiao Chen Yi Cheng Pengwu Song Pengfei Shao Shuwei Shen Peng Yao Ronald X. Xu |
| author_sort | Liang Xu |
| collection | DOAJ |
| description | Abstract The UNet architecture, based on convolutional neural networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this limitation by effectively capturing global feature correlations. However, the integration of the Transformer modules may result in the loss of local contextual information during the global feature fusion process. In this work, we propose a 2D medical image segmentation model called multi-scale cross perceptron attention network (MCPA). The MCPA consists of three main components: an encoder, a decoder, and a Cross Perceptron. The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales. The resulting multi-scale feature vectors are then spatially unfolded, concatenated, and fed through a Global Perceptron module to model global dependencies. Considering the high computational cost of using 3D neural network models, and the fact that many important clinical data can only be obtained in two dimensions, our MCPA focuses on 2D medical image segmentation. Furthermore, we introduce a progressive dual-branch structure (PDBS) to address the semantic segmentation of the image involving finer tissue structures. This structure gradually shifts the segmentation focus of MCPA network training from large-scale structural features to more sophisticated pixel-level features. We evaluate our proposed MCPA model on several publicly available medical image datasets from different tasks and devices, including the open large-scale dataset of CT (Synapse), MRI (ACDC), and widely used 2D medical imaging datasets captured by fundus camera (DRIVE, CHASE $$\_$$ _ DB1, HRF), and OCTA (ROSE). The experimental results show that our MCPA model achieves state-of-the-art performance. |
| format | Article |
| id | doaj-art-01017c3c84804c1fa8afe8d327547432 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-01017c3c84804c1fa8afe8d3275474322025-02-02T12:49:44ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-12-0111111610.1007/s40747-024-01671-1MCPA: multi-scale cross perceptron attention network for 2D medical image segmentationLiang Xu0Mingxiao Chen1Yi Cheng2Pengwu Song3Pengfei Shao4Shuwei Shen5Peng Yao6Ronald X. Xu7School of Biomedical Engineering Division of Life Sciences and Medicine, University of Science and Technology of ChinaDepartment of Precision Machinery and Precision Instrument, University of Science and Technology of ChinaDepartment of Precision Machinery and Precision Instrument, University of Science and Technology of ChinaSchool of Biomedical Engineering Division of Life Sciences and Medicine, University of Science and Technology of ChinaDepartment of Precision Machinery and Precision Instrument, University of Science and Technology of ChinaSchool of Biomedical Engineering Division of Life Sciences and Medicine, University of Science and Technology of ChinaSchool of Microelectronics, University of Science and Technology of ChinaSchool of Biomedical Engineering Division of Life Sciences and Medicine, University of Science and Technology of ChinaAbstract The UNet architecture, based on convolutional neural networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this limitation by effectively capturing global feature correlations. However, the integration of the Transformer modules may result in the loss of local contextual information during the global feature fusion process. In this work, we propose a 2D medical image segmentation model called multi-scale cross perceptron attention network (MCPA). The MCPA consists of three main components: an encoder, a decoder, and a Cross Perceptron. The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales. The resulting multi-scale feature vectors are then spatially unfolded, concatenated, and fed through a Global Perceptron module to model global dependencies. Considering the high computational cost of using 3D neural network models, and the fact that many important clinical data can only be obtained in two dimensions, our MCPA focuses on 2D medical image segmentation. Furthermore, we introduce a progressive dual-branch structure (PDBS) to address the semantic segmentation of the image involving finer tissue structures. This structure gradually shifts the segmentation focus of MCPA network training from large-scale structural features to more sophisticated pixel-level features. We evaluate our proposed MCPA model on several publicly available medical image datasets from different tasks and devices, including the open large-scale dataset of CT (Synapse), MRI (ACDC), and widely used 2D medical imaging datasets captured by fundus camera (DRIVE, CHASE $$\_$$ _ DB1, HRF), and OCTA (ROSE). The experimental results show that our MCPA model achieves state-of-the-art performance.https://doi.org/10.1007/s40747-024-01671-1Medical imageSegmentationMulti-scaleCross perceptronProgressive dual-branch structure |
| spellingShingle | Liang Xu Mingxiao Chen Yi Cheng Pengwu Song Pengfei Shao Shuwei Shen Peng Yao Ronald X. Xu MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation Complex & Intelligent Systems Medical image Segmentation Multi-scale Cross perceptron Progressive dual-branch structure |
| title | MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation |
| title_full | MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation |
| title_fullStr | MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation |
| title_full_unstemmed | MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation |
| title_short | MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation |
| title_sort | mcpa multi scale cross perceptron attention network for 2d medical image segmentation |
| topic | Medical image Segmentation Multi-scale Cross perceptron Progressive dual-branch structure |
| url | https://doi.org/10.1007/s40747-024-01671-1 |
| work_keys_str_mv | AT liangxu mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT mingxiaochen mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT yicheng mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT pengwusong mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT pengfeishao mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT shuweishen mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT pengyao mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation AT ronaldxxu mcpamultiscalecrossperceptronattentionnetworkfor2dmedicalimagesegmentation |