DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation
Abstract In recent years, convolutional neural networks (CNN)‐based automatic segmentation of medical images has become one of the hot topics in clinical disease diagnosis. It is still a challenging task to improve the segmentation accuracy of the network model with the large variation of pathologic...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-11-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12904 |
| _version_ | 1827770938555367424 |
|---|---|
| author | Qiulang Ji Jihong Wang Caifu Ding Yuhang Wang Wen Zhou Zijie Liu Chen Yang |
| author_facet | Qiulang Ji Jihong Wang Caifu Ding Yuhang Wang Wen Zhou Zijie Liu Chen Yang |
| author_sort | Qiulang Ji |
| collection | DOAJ |
| description | Abstract In recent years, convolutional neural networks (CNN)‐based automatic segmentation of medical images has become one of the hot topics in clinical disease diagnosis. It is still a challenging task to improve the segmentation accuracy of the network model with the large variation of pathological regions in different patients and the fuzzy boundary of pathological regions. A Dual‐path Multi‐scale Attention Guided network (DMAGNet) for medical image segmentation is proposed in this paper. First, the Dual‐path Multi‐scale Attention Fusion Module (DMAF) is proposed as a novel skip connection strategy, which is applied to encode semantic dependencies between high‐level and low‐level channels. Second, the Multi‐scale Normalized Channel Attention Module (MNCA) based on the atrous convolution, normalization channel attention mechanism, and the Depthwise Separable Convolutions (DSConv) is developed to strengthen dependencies between channels. Finally, the encoder–decoder backbone employs the DSConv, as well as the pretrained Resnet34 block is combined in the encoder part to further improve the backbone network performance. Comprehensive experiments on brain, lung, and liver segmentation tasks show that the proposed DMAGNet outperforms the original U‐Net method and other advanced methods. |
| first_indexed | 2024-03-11T12:46:31Z |
| format | Article |
| id | doaj.art-4a95f673ce5b434c92e0b781bc396c92 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-03-11T12:46:31Z |
| publishDate | 2023-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-4a95f673ce5b434c92e0b781bc396c922023-11-05T03:33:28ZengWileyIET Image Processing1751-96591751-96672023-11-0117133631364410.1049/ipr2.12904DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentationQiulang Ji0Jihong Wang1Caifu Ding2Yuhang Wang3Wen Zhou4Zijie Liu5Chen Yang6Power Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaPower Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaPower Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaPower Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaPower Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaPower Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaPower Systems Engineering Research Center Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang ChinaAbstract In recent years, convolutional neural networks (CNN)‐based automatic segmentation of medical images has become one of the hot topics in clinical disease diagnosis. It is still a challenging task to improve the segmentation accuracy of the network model with the large variation of pathological regions in different patients and the fuzzy boundary of pathological regions. A Dual‐path Multi‐scale Attention Guided network (DMAGNet) for medical image segmentation is proposed in this paper. First, the Dual‐path Multi‐scale Attention Fusion Module (DMAF) is proposed as a novel skip connection strategy, which is applied to encode semantic dependencies between high‐level and low‐level channels. Second, the Multi‐scale Normalized Channel Attention Module (MNCA) based on the atrous convolution, normalization channel attention mechanism, and the Depthwise Separable Convolutions (DSConv) is developed to strengthen dependencies between channels. Finally, the encoder–decoder backbone employs the DSConv, as well as the pretrained Resnet34 block is combined in the encoder part to further improve the backbone network performance. Comprehensive experiments on brain, lung, and liver segmentation tasks show that the proposed DMAGNet outperforms the original U‐Net method and other advanced methods.https://doi.org/10.1049/ipr2.12904codecsconvolutional neural netsimage processingimage segmentation |
| spellingShingle | Qiulang Ji Jihong Wang Caifu Ding Yuhang Wang Wen Zhou Zijie Liu Chen Yang DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation IET Image Processing codecs convolutional neural nets image processing image segmentation |
| title | DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation |
| title_full | DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation |
| title_fullStr | DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation |
| title_full_unstemmed | DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation |
| title_short | DMAGNet: Dual‐path multi‐scale attention guided network for medical image segmentation |
| title_sort | dmagnet dual path multi scale attention guided network for medical image segmentation |
| topic | codecs convolutional neural nets image processing image segmentation |
| url | https://doi.org/10.1049/ipr2.12904 |
| work_keys_str_mv | AT qiulangji dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation AT jihongwang dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation AT caifuding dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation AT yuhangwang dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation AT wenzhou dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation AT zijieliu dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation AT chenyang dmagnetdualpathmultiscaleattentionguidednetworkformedicalimagesegmentation |