Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation
Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentat...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/1/19 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588293102895104 |
|---|---|
| author | Haoran Wang Gengshen Wu Yi Liu |
| author_facet | Haoran Wang Gengshen Wu Yi Liu |
| author_sort | Haoran Wang |
| collection | DOAJ |
| description | Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model’s capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher performance on the Jaccard metric, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher on the Dice metric, and nearly <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet. |
| format | Article |
| id | doaj-art-a2230a0de5264610b84082018b2a5473 |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-a2230a0de5264610b84082018b2a54732025-01-24T13:36:17ZengMDPI AGJournal of Imaging2313-433X2025-01-011111910.3390/jimaging11010019Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image SegmentationHaoran Wang0Gengshen Wu1Yi Liu2Faculty of Data Science, City University of Macau, Avenida Padre Tomás Pereira Taipa, Macao 999078, ChinaFaculty of Data Science, City University of Macau, Avenida Padre Tomás Pereira Taipa, Macao 999078, ChinaSchool of Computer Science and Artificial Intelligence, Changzhou University, Changzhou 213000, ChinaManual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model’s capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher performance on the Jaccard metric, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher on the Dice metric, and nearly <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet.https://www.mdpi.com/2313-433X/11/1/19image segmentationmedical image analysisdeep learningattention mechanism |
| spellingShingle | Haoran Wang Gengshen Wu Yi Liu Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation Journal of Imaging image segmentation medical image analysis deep learning attention mechanism |
| title | Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation |
| title_full | Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation |
| title_fullStr | Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation |
| title_full_unstemmed | Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation |
| title_short | Efficient Generative-Adversarial U-Net for Multi-Organ Medical Image Segmentation |
| title_sort | efficient generative adversarial u net for multi organ medical image segmentation |
| topic | image segmentation medical image analysis deep learning attention mechanism |
| url | https://www.mdpi.com/2313-433X/11/1/19 |
| work_keys_str_mv | AT haoranwang efficientgenerativeadversarialunetformultiorganmedicalimagesegmentation AT gengshenwu efficientgenerativeadversarialunetformultiorganmedicalimagesegmentation AT yiliu efficientgenerativeadversarialunetformultiorganmedicalimagesegmentation |