Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance
Prostate diseases are very common in men. Accurate segmentation of the prostate plays a significant role in further clinical treatment and diagnosis. There have been some methods that combine the segmentation network and generative adversarial network, using the adversarial training to boost the per...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8932422/ |
| _version_ | 1818330173194371072 |
|---|---|
| author | Chengwei Su Renxiang Huang Chang Liu Tailang Yin Bo Du |
| author_facet | Chengwei Su Renxiang Huang Chang Liu Tailang Yin Bo Du |
| author_sort | Chengwei Su |
| collection | DOAJ |
| description | Prostate diseases are very common in men. Accurate segmentation of the prostate plays a significant role in further clinical treatment and diagnosis. There have been some methods that combine the segmentation network and generative adversarial network, using the adversarial training to boost the performance of segmentation network. However, the traditional adversarial training is unstable, which is hard to train. This attribute can easily lead to training failure. In this paper, we propose a segmentation network with self-attention adversarial training based on Wasserstein distance to tackle the problem. First, a segmentation network with residual connection and attention mechanism is deployed to generate the prostate segmentation prediction. Then, a self-attention discriminator network is added to the segmentation network to discriminate the prediction from ground truth. In the discriminator network, we replace the cross-entropy loss function with Wasserstein distance loss function which is better to measure the difference between distributions. The comparative experiments suggest our method is more stable than traditional adversarial training and achieves state-of-the-art performance. |
| first_indexed | 2024-12-13T12:59:44Z |
| format | Article |
| id | doaj.art-c3e0ecab32174c29b95ffb9abc676e17 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T12:59:44Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c3e0ecab32174c29b95ffb9abc676e172022-12-21T23:45:04ZengIEEEIEEE Access2169-35362019-01-01718427618428410.1109/ACCESS.2019.29596118932422Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein DistanceChengwei Su0https://orcid.org/0000-0003-1492-723XRenxiang Huang1https://orcid.org/0000-0003-3210-2717Chang Liu2https://orcid.org/0000-0002-1542-0257Tailang Yin3https://orcid.org/0000-0003-2032-0901Bo Du4https://orcid.org/0000-0002-0059-8458School of Computer Science, Wuhan University, Wuhan, ChinaGeography and Geology School, Eastern Michigan University, Ypsilanti, MI, USASchool of Computer Science, Wuhan University, Wuhan, ChinaRenmin Hospital, Wuhan University, Wuhan, ChinaSchool of Computer Science, Wuhan University, Wuhan, ChinaProstate diseases are very common in men. Accurate segmentation of the prostate plays a significant role in further clinical treatment and diagnosis. There have been some methods that combine the segmentation network and generative adversarial network, using the adversarial training to boost the performance of segmentation network. However, the traditional adversarial training is unstable, which is hard to train. This attribute can easily lead to training failure. In this paper, we propose a segmentation network with self-attention adversarial training based on Wasserstein distance to tackle the problem. First, a segmentation network with residual connection and attention mechanism is deployed to generate the prostate segmentation prediction. Then, a self-attention discriminator network is added to the segmentation network to discriminate the prediction from ground truth. In the discriminator network, we replace the cross-entropy loss function with Wasserstein distance loss function which is better to measure the difference between distributions. The comparative experiments suggest our method is more stable than traditional adversarial training and achieves state-of-the-art performance.https://ieeexplore.ieee.org/document/8932422/Medical image segmentationconvolution neural networksadversarial trainingself-attention mechanism |
| spellingShingle | Chengwei Su Renxiang Huang Chang Liu Tailang Yin Bo Du Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance IEEE Access Medical image segmentation convolution neural networks adversarial training self-attention mechanism |
| title | Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance |
| title_full | Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance |
| title_fullStr | Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance |
| title_full_unstemmed | Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance |
| title_short | Prostate MR Image Segmentation With Self-Attention Adversarial Training Based on Wasserstein Distance |
| title_sort | prostate mr image segmentation with self attention adversarial training based on wasserstein distance |
| topic | Medical image segmentation convolution neural networks adversarial training self-attention mechanism |
| url | https://ieeexplore.ieee.org/document/8932422/ |
| work_keys_str_mv | AT chengweisu prostatemrimagesegmentationwithselfattentionadversarialtrainingbasedonwassersteindistance AT renxianghuang prostatemrimagesegmentationwithselfattentionadversarialtrainingbasedonwassersteindistance AT changliu prostatemrimagesegmentationwithselfattentionadversarialtrainingbasedonwassersteindistance AT tailangyin prostatemrimagesegmentationwithselfattentionadversarialtrainingbasedonwassersteindistance AT bodu prostatemrimagesegmentationwithselfattentionadversarialtrainingbasedonwassersteindistance |