Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework
To develop an accurate segmentation model for the prostate and lesion area to help clinicians diagnose diseases, we propose a multi-encoder and decoder segmentation network, denoted Muled-Net, which can concurrently segment the prostate and lesion regions in an image. The model performs parallel cal...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10244203/ |
| _version_ | 1797674380396855296 |
|---|---|
| author | Chengjuan Ren Ziyu Guo Huipeng Ren Dongwon Jeong Dae-Kyoo Kim Shiyan Zhang Jiacheng Wang Guangnan Zhang |
| author_facet | Chengjuan Ren Ziyu Guo Huipeng Ren Dongwon Jeong Dae-Kyoo Kim Shiyan Zhang Jiacheng Wang Guangnan Zhang |
| author_sort | Chengjuan Ren |
| collection | DOAJ |
| description | To develop an accurate segmentation model for the prostate and lesion area to help clinicians diagnose diseases, we propose a multi-encoder and decoder segmentation network, denoted Muled-Net, which can concurrently segment the prostate and lesion regions in an image. The model performs parallel calculations for dual input. In two encoder branches of the model, a new transformer encoder is used to overcome the fact that only information from the neighborhood pixels can be captured, increasing the ability to capture global dependencies. Furthermore, given the usually small size of the lesion, ASPP and feature fusion are merged to expand the perceptual field and retain more contextual information of the shallow layer in decoder. To the best of our limited knowledge, there is no public dataset for the segmentation of the prostate and its lesion regions. So we made a publicly usable dataset. Muled-Net is compared with other deep learning methods, FCN, U-Net, U-Net++, and ResU-Net with four-fold cross-validation. Of all 218 subjects, 140 healthy individuals and 78 patients with prostate cancer were included in this work. Average Dice of 95%, Iou of 89%, sensitivity of 94%, 95HD of 9.56, and MSD of 0.66 are achieved for the prostate segmentation and average Dice of 89%, Iou of 82%, sensitivity of 92%, 95HD of 11.16, and MSD of 1.09 for the segmentation of the prostate lesion regions. The performance of the proposed model has made significant improvements to the segmentation of the lesion regions in particular, suggesting that the model could be considered as an auxiliary tool to ease the workload of physicians and help them in making treatment decisions. |
| first_indexed | 2024-03-11T21:58:13Z |
| format | Article |
| id | doaj.art-fec3e2798fc94cb99f3eefe24516e285 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T21:58:13Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fec3e2798fc94cb99f3eefe24516e2852023-09-25T23:00:23ZengIEEEIEEE Access2169-35362023-01-011110163010164310.1109/ACCESS.2023.331342010244203Prostate Segmentation in MRI Using Transformer Encoder and Decoder FrameworkChengjuan Ren0https://orcid.org/0009-0005-7866-4813Ziyu Guo1Huipeng Ren2Dongwon Jeong3Dae-Kyoo Kim4Shiyan Zhang5Jiacheng Wang6Guangnan Zhang7Guangdong Atv Academy for Performing Arts, Zhaoqing, ChinaDepartment of Computer Science and Engineering, The Chinese University of Hong Kong, HongKong, ChinaDepartment of Medical Imaging, Baoji Central Hospital, Baoji, ChinaSoftware Convergence Engineering Department, Kunsan National University, Gunsan, South KoreaComputer Science and Engineering Department, Oakland University, Michigan, MI, USASchool of Computer, Baoji University of Arts and Sciences, Baoji, ChinaSchool of Computer, Baoji University of Arts and Sciences, Baoji, ChinaSchool of Computer, Baoji University of Arts and Sciences, Baoji, ChinaTo develop an accurate segmentation model for the prostate and lesion area to help clinicians diagnose diseases, we propose a multi-encoder and decoder segmentation network, denoted Muled-Net, which can concurrently segment the prostate and lesion regions in an image. The model performs parallel calculations for dual input. In two encoder branches of the model, a new transformer encoder is used to overcome the fact that only information from the neighborhood pixels can be captured, increasing the ability to capture global dependencies. Furthermore, given the usually small size of the lesion, ASPP and feature fusion are merged to expand the perceptual field and retain more contextual information of the shallow layer in decoder. To the best of our limited knowledge, there is no public dataset for the segmentation of the prostate and its lesion regions. So we made a publicly usable dataset. Muled-Net is compared with other deep learning methods, FCN, U-Net, U-Net++, and ResU-Net with four-fold cross-validation. Of all 218 subjects, 140 healthy individuals and 78 patients with prostate cancer were included in this work. Average Dice of 95%, Iou of 89%, sensitivity of 94%, 95HD of 9.56, and MSD of 0.66 are achieved for the prostate segmentation and average Dice of 89%, Iou of 82%, sensitivity of 92%, 95HD of 11.16, and MSD of 1.09 for the segmentation of the prostate lesion regions. The performance of the proposed model has made significant improvements to the segmentation of the lesion regions in particular, suggesting that the model could be considered as an auxiliary tool to ease the workload of physicians and help them in making treatment decisions.https://ieeexplore.ieee.org/document/10244203/Diagnose diseasessegment prostatemulti-encoder and decoderfeature fusionASPP |
| spellingShingle | Chengjuan Ren Ziyu Guo Huipeng Ren Dongwon Jeong Dae-Kyoo Kim Shiyan Zhang Jiacheng Wang Guangnan Zhang Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework IEEE Access Diagnose diseases segment prostate multi-encoder and decoder feature fusion ASPP |
| title | Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework |
| title_full | Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework |
| title_fullStr | Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework |
| title_full_unstemmed | Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework |
| title_short | Prostate Segmentation in MRI Using Transformer Encoder and Decoder Framework |
| title_sort | prostate segmentation in mri using transformer encoder and decoder framework |
| topic | Diagnose diseases segment prostate multi-encoder and decoder feature fusion ASPP |
| url | https://ieeexplore.ieee.org/document/10244203/ |
| work_keys_str_mv | AT chengjuanren prostatesegmentationinmriusingtransformerencoderanddecoderframework AT ziyuguo prostatesegmentationinmriusingtransformerencoderanddecoderframework AT huipengren prostatesegmentationinmriusingtransformerencoderanddecoderframework AT dongwonjeong prostatesegmentationinmriusingtransformerencoderanddecoderframework AT daekyookim prostatesegmentationinmriusingtransformerencoderanddecoderframework AT shiyanzhang prostatesegmentationinmriusingtransformerencoderanddecoderframework AT jiachengwang prostatesegmentationinmriusingtransformerencoderanddecoderframework AT guangnanzhang prostatesegmentationinmriusingtransformerencoderanddecoderframework |