Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning
Objective To construct an automatic segmentation model to segment female urine control anatomy on MRI images based on deep learning methods in order to improve the segmentation efficiency and accuracy. Methods A dataset comprising 49 female pelvic floor muscle MRI images [30 women with varying d...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Army Medical University
2025-07-01
|
| Series: | 陆军军医大学学报 |
| Subjects: | |
| Online Access: | https://aammt.tmmu.edu.cn/html/202406055.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849418723130081280 |
|---|---|
| author | ZHANG Ziqin WU Yi ZHANG Xiaoqin |
| author_facet | ZHANG Ziqin WU Yi ZHANG Xiaoqin |
| author_sort | ZHANG Ziqin |
| collection | DOAJ |
| description | Objective To construct an automatic segmentation model to segment female urine control anatomy on MRI images based on deep learning methods in order to improve the segmentation efficiency and accuracy. Methods A dataset comprising 49 female pelvic floor muscle MRI images [30 women with varying degrees of pelvic organ prolapse (POP) and 19 healthy individuals], obtained from Faculty of Biomedical Engineering and Medical Imaging in Army Medical University, was used for model training and testing. The dataset was split into a training set (17 normal cases and 22 POP cases) and a testing set (4 normal cases and 6 POP cases) in a ratio of 8∶2. The training set was used to train UNet, UNet+++, Dense UNet, and UNet++ models separately, and then input into each network. The model achieving the highest testing accuracy was selected as the backbone network. Results Under the training of UNet, UNet+++, Dense UNet, and UNet++, the 4 models achieved average Dice similarity coefficients of 61.82%, 57.94%, 57.63%, and 62.76%, respectively, for the segmentation of 5 anatomical structures (compressor urethrae, urethra sphincter body, bladder wall, bladder cavity and urethra submucosa). The corresponding Intersection over Union (IoU) score was 49.74%, 46.59%, 46.07%, and 49.44%, while the accuracy rate was 61.74%, 55.03%, 59.23%, and 61.91%, respectively for the 4 models. Notably, UNet++ consistently outperformed UNet, UNet+++, and Dense UNet across the 3 metrics, indicating that UNet++ achieved the highest overall segmentation accuracy. Conclusion In UNet, UNet++, Dense UNet and UNet++ for automatic segmentation of 5 female urine control anatomical elements, UNet++ achieves the best overall segmentation accuracy.
［Key words］ deep learning, image segmentation, intelligent assisted diagnosis, nuclear magnetic resonance image, |
| format | Article |
| id | doaj-art-9dc708f5209243139c94de3338ca8ab2 |
| institution | Kabale University |
| issn | 2097-0927 |
| language | zho |
| publishDate | 2025-07-01 |
| publisher | Editorial Office of Journal of Army Medical University |
| record_format | Article |
| series | 陆军军医大学学报 |
| spelling | doaj-art-9dc708f5209243139c94de3338ca8ab22025-08-20T03:32:23ZzhoEditorial Office of Journal of Army Medical University陆军军医大学学报2097-09272025-07-0147141568157610.16016/j.2097-0927.202406055Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learningZHANG Ziqin0WU Yi1ZHANG Xiaoqin2School of Mathematical Sciences， Chongqing Normal University， ChongqingDepartment of Digital Medicine， Faculty of Biomedical Engineering and Imaging Medicine， Army Medical University （Third Military Medical University）， ChongqingDepartment of Digital Medicine， Faculty of Biomedical Engineering and Imaging Medicine， Army Medical University （Third Military Medical University）， ChongqingObjective To construct an automatic segmentation model to segment female urine control anatomy on MRI images based on deep learning methods in order to improve the segmentation efficiency and accuracy. Methods A dataset comprising 49 female pelvic floor muscle MRI images [30 women with varying degrees of pelvic organ prolapse (POP) and 19 healthy individuals], obtained from Faculty of Biomedical Engineering and Medical Imaging in Army Medical University, was used for model training and testing. The dataset was split into a training set (17 normal cases and 22 POP cases) and a testing set (4 normal cases and 6 POP cases) in a ratio of 8∶2. The training set was used to train UNet, UNet+++, Dense UNet, and UNet++ models separately, and then input into each network. The model achieving the highest testing accuracy was selected as the backbone network. Results Under the training of UNet, UNet+++, Dense UNet, and UNet++, the 4 models achieved average Dice similarity coefficients of 61.82%, 57.94%, 57.63%, and 62.76%, respectively, for the segmentation of 5 anatomical structures (compressor urethrae, urethra sphincter body, bladder wall, bladder cavity and urethra submucosa). The corresponding Intersection over Union (IoU) score was 49.74%, 46.59%, 46.07%, and 49.44%, while the accuracy rate was 61.74%, 55.03%, 59.23%, and 61.91%, respectively for the 4 models. Notably, UNet++ consistently outperformed UNet, UNet+++, and Dense UNet across the 3 metrics, indicating that UNet++ achieved the highest overall segmentation accuracy. Conclusion In UNet, UNet++, Dense UNet and UNet++ for automatic segmentation of 5 female urine control anatomical elements, UNet++ achieves the best overall segmentation accuracy. ［Key words］ deep learning, image segmentation, intelligent assisted diagnosis, nuclear magnetic resonance image,https://aammt.tmmu.edu.cn/html/202406055.htmldeep learningimage segmentationintelligent assisted diagnosisnuclear magnetic resonance image |
| spellingShingle | ZHANG Ziqin WU Yi ZHANG Xiaoqin Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning 陆军军医大学学报 deep learning image segmentation intelligent assisted diagnosis nuclear magnetic resonance image |
| title | Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning |
| title_full | Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning |
| title_fullStr | Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning |
| title_full_unstemmed | Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning |
| title_short | Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning |
| title_sort | automatic segmentation of female urine control anatomical elements and related structures in mri images based on deep learning |
| topic | deep learning image segmentation intelligent assisted diagnosis nuclear magnetic resonance image |
| url | https://aammt.tmmu.edu.cn/html/202406055.html |
| work_keys_str_mv | AT zhangziqin automaticsegmentationoffemaleurinecontrolanatomicalelementsandrelatedstructuresinmriimagesbasedondeeplearning AT wuyi automaticsegmentationoffemaleurinecontrolanatomicalelementsandrelatedstructuresinmriimagesbasedondeeplearning AT zhangxiaoqin automaticsegmentationoffemaleurinecontrolanatomicalelementsandrelatedstructuresinmriimagesbasedondeeplearning |