Automatic segmentation of ovarian follicles using deep neural network combined with edge information
Medical ultrasound imaging plays an important role in computer-aided diagnosis systems. In many cases, it is the preferred method of doctors for diagnosing diseases. Combined with computer vision technology, segmentation of ovarian ultrasound images can help doctors accurately judge diseases, reduce...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Reproductive Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frph.2022.877216/full |
| _version_ | 1798041938984697856 |
|---|---|
| author | Zhong Chen Changheng Zhang Zhou Li Jinkun Yang He Deng |
| author_facet | Zhong Chen Changheng Zhang Zhou Li Jinkun Yang He Deng |
| author_sort | Zhong Chen |
| collection | DOAJ |
| description | Medical ultrasound imaging plays an important role in computer-aided diagnosis systems. In many cases, it is the preferred method of doctors for diagnosing diseases. Combined with computer vision technology, segmentation of ovarian ultrasound images can help doctors accurately judge diseases, reduce doctors' workload, and improve doctors' work efficiency. However, accurate segmentation of an ovarian ultrasound image is a challenging task. On the one hand, there is a lot of speckle noise in ultrasound images; on the other hand, the edges of objects are blurred in ultrasound images. In order to segment the target accurately, we propose an ovarian follicles segmentation network combined with edge information. By adding an edge detection branch at the end of the network and taking the edge detection results as one of the losses of the network, we can accurately segment the ovarian follicles in an ultrasound image, making the segmentation results finer on the edge. Experiments show that the proposed network improves the segmentation accuracy of ovarian follicles, and that it has advantages over current algorithms. |
| first_indexed | 2024-04-11T22:28:34Z |
| format | Article |
| id | doaj.art-870d8ec3bca446aca7898e765246091d |
| institution | Directory Open Access Journal |
| issn | 2673-3153 |
| language | English |
| last_indexed | 2024-04-11T22:28:34Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Reproductive Health |
| spelling | doaj.art-870d8ec3bca446aca7898e765246091d2022-12-22T03:59:34ZengFrontiers Media S.A.Frontiers in Reproductive Health2673-31532022-08-01410.3389/frph.2022.877216877216Automatic segmentation of ovarian follicles using deep neural network combined with edge informationZhong Chen0Changheng Zhang1Zhou Li2Jinkun Yang3He Deng4National Key Laboratory of Science and Technology on Multi-Spectral Information Processing, Key Laboratory for Image Information Processing and Intelligence Control of Education Ministry, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, ChinaNational Key Laboratory of Science and Technology on Multi-Spectral Information Processing, Key Laboratory for Image Information Processing and Intelligence Control of Education Ministry, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, ChinaReproductive Medicine Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaNational Key Laboratory of Science and Technology on Multi-Spectral Information Processing, Key Laboratory for Image Information Processing and Intelligence Control of Education Ministry, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, ChinaMedical ultrasound imaging plays an important role in computer-aided diagnosis systems. In many cases, it is the preferred method of doctors for diagnosing diseases. Combined with computer vision technology, segmentation of ovarian ultrasound images can help doctors accurately judge diseases, reduce doctors' workload, and improve doctors' work efficiency. However, accurate segmentation of an ovarian ultrasound image is a challenging task. On the one hand, there is a lot of speckle noise in ultrasound images; on the other hand, the edges of objects are blurred in ultrasound images. In order to segment the target accurately, we propose an ovarian follicles segmentation network combined with edge information. By adding an edge detection branch at the end of the network and taking the edge detection results as one of the losses of the network, we can accurately segment the ovarian follicles in an ultrasound image, making the segmentation results finer on the edge. Experiments show that the proposed network improves the segmentation accuracy of ovarian follicles, and that it has advantages over current algorithms.https://www.frontiersin.org/articles/10.3389/frph.2022.877216/fullovarian follicle segmentationmedical image segmentationdeep neural networkdeep learningcomputer-aided diagnosis |
| spellingShingle | Zhong Chen Changheng Zhang Zhou Li Jinkun Yang He Deng Automatic segmentation of ovarian follicles using deep neural network combined with edge information Frontiers in Reproductive Health ovarian follicle segmentation medical image segmentation deep neural network deep learning computer-aided diagnosis |
| title | Automatic segmentation of ovarian follicles using deep neural network combined with edge information |
| title_full | Automatic segmentation of ovarian follicles using deep neural network combined with edge information |
| title_fullStr | Automatic segmentation of ovarian follicles using deep neural network combined with edge information |
| title_full_unstemmed | Automatic segmentation of ovarian follicles using deep neural network combined with edge information |
| title_short | Automatic segmentation of ovarian follicles using deep neural network combined with edge information |
| title_sort | automatic segmentation of ovarian follicles using deep neural network combined with edge information |
| topic | ovarian follicle segmentation medical image segmentation deep neural network deep learning computer-aided diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/frph.2022.877216/full |
| work_keys_str_mv | AT zhongchen automaticsegmentationofovarianfolliclesusingdeepneuralnetworkcombinedwithedgeinformation AT changhengzhang automaticsegmentationofovarianfolliclesusingdeepneuralnetworkcombinedwithedgeinformation AT zhouli automaticsegmentationofovarianfolliclesusingdeepneuralnetworkcombinedwithedgeinformation AT jinkunyang automaticsegmentationofovarianfolliclesusingdeepneuralnetworkcombinedwithedgeinformation AT hedeng automaticsegmentationofovarianfolliclesusingdeepneuralnetworkcombinedwithedgeinformation |