Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints
Abstract Accurately extracting organs from medical images provides radiologist with more comprehensive evidences to clinical diagnose, which offers up a higher accuracy and efficiency. However, the key to achieving accurate segmentation lies in abundant clues for contour distinction, which has a hig...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-86087-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594785988247552 |
|---|---|
| author | Fenghui Lian Yingjie Sun Meiyu Li |
| author_facet | Fenghui Lian Yingjie Sun Meiyu Li |
| author_sort | Fenghui Lian |
| collection | DOAJ |
| description | Abstract Accurately extracting organs from medical images provides radiologist with more comprehensive evidences to clinical diagnose, which offers up a higher accuracy and efficiency. However, the key to achieving accurate segmentation lies in abundant clues for contour distinction, which has a high demand for the network architecture design and its practical training status. To this end, we design auxiliary and refined constraints to optimize the energy function by supplying additional guidance in training procedure, thus promoting model’s ability to capture information. Specifically, for the auxiliary constraint, a set of convolutional structures are involved into a conventional network to act as a discriminator, then adversarial network is established. Based on the obtained architecture, we further build adversarial mechanism by introducing a second discriminator into segmentor for refinement. The involvement of refined constraint contributes to ameliorate training situation, optimize model performance, and boost its ability of collecting information for segmentation. We evaluate the proposed framework on two public databases (NIH Pancreas-CT and MICCAI Sliver07). Experimental results show that the proposed network achieves comparable performance to current pancreas segmentation algorithms and outperforms most state-of-the-art liver segmentation methods. The obtained results on public datasets sufficiently demonstrate the effectiveness of the proposed model for organ segmentation. |
| format | Article |
| id | doaj-art-ac676460765c4e7a9ca9a7b1d289f9aa |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-ac676460765c4e7a9ca9a7b1d289f9aa2025-01-19T12:20:02ZengNature PortfolioScientific Reports2045-23222025-01-0115111210.1038/s41598-025-86087-8Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraintsFenghui Lian0Yingjie Sun1Meiyu Li2School of Aviation Operations and Services, Air Force Aviation UniversitySchool of Aviation Operations and Services, Air Force Aviation UniversityDepartment of Rehabilitation Medicine, Tongren Hospital, Shanghai Jiao Tong University School of MedicineAbstract Accurately extracting organs from medical images provides radiologist with more comprehensive evidences to clinical diagnose, which offers up a higher accuracy and efficiency. However, the key to achieving accurate segmentation lies in abundant clues for contour distinction, which has a high demand for the network architecture design and its practical training status. To this end, we design auxiliary and refined constraints to optimize the energy function by supplying additional guidance in training procedure, thus promoting model’s ability to capture information. Specifically, for the auxiliary constraint, a set of convolutional structures are involved into a conventional network to act as a discriminator, then adversarial network is established. Based on the obtained architecture, we further build adversarial mechanism by introducing a second discriminator into segmentor for refinement. The involvement of refined constraint contributes to ameliorate training situation, optimize model performance, and boost its ability of collecting information for segmentation. We evaluate the proposed framework on two public databases (NIH Pancreas-CT and MICCAI Sliver07). Experimental results show that the proposed network achieves comparable performance to current pancreas segmentation algorithms and outperforms most state-of-the-art liver segmentation methods. The obtained results on public datasets sufficiently demonstrate the effectiveness of the proposed model for organ segmentation.https://doi.org/10.1038/s41598-025-86087-8Organ segmentationConvolutional neural networkAuxiliary constraintRefined constraint |
| spellingShingle | Fenghui Lian Yingjie Sun Meiyu Li Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints Scientific Reports Organ segmentation Convolutional neural network Auxiliary constraint Refined constraint |
| title | Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints |
| title_full | Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints |
| title_fullStr | Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints |
| title_full_unstemmed | Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints |
| title_short | Extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints |
| title_sort | extracting organs of interest from medical images based on convolutional neural network with auxiliary and refined constraints |
| topic | Organ segmentation Convolutional neural network Auxiliary constraint Refined constraint |
| url | https://doi.org/10.1038/s41598-025-86087-8 |
| work_keys_str_mv | AT fenghuilian extractingorgansofinterestfrommedicalimagesbasedonconvolutionalneuralnetworkwithauxiliaryandrefinedconstraints AT yingjiesun extractingorgansofinterestfrommedicalimagesbasedonconvolutionalneuralnetworkwithauxiliaryandrefinedconstraints AT meiyuli extractingorgansofinterestfrommedicalimagesbasedonconvolutionalneuralnetworkwithauxiliaryandrefinedconstraints |