A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images
Abstract Background The adrenal glands are small retroperitoneal organs, few reference standards exist for adrenal CT measurements in clinical practice. This study aims to develop a deep learning (DL) model for automated adrenal gland segmentation on non-contrast CT images, and to conduct a prelimin...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01682-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850042889359327232 |
|---|---|
| author | Fanxing Meng Tuo Zhang Yukun Pan Xiaojing Kan Yuwei Xia Mengyuan Xu Jin Cai Fangbin Liu Yinghui Ge |
| author_facet | Fanxing Meng Tuo Zhang Yukun Pan Xiaojing Kan Yuwei Xia Mengyuan Xu Jin Cai Fangbin Liu Yinghui Ge |
| author_sort | Fanxing Meng |
| collection | DOAJ |
| description | Abstract Background The adrenal glands are small retroperitoneal organs, few reference standards exist for adrenal CT measurements in clinical practice. This study aims to develop a deep learning (DL) model for automated adrenal gland segmentation on non-contrast CT images, and to conduct a preliminary large-scale study on age-related volume changes in normal adrenal glands using the model output values. Methods The model was trained and evaluated on a development dataset of annotated non-contrast CT scans of bilateral adrenal glands, utilizing nnU-Net for segmentation task. The ground truth was manually established by two experienced radiologists, and the model performance was assessed using the Dice similarity coefficient (DSC). Additionally, five radiologists provided annotations on a subset of 20 randomly selected cases to measure inter-observer variability. Following validation, the model was applied to a large-scale normal adrenal glands dataset to segment adrenal glands. Results The DL model development dataset contained 1301 CT examinations. In the test set, the median DSC scores for the segmentation model of left and right adrenal glands were 0.899 and 0.904 respectively, and in the independent test set were 0.900 and 0.896. Inter-observer DSC for radiologist manual segmentation did not differ from automated machine segmentation (P = 0.541). The large-scale normal adrenal glands dataset contained 2000 CT examinations, the graph shows that adrenal gland volume increases first and then decreases with age. Conclusion The developed DL model demonstrates accurate adrenal gland segmentation, and enables a comprehensive study of age-related adrenal gland volume variations. |
| format | Article |
| id | doaj-art-10f71d5b8e7148bc8bedcb772ff99407 |
| institution | DOAJ |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-10f71d5b8e7148bc8bedcb772ff994072025-08-20T02:55:24ZengBMCBMC Medical Imaging1471-23422025-05-012511910.1186/s12880-025-01682-5A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT imagesFanxing Meng0Tuo Zhang1Yukun Pan2Xiaojing Kan3Yuwei Xia4Mengyuan Xu5Jin Cai6Fangbin Liu7Yinghui Ge8Department of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityShanghai United Imaging Intelligence Co. LtdDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityDepartment of Radiology, Central China Subcenter of National Center for Cardiovascular Diseases, Fuwai Central-China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou UniversityAbstract Background The adrenal glands are small retroperitoneal organs, few reference standards exist for adrenal CT measurements in clinical practice. This study aims to develop a deep learning (DL) model for automated adrenal gland segmentation on non-contrast CT images, and to conduct a preliminary large-scale study on age-related volume changes in normal adrenal glands using the model output values. Methods The model was trained and evaluated on a development dataset of annotated non-contrast CT scans of bilateral adrenal glands, utilizing nnU-Net for segmentation task. The ground truth was manually established by two experienced radiologists, and the model performance was assessed using the Dice similarity coefficient (DSC). Additionally, five radiologists provided annotations on a subset of 20 randomly selected cases to measure inter-observer variability. Following validation, the model was applied to a large-scale normal adrenal glands dataset to segment adrenal glands. Results The DL model development dataset contained 1301 CT examinations. In the test set, the median DSC scores for the segmentation model of left and right adrenal glands were 0.899 and 0.904 respectively, and in the independent test set were 0.900 and 0.896. Inter-observer DSC for radiologist manual segmentation did not differ from automated machine segmentation (P = 0.541). The large-scale normal adrenal glands dataset contained 2000 CT examinations, the graph shows that adrenal gland volume increases first and then decreases with age. Conclusion The developed DL model demonstrates accurate adrenal gland segmentation, and enables a comprehensive study of age-related adrenal gland volume variations.https://doi.org/10.1186/s12880-025-01682-5Adrenal glandAdrenal gland segmentationnnU-NetNon-contrast CTDice similarity coefficient |
| spellingShingle | Fanxing Meng Tuo Zhang Yukun Pan Xiaojing Kan Yuwei Xia Mengyuan Xu Jin Cai Fangbin Liu Yinghui Ge A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images BMC Medical Imaging Adrenal gland Adrenal gland segmentation nnU-Net Non-contrast CT Dice similarity coefficient |
| title | A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images |
| title_full | A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images |
| title_fullStr | A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images |
| title_full_unstemmed | A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images |
| title_short | A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images |
| title_sort | deep learning algorithm for automated adrenal gland segmentation on non contrast ct images |
| topic | Adrenal gland Adrenal gland segmentation nnU-Net Non-contrast CT Dice similarity coefficient |
| url | https://doi.org/10.1186/s12880-025-01682-5 |
| work_keys_str_mv | AT fanxingmeng adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT tuozhang adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT yukunpan adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT xiaojingkan adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT yuweixia adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT mengyuanxu adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT jincai adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT fangbinliu adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT yinghuige adeeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT fanxingmeng deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT tuozhang deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT yukunpan deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT xiaojingkan deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT yuweixia deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT mengyuanxu deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT jincai deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT fangbinliu deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages AT yinghuige deeplearningalgorithmforautomatedadrenalglandsegmentationonnoncontrastctimages |