Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net
PurposeTrigeminal neuralgia (TN) poses significant challenges in its diagnosis and treatment due to its extreme pain. Magnetic resonance imaging (MRI) plays a crucial role in diagnosing TN and understanding its pathogenesis. Manual delineation of the trigeminal nerve in volumetric images is time-con...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1265032/full |
| _version_ | 1797657505923334144 |
|---|---|
| author | Chuan Zhang Chuan Zhang Man Li Zheng Luo Ruhui Xiao Bing Li Jing Shi Chen Zeng BaiJinTao Sun Xiaoxue Xu Hanfeng Yang Hanfeng Yang |
| author_facet | Chuan Zhang Chuan Zhang Man Li Zheng Luo Ruhui Xiao Bing Li Jing Shi Chen Zeng BaiJinTao Sun Xiaoxue Xu Hanfeng Yang Hanfeng Yang |
| author_sort | Chuan Zhang |
| collection | DOAJ |
| description | PurposeTrigeminal neuralgia (TN) poses significant challenges in its diagnosis and treatment due to its extreme pain. Magnetic resonance imaging (MRI) plays a crucial role in diagnosing TN and understanding its pathogenesis. Manual delineation of the trigeminal nerve in volumetric images is time-consuming and subjective. This study introduces a Squeeze and Excitation with BottleNeck V-Net (SEVB-Net), a novel approach for the automatic segmentation of the trigeminal nerve in three-dimensional T2 MRI volumes.MethodsWe enrolled 88 patients with trigeminal neuralgia and 99 healthy volunteers, dividing them into training and testing groups. The SEVB-Net was designed for end-to-end training, taking three-dimensional T2 images as input and producing a segmentation volume of the same size. We assessed the performance of the basic V-Net, nnUNet, and SEVB-Net models by calculating the Dice similarity coefficient (DSC), sensitivity, precision, and network complexity. Additionally, we used the Mann–Whitney U test to compare the time required for manual segmentation and automatic segmentation with manual modification.ResultsIn the testing group, the experimental results demonstrated that the proposed method achieved state-of-the-art performance. SEVB-Net combined with the ωDoubleLoss loss function achieved a DSC ranging from 0.6070 to 0.7923. SEVB-Net combined with the ωDoubleLoss method and nnUNet combined with the DoubleLoss method, achieved DSC, sensitivity, and precision values exceeding 0.7. However, SEVB-Net significantly reduced the number of parameters (2.20 M), memory consumption (11.41 MB), and model size (17.02 MB), resulting in improved computation and forward time compared with nnUNet. The difference in average time between manual segmentation and automatic segmentation with manual modification for both radiologists was statistically significant (p < 0.001).ConclusionThe experimental results demonstrate that the proposed method can automatically segment the root and three main branches of the trigeminal nerve in three-dimensional T2 images. SEVB-Net, compared with the basic V-Net model, showed improved segmentation performance and achieved a level similar to nnUNet. The segmentation volumes of both SEVB-Net and nnUNet aligned with expert annotations but SEVB-Net displayed a more lightweight feature. |
| first_indexed | 2024-03-11T17:45:29Z |
| format | Article |
| id | doaj.art-0c02d4ec937843079e77ae9d8ebb0ca3 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-11T17:45:29Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-0c02d4ec937843079e77ae9d8ebb0ca32023-10-18T07:08:50ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-10-011710.3389/fnins.2023.12650321265032Deep learning-driven MRI trigeminal nerve segmentation with SEVB-netChuan Zhang0Chuan Zhang1Man Li2Zheng Luo3Ruhui Xiao4Bing Li5Jing Shi6Chen Zeng7BaiJinTao Sun8Xiaoxue Xu9Hanfeng Yang10Hanfeng Yang11The First Affiliated Hospital, Jinan University, Guangzhou, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaShanghai United Imaging Intelligence, Co., Ltd., Shanghai, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaThe First Affiliated Hospital, Jinan University, Guangzhou, ChinaDepartment of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, ChinaPurposeTrigeminal neuralgia (TN) poses significant challenges in its diagnosis and treatment due to its extreme pain. Magnetic resonance imaging (MRI) plays a crucial role in diagnosing TN and understanding its pathogenesis. Manual delineation of the trigeminal nerve in volumetric images is time-consuming and subjective. This study introduces a Squeeze and Excitation with BottleNeck V-Net (SEVB-Net), a novel approach for the automatic segmentation of the trigeminal nerve in three-dimensional T2 MRI volumes.MethodsWe enrolled 88 patients with trigeminal neuralgia and 99 healthy volunteers, dividing them into training and testing groups. The SEVB-Net was designed for end-to-end training, taking three-dimensional T2 images as input and producing a segmentation volume of the same size. We assessed the performance of the basic V-Net, nnUNet, and SEVB-Net models by calculating the Dice similarity coefficient (DSC), sensitivity, precision, and network complexity. Additionally, we used the Mann–Whitney U test to compare the time required for manual segmentation and automatic segmentation with manual modification.ResultsIn the testing group, the experimental results demonstrated that the proposed method achieved state-of-the-art performance. SEVB-Net combined with the ωDoubleLoss loss function achieved a DSC ranging from 0.6070 to 0.7923. SEVB-Net combined with the ωDoubleLoss method and nnUNet combined with the DoubleLoss method, achieved DSC, sensitivity, and precision values exceeding 0.7. However, SEVB-Net significantly reduced the number of parameters (2.20 M), memory consumption (11.41 MB), and model size (17.02 MB), resulting in improved computation and forward time compared with nnUNet. The difference in average time between manual segmentation and automatic segmentation with manual modification for both radiologists was statistically significant (p < 0.001).ConclusionThe experimental results demonstrate that the proposed method can automatically segment the root and three main branches of the trigeminal nerve in three-dimensional T2 images. SEVB-Net, compared with the basic V-Net model, showed improved segmentation performance and achieved a level similar to nnUNet. The segmentation volumes of both SEVB-Net and nnUNet aligned with expert annotations but SEVB-Net displayed a more lightweight feature.https://www.frontiersin.org/articles/10.3389/fnins.2023.1265032/fulltrigeminal neuralgiatrigeminal nervedeep learningautomatic segmentationmagnetic resonance imaging |
| spellingShingle | Chuan Zhang Chuan Zhang Man Li Zheng Luo Ruhui Xiao Bing Li Jing Shi Chen Zeng BaiJinTao Sun Xiaoxue Xu Hanfeng Yang Hanfeng Yang Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net Frontiers in Neuroscience trigeminal neuralgia trigeminal nerve deep learning automatic segmentation magnetic resonance imaging |
| title | Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net |
| title_full | Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net |
| title_fullStr | Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net |
| title_full_unstemmed | Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net |
| title_short | Deep learning-driven MRI trigeminal nerve segmentation with SEVB-net |
| title_sort | deep learning driven mri trigeminal nerve segmentation with sevb net |
| topic | trigeminal neuralgia trigeminal nerve deep learning automatic segmentation magnetic resonance imaging |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1265032/full |
| work_keys_str_mv | AT chuanzhang deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT chuanzhang deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT manli deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT zhengluo deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT ruhuixiao deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT bingli deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT jingshi deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT chenzeng deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT baijintaosun deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT xiaoxuexu deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT hanfengyang deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet AT hanfengyang deeplearningdrivenmritrigeminalnervesegmentationwithsevbnet |