File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3390/diagnostics13050817
- Scopus: eid_2-s2.0-85149784337
- WOS: WOS:000947466300001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Deep Learning-Based Auto-Segmentation of Spinal Cord Internal Structure of Diffusion Tensor Imaging in Cervical Spondylotic Myelopathy
Title | Deep Learning-Based Auto-Segmentation of Spinal Cord Internal Structure of Diffusion Tensor Imaging in Cervical Spondylotic Myelopathy |
---|---|
Authors | |
Keywords | cervical spondylotic myelopathy (CSM) deep learning diffusion tensor imaging (DTI) fractional anisotropy (FA) image segmentation |
Issue Date | 21-Feb-2023 |
Publisher | MDPI |
Citation | Diagnostics, 2023, v. 13, n. 5 How to Cite? |
Abstract | Cervical spondylotic myelopathy (CSM) is a chronic disorder of the spinal cord. ROI-based features on diffusion tensor imaging (DTI) provide additional information about spinal cord status, which would benefit the diagnosis and prognosis of CSM. However, the manual extraction of the DTI-related features on multiple ROIs is time-consuming and laborious. In total, 1159 slices at cervical levels from 89 CSM patients were analyzed, and corresponding fractional anisotropy (FA) maps were calculated. Eight ROIs were drawn, covering both sides of lateral, dorsal, ventral, and gray matter. The UNet model was trained with the proposed heatmap distance loss for auto-segmentation. Mean Dice coefficients on the test dataset for dorsal, lateral, and ventral column and gray matter were 0.69, 0.67, 0.57, 0.54 on the left side and 0.68, 0.67, 0.59, 0.55 on the right side. The ROI-based mean FA value based on segmentation model strongly correlated with the value based on manual drawing. The percentages of the mean absolute error between the two values of multiple ROIs were 0.07, 0.07, 0.11, and 0.08 on the left side and 0.07, 0.1, 0.1, 0.11, and 0.07 on the right side. The proposed segmentation model has the potential to offer a more detailed spinal cord segmentation and would be beneficial for quantifying a more detailed status of the cervical spinal cord. Keywords: diffusion tensor imaging (DTI); image segmentation; deep learning; fractional anisotropy (FA); cervical spondylotic myelopathy (CSM) |
Persistent Identifier | http://hdl.handle.net/10722/337329 |
ISSN | 2023 Impact Factor: 3.0 2023 SCImago Journal Rankings: 0.667 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fei, Ningbo | - |
dc.contributor.author | Li, Guangsheng | - |
dc.contributor.author | Wang, Xuxiang | - |
dc.contributor.author | Li, Junpeng | - |
dc.contributor.author | Hu, Xiaosong | - |
dc.contributor.author | Hu, Yong | - |
dc.date.accessioned | 2024-03-11T10:20:02Z | - |
dc.date.available | 2024-03-11T10:20:02Z | - |
dc.date.issued | 2023-02-21 | - |
dc.identifier.citation | Diagnostics, 2023, v. 13, n. 5 | - |
dc.identifier.issn | 2075-4418 | - |
dc.identifier.uri | http://hdl.handle.net/10722/337329 | - |
dc.description.abstract | <p>Cervical spondylotic myelopathy (CSM) is a chronic disorder of the spinal cord. ROI-based features on diffusion tensor imaging (DTI) provide additional information about spinal cord status, which would benefit the diagnosis and prognosis of CSM. However, the manual extraction of the DTI-related features on multiple ROIs is time-consuming and laborious. In total, 1159 slices at cervical levels from 89 CSM patients were analyzed, and corresponding fractional anisotropy (FA) maps were calculated. Eight ROIs were drawn, covering both sides of lateral, dorsal, ventral, and gray matter. The UNet model was trained with the proposed heatmap distance loss for auto-segmentation. Mean Dice coefficients on the test dataset for dorsal, lateral, and ventral column and gray matter were 0.69, 0.67, 0.57, 0.54 on the left side and 0.68, 0.67, 0.59, 0.55 on the right side. The ROI-based mean FA value based on segmentation model strongly correlated with the value based on manual drawing. The percentages of the mean absolute error between the two values of multiple ROIs were 0.07, 0.07, 0.11, and 0.08 on the left side and 0.07, 0.1, 0.1, 0.11, and 0.07 on the right side. The proposed segmentation model has the potential to offer a more detailed spinal cord segmentation and would be beneficial for quantifying a more detailed status of the cervical spinal cord.</p><p>Keywords: </p><p><a href="https://www.mdpi.com/search?q=diffusion+tensor+imaging+%28DTI%29">diffusion tensor imaging (DTI)</a>; <a href="https://www.mdpi.com/search?q=image+segmentation">image segmentation</a>; <a href="https://www.mdpi.com/search?q=deep+learning">deep learning</a>; <a href="https://www.mdpi.com/search?q=fractional+anisotropy+%28FA%29">fractional anisotropy (FA)</a>; <a href="https://www.mdpi.com/search?q=cervical+spondylotic+myelopathy+%28CSM%29">cervical spondylotic myelopathy (CSM)</a></p> | - |
dc.language | eng | - |
dc.publisher | MDPI | - |
dc.relation.ispartof | Diagnostics | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | cervical spondylotic myelopathy (CSM) | - |
dc.subject | deep learning | - |
dc.subject | diffusion tensor imaging (DTI) | - |
dc.subject | fractional anisotropy (FA) | - |
dc.subject | image segmentation | - |
dc.title | Deep Learning-Based Auto-Segmentation of Spinal Cord Internal Structure of Diffusion Tensor Imaging in Cervical Spondylotic Myelopathy | - |
dc.type | Article | - |
dc.identifier.doi | 10.3390/diagnostics13050817 | - |
dc.identifier.scopus | eid_2-s2.0-85149784337 | - |
dc.identifier.volume | 13 | - |
dc.identifier.issue | 5 | - |
dc.identifier.eissn | 2075-4418 | - |
dc.identifier.isi | WOS:000947466300001 | - |
dc.identifier.issnl | 2075-4418 | - |