Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines
We propose a semi-automatic algorithm for the segmentation of vertebral bodies in magnetic resonance (MR) images of the human lumbar spine. Quantitative analysis of spine MR images often necessitate segmentation of the image into specific regions representing anatomic structures of interest. Existin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/8/9/1586 |
| _version_ | 1818880063276318720 |
|---|---|
| author | Sewon Kim Won C. Bae Koichi Masuda Christine B. Chung Dosik Hwang |
| author_facet | Sewon Kim Won C. Bae Koichi Masuda Christine B. Chung Dosik Hwang |
| author_sort | Sewon Kim |
| collection | DOAJ |
| description | We propose a semi-automatic algorithm for the segmentation of vertebral bodies in magnetic resonance (MR) images of the human lumbar spine. Quantitative analysis of spine MR images often necessitate segmentation of the image into specific regions representing anatomic structures of interest. Existing algorithms for vertebral body segmentation require heavy inputs from the user, which is a disadvantage. For example, the user needs to define individual regions of interest (ROIs) for each vertebral body, and specify parameters for the segmentation algorithm. To overcome these drawbacks, we developed a semi-automatic algorithm that considerably reduces the need for user inputs. First, we simplified the ROI placement procedure by reducing the requirement to only one ROI, which includes a vertebral body; subsequently, a correlation algorithm is used to identify the remaining vertebral bodies and to automatically detect the ROIs. Second, the detected ROIs are adjusted to facilitate the subsequent segmentation process. Third, the segmentation is performed via graph-based and line-based segmentation algorithms. We tested our algorithm on sagittal MR images of the lumbar spine and achieved a 90% dice similarity coefficient, when compared with manual segmentation. Our new semi-automatic method significantly reduces the user’s role while achieving good segmentation accuracy. |
| first_indexed | 2024-12-19T14:40:00Z |
| format | Article |
| id | doaj.art-e3115e9e698243b8bcc7c84c6f8fa034 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-19T14:40:00Z |
| publishDate | 2018-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e3115e9e698243b8bcc7c84c6f8fa0342022-12-21T20:17:07ZengMDPI AGApplied Sciences2076-34172018-09-0189158610.3390/app8091586app8091586Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar SpinesSewon Kim0Won C. Bae1Koichi Masuda2Christine B. Chung3Dosik Hwang4School of Electrical and Electronic Engineering, Yonsei University, Seoul 06974, KoreaDepartment of Radiology, VA San Diego Healthcare System, San Diego, CA 92161-0114, USADepartment of Orthopedic Surgery, University of California-San Diego, La Jolla, CA 92037, USADepartment of Radiology, VA San Diego Healthcare System, San Diego, CA 92161-0114, USASchool of Electrical and Electronic Engineering, Yonsei University, Seoul 06974, KoreaWe propose a semi-automatic algorithm for the segmentation of vertebral bodies in magnetic resonance (MR) images of the human lumbar spine. Quantitative analysis of spine MR images often necessitate segmentation of the image into specific regions representing anatomic structures of interest. Existing algorithms for vertebral body segmentation require heavy inputs from the user, which is a disadvantage. For example, the user needs to define individual regions of interest (ROIs) for each vertebral body, and specify parameters for the segmentation algorithm. To overcome these drawbacks, we developed a semi-automatic algorithm that considerably reduces the need for user inputs. First, we simplified the ROI placement procedure by reducing the requirement to only one ROI, which includes a vertebral body; subsequently, a correlation algorithm is used to identify the remaining vertebral bodies and to automatically detect the ROIs. Second, the detected ROIs are adjusted to facilitate the subsequent segmentation process. Third, the segmentation is performed via graph-based and line-based segmentation algorithms. We tested our algorithm on sagittal MR images of the lumbar spine and achieved a 90% dice similarity coefficient, when compared with manual segmentation. Our new semi-automatic method significantly reduces the user’s role while achieving good segmentation accuracy.http://www.mdpi.com/2076-3417/8/9/1586semi-automatic segmentationMR spine imagevertebral bodygraph-based segmentationcorrelation |
| spellingShingle | Sewon Kim Won C. Bae Koichi Masuda Christine B. Chung Dosik Hwang Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines Applied Sciences semi-automatic segmentation MR spine image vertebral body graph-based segmentation correlation |
| title | Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines |
| title_full | Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines |
| title_fullStr | Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines |
| title_full_unstemmed | Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines |
| title_short | Semi-Automatic Segmentation of Vertebral Bodies in MR Images of Human Lumbar Spines |
| title_sort | semi automatic segmentation of vertebral bodies in mr images of human lumbar spines |
| topic | semi-automatic segmentation MR spine image vertebral body graph-based segmentation correlation |
| url | http://www.mdpi.com/2076-3417/8/9/1586 |
| work_keys_str_mv | AT sewonkim semiautomaticsegmentationofvertebralbodiesinmrimagesofhumanlumbarspines AT woncbae semiautomaticsegmentationofvertebralbodiesinmrimagesofhumanlumbarspines AT koichimasuda semiautomaticsegmentationofvertebralbodiesinmrimagesofhumanlumbarspines AT christinebchung semiautomaticsegmentationofvertebralbodiesinmrimagesofhumanlumbarspines AT dosikhwang semiautomaticsegmentationofvertebralbodiesinmrimagesofhumanlumbarspines |