Paraspinal Muscle Segmentation Based on Deep Neural Network
The accurate segmentation of the paraspinal muscle in Magnetic Resonance (MR) images is a critical step in the automated analysis of lumbar diseases such as chronic low back pain, disc herniation and lumbar spinal stenosis. However, the automatic segmentation of multifidus and erector spinae has not...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/12/2650 |
| _version_ | 1818035849352183808 |
|---|---|
| author | Haixing Li Haibo Luo Yunpeng Liu |
| author_facet | Haixing Li Haibo Luo Yunpeng Liu |
| author_sort | Haixing Li |
| collection | DOAJ |
| description | The accurate segmentation of the paraspinal muscle in Magnetic Resonance (MR) images is a critical step in the automated analysis of lumbar diseases such as chronic low back pain, disc herniation and lumbar spinal stenosis. However, the automatic segmentation of multifidus and erector spinae has not yet been achieved due to three unusual challenges: (1) the muscle boundary is unclear; (2) the gray histogram distribution of the target overlaps with the background; (3) the intra- and inter-patient shape is variable. We propose to tackle the problem of the automatic segmentation of paravertebral muscles using a deformed U-net consisting of two main modules: the residual module and the feature pyramid attention (FPA) module. The residual module can directly return the gradient while preserving the details of the image to make the model easier to train. The FPA module fuses different scales of context information and provides useful salient features for high-level feature maps. In this paper, 120 cases were used for experiments, which were provided and labeled by the spine surgery department of Shengjing Hospital of China Medical University. The experimental results show that the model can achieve higher predictive capability. The dice coefficient of the multifidus is as high as 0.949, and the Hausdorff distance is 4.62 mm. The dice coefficient of the erector spinae is 0.913 and the Hausdorff distance is 7.89 mm. The work of this paper will contribute to the development of an automatic measurement system for paraspinal muscles, which is of great significance for the treatment of spinal diseases. |
| first_indexed | 2024-12-10T07:01:35Z |
| format | Article |
| id | doaj.art-a7c2fbae4c7c4f9dac697dcdca9cd684 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T07:01:35Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a7c2fbae4c7c4f9dac697dcdca9cd6842022-12-22T01:58:19ZengMDPI AGSensors1424-82202019-06-011912265010.3390/s19122650s19122650Paraspinal Muscle Segmentation Based on Deep Neural NetworkHaixing Li0Haibo Luo1Yunpeng Liu2Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaThe accurate segmentation of the paraspinal muscle in Magnetic Resonance (MR) images is a critical step in the automated analysis of lumbar diseases such as chronic low back pain, disc herniation and lumbar spinal stenosis. However, the automatic segmentation of multifidus and erector spinae has not yet been achieved due to three unusual challenges: (1) the muscle boundary is unclear; (2) the gray histogram distribution of the target overlaps with the background; (3) the intra- and inter-patient shape is variable. We propose to tackle the problem of the automatic segmentation of paravertebral muscles using a deformed U-net consisting of two main modules: the residual module and the feature pyramid attention (FPA) module. The residual module can directly return the gradient while preserving the details of the image to make the model easier to train. The FPA module fuses different scales of context information and provides useful salient features for high-level feature maps. In this paper, 120 cases were used for experiments, which were provided and labeled by the spine surgery department of Shengjing Hospital of China Medical University. The experimental results show that the model can achieve higher predictive capability. The dice coefficient of the multifidus is as high as 0.949, and the Hausdorff distance is 4.62 mm. The dice coefficient of the erector spinae is 0.913 and the Hausdorff distance is 7.89 mm. The work of this paper will contribute to the development of an automatic measurement system for paraspinal muscles, which is of great significance for the treatment of spinal diseases.https://www.mdpi.com/1424-8220/19/12/2650paraspinal musclessegmentationU-Netresidual moduleFPA module |
| spellingShingle | Haixing Li Haibo Luo Yunpeng Liu Paraspinal Muscle Segmentation Based on Deep Neural Network Sensors paraspinal muscles segmentation U-Net residual module FPA module |
| title | Paraspinal Muscle Segmentation Based on Deep Neural Network |
| title_full | Paraspinal Muscle Segmentation Based on Deep Neural Network |
| title_fullStr | Paraspinal Muscle Segmentation Based on Deep Neural Network |
| title_full_unstemmed | Paraspinal Muscle Segmentation Based on Deep Neural Network |
| title_short | Paraspinal Muscle Segmentation Based on Deep Neural Network |
| title_sort | paraspinal muscle segmentation based on deep neural network |
| topic | paraspinal muscles segmentation U-Net residual module FPA module |
| url | https://www.mdpi.com/1424-8220/19/12/2650 |
| work_keys_str_mv | AT haixingli paraspinalmusclesegmentationbasedondeepneuralnetwork AT haiboluo paraspinalmusclesegmentationbasedondeepneuralnetwork AT yunpengliu paraspinalmusclesegmentationbasedondeepneuralnetwork |