journal article·2020-02-18Open access

Spinal Cord Segmentation in Ultrasound Medical Imagery

Bilel Benjdira, Kais Ouni, Mohamad M. Al Rahhal, Abdulrahman Albakr, Amro Al-Habib, Emad Mahrous

Applied Sciences· Volume 10· Issue 4

Abstract

In this paper, we study and evaluate the task of semantic segmentation of the spinal cord in ultrasound medical imagery. This task is useful for neurosurgeons to analyze the spinal cord movement during and after the laminectomy surgical operation. Laminectomy is performed on patients that suffer from an abnormal pressure made on the spinal cord. The surgeon operates by cutting the bones of the laminae and the intervening ligaments to relieve this pressure. During the surgery, ultrasound waves can pass through the laminectomy area to give real-time exploitable images of the spinal cord. The surgeon uses them to confirm spinal cord decompression or, occasionally, to assess a tumor adjacent to the spinal cord. The Freely pulsating spinal cord is a sign of adequate decompression. To evaluate the semantic segmentation approaches chosen in this study, we constructed two datasets using images collected from 10 different patients performing the laminectomy surgery. We found that the best solution for this task is Fully Convolutional DenseNets if the spinal cord is already in the train set. If the spinal cord does not exist in the train set, U-Net is the best. We also studied the effect of integrating inside both models some deep learning components like Atrous Spatial Pyramid Pooling (ASPP) and Depthwise Separable Convolution (DSC). We added a post-processing step and detailed the configurations to set for both models.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Medical Imaging and Analysis · Advanced Neural Network Applications · Artificial Intelligence in Healthcare and Education

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Robotics and Internet of Things Laboratory, College of Computer and Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia

Research Laboratory Smart Electricity & ICT, SEICT, LR18ES44, National Engineering School of Carthage, University of Carthage, Charguia II Tunis-Carthage 2035, Tunisia

Information System Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia

Departments of Neurosurgery, University of Calgary, Foothills Medical Center, Calgary, AB T2N 1N4, Canada

Division of Neurosurgery, Department of Surgery, College of Medicine, King Saud University, Riyadh 11472, Saudi Arabia

Raytheon Chair for Systems Engineering (RCSE Chair), Advanced Manufacturing Institute, King Saud University, Riyadh 11451, Saudi Arabia

Electrical Engineering Department, College of Engineering, King Saud University, P.O. Box 800, Riyadh 11421, Saudi Arabia

Funding

Prince Sultan University · Raytheon Chair for Systems Engineering (RCSE)

References (41)

Show source-provided references
1. Automatic measurement of spine curvature on 3-D ultrasound volume projection image with phase features10.1109/TMI.2017.2674681 ↗
2. (2019, April 23). Encyclopaedia Brittanica. Available online: https://www.britannica.com.
3. (2019, April 23). Virgina Spine Institute. Available online: https://www.spinemd.com/treatments/laminoplasty.
4. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
5. Real-time transverse process detection in ultrasound
6. Step-wise identification of ultrasound-visible anatomical landmarks for 3D visualization of scoliotic spine
7. Navigated 3-Dimensional Intraoperative Ultrasound for Spine Surgery10.1016/j.wneu.2019.07.188 ↗
8. Ultrasonographic quantification of spinal cord and dural pulsations during cervical laminoplasty in patients with compressive myelopathy10.1007/s00586-012-2430-9 ↗
9. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, MIT Press.
10. Benjdira, B., Bazi, Y., Koubaa, A., and Ouni, K. (2019). Unsupervised Domain Adaptation Using Generative Adversarial Networks for Semantic Segmentation of Aerial Images. Remote Sens., 11.10.3390/rs11111369 ↗
11. Benjdira, B., Khursheed, T., Koubaa, A., Ammar, A., and Ouni, K. (2019, January 5–8). Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3. Proceedings of the 2019 1st International Conference on Unmanned Vehicle Systems-Oman (UVS), Muscat, Oman.10.1109/UVS.2019.8658300 ↗
12. Convolutional neural networks for electrocardiogram classification10.1007/s40846-018-0389-7 ↗
13. Ammour, N., Alhichri, H., Bazi, Y., Benjdira, B., Alajlan, N., and Zuair, M. (2017). Deep learning approach for car detection in UAV imagery. Remote Sens., 9.10.3390/rs9040312 ↗
14. Benjdira, B., Ammar, A., Koubaa, A., and Ouni, K. (2020). Data-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networks. Appl. Sci., 10.10.3390/app10031092 ↗
15. SLIDE: Automatic spine level identification system using a deep convolutional neural network10.1007/s11548-017-1575-8 ↗
16. A novel ultrasound methodology for estimating spine mineral density10.1016/j.ultrasmedbio.2014.08.017 ↗
17. Transabdominal Imaging of the Lumbar Spine with Portable Ultrasound10.18535/ijmsci/v5i1.06 ↗
18. Ultrasound examination of pediatric musculoskeletal diseases and neonatal spine10.1007/s12098-015-1957-2 ↗
19. Ultrasound examination of the neonatal and infant spine
20. Ungi, T., Lasso, A., and Fichtinger, G. (2015). Tracked ultrasound in navigated spine interventions. Spinal Imaging and Image Analysis, Springer.10.1007/978-3-319-12508-4_15 ↗
21. Chen, F., Wu, D., and Liao, H. (2016, January 24–26). Registration of CT and ultrasound images of the spine with neural network and orientation code mutual information. Proceedings of the International Conference on Medical Imaging and Augmented Reality, Bern, Switzerland.10.1007/978-3-319-43775-0_26 ↗
22. Spine surface detection from local phase-symmetry enhanced ridges in ultrasound images10.1002/mp.12509 ↗
23. Ultrasound-guided spinal procedures for pain: A review10.1016/j.pmr.2016.04.011 ↗
24. Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv.
25. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
26. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
27. Huang, G., Liu, Z., Maaten, L.v.d., and Weinberger, K.Q. (2017, January 21–26). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
28. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
29. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
30. Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., and Bengio, Y. (2017, January 21–26). The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.10.1109/CVPRW.2017.156 ↗
31. Learning hierarchical features for scene labeling10.1109/TPAMI.2012.231 ↗
32. He, K., Zhang, X., Ren, S., and Sun, J. (2014, January 6–12). Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland. Lecture Notes in Computer Science.10.1007/978-3-319-10578-9_23 ↗
33. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision, Munich, Germany. Lecture Notes in Computer Science.10.1007/978-3-030-01234-2_49 ↗
34. (2019, October 02). Semantic Segmentation on PASCAL Voc 2012 Dataset. Available online: https://paperswithcode.com/sota/semantic-segmentation-on-pascal-voc-2012.
35. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
36. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21–26). Pyramid Scene Parsing Network. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.660 ↗
37. (2019, March 28). Real-Time Semantic Segmentation on Cityscapes. Available online: https://paperswithcode.com/sota/real-time-semantic-segmentation-cityscap.
38. Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., and Sang, N. (2018, January 8–14). BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation. Proceedings of the European Conference on Computer Vision, Munich, Germany. Lecture Notes in Computer Science.10.1007/978-3-030-01261-8_20 ↗
39. (2019, March 28). Semantic Segmentation Suite. Available online: https://github.com/GeorgeSeif/Semantic-Segmentation-Suite.
40. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2–4). TensorFlow: A system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA.
41. Fully convolutional densenet with multiscale context for automated breast tumor segmentation10.1155/2019/8415485 ↗