Localization of the correct vertebral level for surgical entry during lumbar hernia surgery is not straightforward. In this paper we develop and evaluate a solution using free-hand 2D ultrasound (US) imaging in the operation room (OR). Our system exploits the difference in spinous process shapes of the vertebrae. The spinous processes are pre-operatively outlined and labeled in a lateral lumbar X-ray of the patient. Then, in the OR the spinous processes are imaged with 2D sagittal US, and are automatically segmented and registered with the X-ray shapes. After a small number of scanned vertebrae, the system robustly matches the shapes, and propagates the X-ray label to the US images. The main contributions of our work are: We propose a deep convolutional neural network based bone segmentation algorithm from US imaging, that outperforms state-of-the-art methods in both performance and speed. We present a matching strategy that determines the levels of the spinal processes being imaged. And lastly, we evaluate the complete procedure on 19 clinical datasets from two hospitals, and two observers. The final labeling was correct in 92% of the cases, demonstrating the feasibility of US based surgical entry point detection for spinal surgeries.

Additional Metadata
Keywords bone segmentation, Bones, computer aided surgery, deep learning, Image segmentation, lumbar X-ray, machine learning, Shape, spine, Surgery, surgical guidance, Two dimensional displays, Ultrasonic imaging, X-ray imaging
Persistent URL dx.doi.org/10.1109/TMI.2017.2738612, hdl.handle.net/1765/101892
Journal IEEE Transactions on Medical Imaging
Note no subscription
Baka, N, Leenstra, S, & van Walsum, T.W. (2017). Ultrasound aided vertebral level localization for lumbar surgery. IEEE Transactions on Medical Imaging. doi:10.1109/TMI.2017.2738612