Ultrasound Aided Vertebral Level Localization for Lumbar Surgery

• Published in: IEEE transactions on medical imaging 2017-10, Vol.36 (10), p.2138-2147
• Main Authors: Baka, Nora, Leenstra, Sieger, van Walsum, Theo
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Bone imaging; Bone segmentation; Bones; computer aided surgery; Deep learning; Feasibility studies; Hernia; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Localization; Lumbar Vertebrae - diagnostic imaging; Lumbar Vertebrae - surgery; lumbar X-ray; Machine Learning; Male; Middle Aged; Neural networks; Shape; Shape recognition; spine; State of the art; Surgery; Surgery, Computer-Assisted - methods; surgical guidance; Two dimensional displays; Ultrasonic imaging; Ultrasonography - methods; Ultrasound; Vertebrae; X-ray imaging
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2017.2738612

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 2-D 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 2-D 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 data sets 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.