A deep learning framework for segmentation and pose estimation of pedicle screw implants based on C-arm fluoroscopy

• Published in: International journal for computer assisted radiology and surgery 2018-08, Vol.13 (8), p.1269-1282
• Main Authors: Esfandiari, Hooman, Newell, Robyn, Anglin, Carolyn, Street, John, Hodgson, Antony J.
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Automation; Background radiation; Computer Imaging; Computer Science; Deep learning; Fluoroscopy; Fluoroscopy - methods; Health Informatics; Humans; Image acquisition; Image segmentation; Imaging; Insertion; Machine Learning; Medicine; Medicine & Public Health; Original Article; Pattern Recognition and Graphics; Pedicle Screws; Pose estimation; Radiology; Reoperation; Screws; Spinal Fusion - methods; Surgery; Surgery, Computer-Assisted - methods; Surgical implants; Tomography, X-Ray Computed - methods; Vision; X-rays
• ISSN: 1861-6410; 1861-6429
• DOI: 10.1007/s11548-018-1776-9

Purpose Pedicle screw fixation is a challenging procedure with a concerning rates of reoperation. After insertion of the screws is completed, the most common intraoperative verification approach is to acquire anterior–posterior and lateral radiographic images, based on which the surgeons try to visually assess the correctness of insertion. Given the limited accuracy of the existing verification techniques, we identified the need for an accurate and automated pedicle screw assessment system that can verify the screw insertion intraoperatively. For doing so, this paper offers a framework for automatic segmentation and pose estimation of pedicle screws based on deep learning principles. Methods Segmentation of pedicle screw X-ray projections was performed by a convolutional neural network. The network could isolate the input X-rays into three classes: screw head, screw shaft and background. Once all the screw shafts were segmented, knowledge about the spatial configuration of the acquired biplanar X-rays was used to identify the correspondence between the projections. Pose estimation was then performed to estimate the 6 degree-of-freedom pose of each screw. The performance of the proposed pose estimation method was tested on a porcine specimen. Results The developed machine learning framework was capable of segmenting the screw shafts with 93% and 83% accuracy when tested on synthetic X-rays and on clinically realistic X-rays, respectively. The pose estimation accuracy of this method was shown to be 1 . 93 ∘ ± 0 . 64 ∘ and 1.92 ± 0.55 mm on clinically realistic X-rays. Conclusions The proposed system offers an accurate and fully automatic pedicle screw segmentation and pose assessment framework. Such a system can help to provide an intraoperative pedicle screw insertion assessment protocol with minimal interference with the existing surgical routines.