Search Results

You are looking at 1 - 6 of 6 items for

  • Author or Editor: Kyle C. Wu x
Clear All Modify Search
Full access

Viren S. Vasudeva, Alexander E. Ropper, Samuel Rodriguez, Kyle C. Wu and John H. Chi

En bloc resection of tumors involving the spinal column is technically challenging and is associated with high morbidity to the patient due to the proximity of critical neurological and vascular structures and the destabilizing nature of this surgery. Nevertheless, evidence has shown improved progression-free survival with en bloc resection for certain low-grade malignant and aggressive benign musculoskeletal tumors. To avoid the morbidity of en bloc spondylectomy in patients with tumors localized to the lateral and posterolateral spinal column, the authors have found that the goals of surgery can be accomplished through a contralateral osteotomy of the pedicle and posterolateral elements for en bloc resection (COPPER). They reviewed their series of 5 patients who underwent successful tumor removal through a COPPER approach. These patients were all found to harbor spinal column tumors involving the posterolateral elements that, based on pathology, would benefit from en bloc resection. Tumor pathology included chondrosarcoma, leiomyosarcoma, osteoblastoma, and liposarcoma. Resections were performed by completing ipsilateral facetectomies above and below the lesion and ipsilateral pedicle osteotomies from a contralateral approach following hemilaminectomy. By disarticulating the posterolateral elements while carefully protecting the thecal sac, the tumors were removed en bloc along with the affected lamina, pedicles, pars interarticularis, and spinous processes, allowing tumor-free margins. This technical report suggests that the COPPER approach is safe and effective for en bloc resection of tumors involving the posterolateral aspect of the spinal column with tumor-free margins and that it eliminates the need for anterior column reconstruction.

Restricted access

Kevin T. Huang, Michael A. Silva, Alfred P. See, Kyle C. Wu, Troy Gallerani, Hasan A. Zaidi, Yi Lu, John H. Chi, Michael W. Groff and Omar M. Arnaout

OBJECTIVE

Recent advances in computer vision have revolutionized many aspects of society but have yet to find significant penetrance in neurosurgery. One proposed use for this technology is to aid in the identification of implanted spinal hardware. In revision operations, knowing the manufacturer and model of previously implanted fusion systems upfront can facilitate a faster and safer procedure, but this information is frequently unavailable or incomplete. The authors present one approach for the automated, high-accuracy classification of anterior cervical hardware fusion systems using computer vision.

METHODS

Patient records were searched for those who underwent anterior-posterior (AP) cervical radiography following anterior cervical discectomy and fusion (ACDF) at the authors’ institution over a 10-year period (2008–2018). These images were then cropped and windowed to include just the cervical plating system. Images were then labeled with the appropriate manufacturer and system according to the operative record. A computer vision classifier was then constructed using the bag-of-visual-words technique and KAZE feature detection. Accuracy and validity were tested using an 80%/20% training/testing pseudorandom split over 100 iterations.

RESULTS

A total of 321 total images were isolated containing 9 different ACDF systems from 5 different companies. The correct system was identified as the top choice in 91.5% ± 3.8% of the cases and one of the top 2 or 3 choices in 97.1% ± 2.0% and 98.4 ± 13% of the cases, respectively. Performance persisted despite the inclusion of variable sizes of hardware (i.e., 1-level, 2-level, and 3-level plates). Stratification by the size of hardware did not improve performance.

CONCLUSIONS

A computer vision algorithm was trained to classify at least 9 different types of anterior cervical fusion systems using relatively sparse data sets and was demonstrated to perform with high accuracy. This represents one of many potential clinical applications of machine learning and computer vision in neurosurgical practice.