Automatic vertebrae localization in spine CT: A deep-learning approach for image guidance and surgical data science

M. Levine, T. De Silva, M. D. Ketcha, R. Vijayan, S. Doerr, A. Uneri, S. Vedula, N. Theodore, J. H. Siewerdsen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Motivation/Purpose: This work reports the development and validation of an algorithm to automatically detect and localize vertebrae in CT images of patients undergoing spine surgery. Slice-by-slice detections using the state-of-the art 2D convolutional neural network (CNN) architectures were combined to estimate vertebra centroid location in 3D including a method that combined detections in sagittal and coronal slices. The solution facilitates applications in image guided surgery and automatic computation of image analytics for surgical data science. Methods: CNN-based object detection models in 3D (volume) and 2D (slice) images were implemented and evaluated for the task of vertebrae detection. Slice-by-slice detections in 2D architectures were combined to estimate the 3D centroid location including a model that simultaneously evaluated 2D detections in orthogonal directions (i.e., sagittal and coronal slices) to improve the robustness against spurious false detections-called Ortho-2D. Performance was evaluated in a data set consisting of 85 patients undergoing spine surgery at our institution, including images presenting spinal instrumentation/implants, spinal deformity, and anatomical abnormalities that are realistic exemplars of pathology in the patient population. Accuracy was quantified in terms of precision, recall, F1 score, and the 3D geometric error in vertebral centroid annotation compared to ground truth (expert manual) annotation. Results: Three CNN object detection models were able to successfully localize vertebrae, with Ortho-2D model that combined 2D detections in orthogonal directions achieving best performance: precision = 0.95, recall = 0.99, and F1 score = 0.97. Overall centroid localization accuracy was 3.4 mm (median) [interquartile range (IQR) = 2.7 mm], and ∼97% of detections (154/159 lumbar cases) yielded acceptable centroid localization error <15 mm (considering average vertebrae size ∼25 mm). Conclusions: State-of-the-art CNN architectures were adapted for vertebral centroid annotation, yielding accurate and robust localization even in the presence of anatomical abnormalities, image artifacts, and dense instrumentation. The methods are employed as a basis for streamlined image guidance (automatic initialization of 3D-2D and 3D-3D registration methods in image-guided surgery) and as an automatic spine labeling tool to generate image analytics.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2019
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
EditorsBaowei Fei, Cristian A. Linte
PublisherSPIE
ISBN (Electronic)9781510625495
DOIs
StatePublished - 2019
EventMedical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling - San Diego, United States
Duration: Feb 17 2019Feb 19 2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10951
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling
Country/TerritoryUnited States
CitySan Diego
Period2/17/192/19/19

Keywords

  • Deep learning
  • Image-analytics
  • Spine surgery
  • Surgical data science
  • Vertebral labeling

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Automatic vertebrae localization in spine CT: A deep-learning approach for image guidance and surgical data science'. Together they form a unique fingerprint.

Cite this