Neurospine.
2024 Mar;21(1):57-67. 10.14245/ns.2347178.589.
Whole Spine Segmentation Using Object Detection and Semantic Segmentation
- Affiliations
-
- 1Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zürich, University of Zürich, Zürich, Switzerland
- 2Department of Neurosurgery, Daejeon Eulji University Hospital, Eulji University Medical School, Daejeon, Korea
- KMID: 2553905
- DOI: http://doi.org/10.14245/ns.2347178.589
Abstract
Objective
Virtual and augmented reality have enjoyed increased attention in spine surgery. Preoperative planning, pedicle screw placement, and surgical training are among the most studied use cases. Identifying osseous structures is a key aspect of navigating a 3-dimensional virtual reconstruction. To automate the otherwise time-consuming process of labeling vertebrae on each slice individually, we propose a fully automated pipeline that automates segmentation on computed tomography (CT) and which can form the basis for further virtual or augmented reality application and radiomic analysis.
Methods
Based on a large public dataset of annotated vertebral CT scans, we first trained a YOLOv8m (You-Only-Look-Once algorithm, Version 8 and size medium) to detect each vertebra individually. On the then cropped images, a 2D-U-Net was developed and externally validated on 2 different public datasets.
Results
Two hundred fourteen CT scans (cervical, thoracic, or lumbar spine) were used for model training, and 40 scans were used for external validation. Vertebra recognition achieved a mAP50 (mean average precision with Jaccard threshold of 0.5) of over 0.84, and the segmentation algorithm attained a mean Dice score of 0.75 ± 0.14 at internal, 0.77 ± 0.12 and 0.82 ± 0.14 at external validation, respectively.
Conclusion
We propose a 2-stage approach consisting of single vertebra labeling by an object detection algorithm followed by semantic segmentation. In our externally validated pilot study, we demonstrate robust performance for our object detection network in identifying individual vertebrae, as well as for our segmentation model in precisely delineating the bony structures.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach
- Application of deep learning for semantic segmentation in robotic prostatectomy: Comparison of convolutional neural networks and visual transformers
- Comparison of Multi-Label U-Net and Mask R-CNN for panoramic radiograph segmentation to detect periodontitis
- A Study on Pupil and Iris Segmentation of the Anterior Segment of the Eye
- Classification of Continuous Heart Sound Signals Using the Ergodic Hidden Markov Model
