Back to Search
Start Over
Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net
- Source :
- Scientific Reports, Scientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
- Publication Year :
- 2021
- Publisher :
- Nature Publishing Group UK, 2021.
-
Abstract
- Automatic vertebrae localization and segmentation in computed tomography (CT) are fundamental for spinal image analysis and spine surgery with computer-assisted surgery systems. But they remain challenging due to high variation in spinal anatomy among patients. In this paper, we proposed a deep-learning approach for automatic CT vertebrae localization and segmentation with a two-stage Dense-U-Net. The first stage used a 2D-Dense-U-Net to localize vertebrae by detecting the vertebrae centroids with dense labels and 2D slices. The second stage segmented the specific vertebra within a region-of-interest identified based on the centroid using 3D-Dense-U-Net. Finally, each segmented vertebra was merged into a complete spine and resampled to original resolution. We evaluated our method on the dataset from the CSI 2014 Workshop with 6 metrics: location error (1.69 ± 0.78 mm), detection rate (100%) for vertebrae localization; the dice coefficient (0.953 ± 0.014), intersection over union (0.911 ± 0.025), Hausdorff distance (4.013 ± 2.128 mm), pixel accuracy (0.998 ± 0.001) for vertebrae segmentation. The experimental results demonstrated the efficiency of the proposed method. Furthermore, evaluation on the dataset from the xVertSeg challenge with location error (4.12 ± 2.31), detection rate (100%), dice coefficient (0.877 ± 0.035) shows the generalizability of our method. In summary, our solution localized the vertebrae successfully by detecting the centroids of vertebrae and implemented instance segmentation of vertebrae in the whole spine.
- Subjects :
- musculoskeletal diseases
Computer science
Science
Image processing
Article
Deep Learning
Sørensen–Dice coefficient
Machine learning
medicine
Image Processing, Computer-Assisted
Humans
Segmentation
Multidisciplinary
medicine.diagnostic_test
Pixel
business.industry
Centroid
Pattern recognition
musculoskeletal system
Spine
Vertebra
Data processing
medicine.anatomical_structure
Hausdorff distance
Positron emission tomography
Medicine
Spinal Fractures
Artificial intelligence
Neural Networks, Computer
Positron-emission tomography
business
Tomography, X-Ray Computed
Biomedical engineering
X-ray tomography
Subjects
Details
- Language :
- English
- ISSN :
- 20452322
- Volume :
- 11
- Database :
- OpenAIRE
- Journal :
- Scientific Reports
- Accession number :
- edsair.doi.dedup.....76329687b527613a631156e9ecad0086