Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images
Quantitative Imaging in Medicine and Surgery · 2024-01 · 14 (1) · 800-813
DOI: 10.21037/qims-23-685 ↗Kurz gefasst
Fachartikel in der Zeitschrift Quantitative Imaging in Medicine and Surgery, 2024-01. Verfasst von Yongjie Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedics, Beijing Luhe Hospital, Capital Medical University, Beijing, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Osteoporotic vertebral compression fractures (OVCFs) are the most common type of fragility fracture. Distinguishing between OVCFs and other types of vertebra diseases, such as old fractures (OFs), Schmorl's node (SN), Kummell's disease (KD), and previous surgery (PS), is critical for subsequent surgery and treatment. Combining with advanced deep learning (DL) technologies, this study plans to develop a DL-driven diagnostic system for diagnosing multi-type vertebra diseases.
Methods
We established a large-scale dataset based on the computed tomography (CT) images of 1,051 patients with OVCFs from Luhe Hospital and used data of 46 patients from Xuanwu Hospital as alternative hospital validation dataset. Each patient underwent one examination. The dataset contained 11,417 CT slices and 19,718 manually annotated vertebrae with diseases. A two-stage DL-based system was developed to diagnose five vertebra diseases. The proposed system consisted of a vertebra detection module (VDModule) and a vertebra classification module (VCModule).
Results
The training and testing dataset for the VDModule consisted of 9,135 and 3,212 vertebrae, respectively. The VDModule using the ResNet18-based Faster region-based convolutional neural network (R-CNN) model achieved an area under the curve (AUC), false-positive (FP) rate, and false-negative (FN) rate of 0.982, 1.52%, and 1.33%, respectively, in the testing dataset. The training dataset for VCModule consisted of 14,584 and 47,604 diseased and normal vertebrae, respectively. The testing dataset consisted of 4,489 and 15,122 diseased and normal vertebrae, respectively. The ResNet50-based VCModule achieved an average sensitivity and specificity of 0.919 and 0.995, respectively, in diagnosing four kinds of vertebra diseases except for SN in the testing dataset. In the alternative hospital validation dataset, the ResNet50-based VCModule achieved an average sensitivity and specificity of 0.891 and 0.989, respectively, in diagnosing four kinds of vertebra diseases except for SN.
Conclusions
Our proposed DL system can accurately diagnose four vertebra diseases and has strong potential to facilitate the accurate and rapid diagnosis of vertebral diseases.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Orthopedics, Beijing Luhe Hospital, Capital Medical University, Beijing, China.
- School of Mechanical Engineering and Automation, Beihang University, Beijing, China.
- Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China.
- Department of Orthopedics, Xuanwu Hospital, Capital Medical University, Beijing, China.
Zitieren
APA
Wang, Y., Su, F., Lu, Q., Zhang, W., Liu, T., Tao, Y., Fu, S., Cui, L., Lu, S. B., Chen, X., & Shi, Z. (2024). Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images. Quantitative Imaging in Medicine and Surgery, 14(1), 800-813. https://doi.org/10.21037/qims-23-685
Vancouver
Wang Y, Su F, Lu Q, Zhang W, Liu T, Tao Y, et al. Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images. Quantitative Imaging in Medicine and Surgery. 2024;14(1):800-813. doi:10.21037/qims-23-685
BibTeX
@article{Wang2024,
author = {Wang, Yongjie and Su, Feng and Lu, Qian and Zhang, Wenkai and Liu, Tao and Tao, Yining and Fu, Shuai and Cui, Libin and Lu, Shi-Bao and Chen, Xueming and Shi, Zhenyun},
title = {Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images},
journal = {Quantitative Imaging in Medicine and Surgery},
year = {2024},
volume = {14},
number = {1},
pages = {800--813},
doi = {10.21037/qims-23-685}
}
EUVIMED