Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images

Yongjie Wang; Feng Su; Qian Lu; Wenkai Zhang; Tao Liu; Yining Tao; Shuai Fu; Libin Cui; Shi-Bao Lu; Xueming Chen; Zhenyun Shi

doi:10.21037/qims-23-685

Deep learning-driven diagnosis of multi-type vertebra diseases based on computed tomography images

Quant Imaging Med Surg. 2024 Jan 3;14(1):800-813. doi: 10.21037/qims-23-685. Epub 2023 Dec 22.

Authors

Yongjie Wang^#¹, Feng Su^#^{2

3}, Qian Lu¹, Wenkai Zhang¹, Tao Liu¹, Yining Tao², Shuai Fu², Libin Cui¹, Shi-Bao Lu⁴, Xueming Chen¹, Zhenyun Shi²

Affiliations

¹ Department of Orthopedics, Beijing Luhe Hospital, Capital Medical University, Beijing, China.
² School of Mechanical Engineering and Automation, Beihang University, Beijing, China.
³ Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China.
⁴ Department of Orthopedics, Xuanwu Hospital, Capital Medical University, Beijing, China.

^# Contributed equally.

Abstract

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.

Keywords: Kummell’s disease (KD); Osteoporotic vertebral compression fracture (OVCF); deep learning (DL); old fracture (OF).