Automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening

Yaling Pan,Yong Lu,Xiaoguang Cheng,Tongtong Chen,Deqi Cui,Dejun Shi,Hanqi Wang

doi:10.1007/s00330-020-06679-y

Abstract

ObjectiveOsteoporosis is a prevalent and treatable condition, but it remains underdiagnosed. In this study, a deep learning-based system was developed to automatically measure bone mineral density (BMD) for opportunistic osteoporosis screening using low-dose chest computed tomography (LDCT) scans obtained for lung cancer screening.MethodsFirst, a deep learning model was trained and tested with 200 annotated LDCT scans to segment and label all vertebral bodies (VBs). Then, the mean CT numbers of the trabecular area of target VBs were obtained based on the segmentation mask through geometric operations. Finally, a linear function was built to map the trabecular CT numbers of target VBs to their BMDs collected from approved software used for osteoporosis diagnosis. The diagnostic performance of the developed system was evaluated using an independent dataset of 374 LDCT scans with standard BMDs and osteoporosis diagnosis.ResultsOur deep learning model achieved a mean Dice coefficient of 86.6% for VB segmentation and 97.5% accuracy for VB labeling. Line regression and Bland-Altman analyses showed good agreement between the predicted BMD and the ground truth, with correlation coefficients of 0.964–0.968 and mean errors of 2.2–4.0 mg/cm3. The area under the curve (AUC) was 0.927 for detecting osteoporosis and 0.942 for distinguishing low BMD.ConclusionThe proposed deep learning-based system demonstrated the potential to automatically perform opportunistic osteoporosis screening using LDCT scans obtained for lung cancer screening.Key Points• Osteoporosis is a prevalent but underdiagnosed condition that can increase the risk of fracture.• A deep learning-based system was developed to fully automate bone mineral density measurement in low-dose chest computed tomography scans.• The developed system achieved high accuracy for automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening.

Highlights

Osteoporosis is a prevalent and latent metabolic bone disease characterized by loss of bone mass and consequent susceptibility to fracture
The developed system achieved high accuracy for automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening
One lowdose chest computed tomography (LDCT) scan presented an error in the vertebral bodies (VBs) labeling, where seven VBs were predicted as class two (T7–T12) VBs resulting in 13 thoracic VBs, and VB L1 was mislabeled as a thoracic VB

Summary

Introduction

Osteoporosis is a prevalent and latent metabolic bone disease characterized by loss of bone mass and consequent susceptibility to fracture. Early screening and monitoring of osteoporosis are crucial for timely prevention and treatment of osteoporotic fracture. Bone mineral density (BMD), directly related to bone strength, is widely used to diagnose and monitor osteoporosis in clinical practice [4]. Quantitative computed tomography (QCT) is increasingly used to measure vertebral BMD from clinical computed tomography (CT) scans and has higher sensitivity than dual-energy X-ray absorptiometry (DXA) for diagnosing osteoporosis and predicting the risk of osteoporotic fracture [5]. Compared with DXA, QCT is less susceptible to confounding factors such as spinal degenerative changes, aortic calcification, bone size, and body mass index, and can selectively measure trabecular BMD [6]. Trabecular BMD is considered a more sensitive marker for changes in overall bone strength because it is generally lost more rapidly than cortical BMD when the disease progresses [7]

Methods

Results

Discussion

Conclusion