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

Abstract

Objective Osteoporosis 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 lowdose chest computed tomography (LDCT) scans obtained for lung cancer screening. Methods First, 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. Results Our 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/cm 3. The area under the curve (AUC) was 0.927 for detecting osteoporosis and 0.942 for distinguishing low BMD. Conclusion The 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. Keywords Bone mineral density. Deep learning. Osteoporosis. Screening Abbreviations AUC Area under the curve BMD Bone mineral density CNN Convolutional neural network CT Computed tomography DL Deep learning DXA Dual-energy X-ray absorptiometry LDCT Low-dose chest computed tomography QA Quality assurance QCT Quantitative computed tomography VB Vertebral body VOI Volume of interest Yaling Pan and Dejun Shi contributed equally to this work.

Computed tomography-based opportunistic osteoporosis assessment: a comparison of two software applications for lumbar vertebral volumetric bone mineral density measurements

“…This indicates that the IP analysis is not suitable for analyzing scans other than those obtained at 120 kVp. Opportunistic vBMD measurement with a CT-based method, both in MECT and DECT mode, is useful, with the potential to contribute to an earlier discovery of osteoporosis without increased radiation exposure (3,4,12,(14)(15)(16)(17)(18). However, the BMD values determined by different software programs in the same patients across different machines should be comparable.…”

“…Various computed tomography (CT)-based methods can be used to potentially improve bone quality assessment and make the diagnosis process in FLSs more effective (4,9,10). FLSs could perform opportunistic volumetric BMD (vBMD) assessment using CT scans conducted at the time of fracture occurrence (i.e., when detecting a vertebral fracture using abdominal or thoracic CT scans) as well as identifying high-risk individuals during opportunistic screening when investigating patients for other diagnoses (3,(10)(11)(12)(13)(14)(15)(16)(17)(18). It is important that these CT-based methods are shown to be reliable and stable across various software programs, CT machines and scan protocols (i.e., not only protocols specific to skeletal imaging).…”

Applications of Artificial Intelligence in Musculoskeletal Imaging: From the Request to the Report

“…Pan et al described a deep learningbased system for bone mineral density measurement on lowdose chest CTs performed for lung cancer screening. 35 In this system, segmentation was performed using a 3D CNN model with U-net architecture and dense connections. Conventional image processing algorithms were used for vertebral body labeling.…”

Evolution in fracture risk assessment: artificial versus augmented intelligence

“…In contrast, fewer than 100 of these were in the field of osteoporosis, although this is following the same exponential trajectory with the majority of studies published during the last 2-3 years. Efforts have been made in osteoporosis diagnosis and classification, bone mineral density assessment, fracture detection, fracture risk estimation, and bone image segmentation [7][8][9][10][11][12][13][14]. The majority of these articles used opportunistic data-particularly in imaging.…”