Addressing Challenges of Opportunistic Computed Tomography Bone Mineral Density Analysis

Abstract

Computed tomography (CT) offers advanced biomedical imaging of the body and is broadly utilized for clinical diagnosis. Traditionally, clinical CT scans have not been used for volumetric bone mineral density (vBMD) assessment; however, computational advances can now leverage clinically obtained CT data for the secondary analysis of bone, known as opportunistic CT analysis. Initial applications focused on using clinically acquired CT scans for secondary osteoporosis screening, but opportunistic CT analysis can also be applied to answer research questions related to vBMD changes in response to various disease states. There are several considerations for opportunistic CT analysis, including scan acquisition, contrast enhancement, the internal calibration technique, and bone segmentation, but there remains no consensus on applying these methods. These factors may influence vBMD measures and therefore the robustness of the opportunistic CT analysis. Further research and standardization efforts are needed to establish a consensus and optimize the application of opportunistic CT analysis for accurate and reliable assessment of vBMD in clinical and research settings. This review summarizes the current state of opportunistic CT analysis, highlighting its potential and addressing the associated challenges.

Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography

“…Interestingly, two studies by Huang CB et al [79] and Qiu H. et al [127] adopted a unique approach by sampling muscles rather than the bony skeleton to predict and classify osteoporosis. This strategy capitalizes on the established link between sarcopenia and osteoporosis [167][168][169].…”

“…Prior studies have shown that individuals with both sarcopenia and low BMD have an increased risk of insufficiency fractures [129,170]. The radiomics model developed by Huang CB et al, which employed gradient boosting methods (GBMs), achieved an AUC of up to 0.860 and an accuracy of 81.0% on validation sets [79]. This method of classifying osteoporosis is especially useful in cases in which direct sampling of the vertebral body may not provide an accurate representation of bone density, for example, in cases of severe spinal spondylosis [171].…”

“…Subsequently, many other studies [67,[75][76][77][78] confirmed the feasibility of trabecular HU values for screening osteoporosis on CT. However, most studies have involved manual or semi-automatic segmentation, which is often time-consuming due to the required manual input and/or computing power [79] and other limitations [80][81][82].…”