Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography

Abstract

Osteoporosis, marked by low bone mineral density (BMD) and a high fracture risk, is a major health issue. Recent progress in medical imaging, especially CT scans, offers new ways of diagnosing and assessing osteoporosis. This review examines the use of AI analysis of CT scans to stratify BMD and diagnose osteoporosis. By summarizing the relevant studies, we aimed to assess the effectiveness, constraints, and potential impact of AI-based osteoporosis classification (severity) via CT. A systematic search of electronic databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 39 articles were retrieved from the databases, and the key findings were compiled and summarized, including the regions analyzed, the type of CT imaging, and their efficacy in predicting BMD compared with conventional DXA studies. Important considerations and limitations are also discussed. The overall reported accuracy, sensitivity, and specificity of AI in classifying osteoporosis using CT images ranged from 61.8% to 99.4%, 41.0% to 100.0%, and 31.0% to 100.0% respectively, with areas under the curve (AUCs) ranging from 0.582 to 0.994. While additional research is necessary to validate the clinical efficacy and reproducibility of these AI tools before incorporating them into routine clinical practice, these studies demonstrate the promising potential of using CT to opportunistically predict and classify osteoporosis without the need for DEXA.

Keywords: artificial intelligence; computed tomography; deep learning; imaging; machine learning; osteoporosis.

Figure 1

PRISMA flowchart for the literature search (this is adapted from the PRISMA group, 2020), which describes the selection of relevant articles.

Figure 2

Diagram illustrating the hierarchical structure of artificial intelligence. Machine learning, a subset of artificial intelligence, is a discipline that imparts computers with the capacity to learn autonomously, bypassing the need for explicit programming. Within the realm of machine learning, deep learning represents a subset that enables the computation of neural networks with multiple layers. CNN is a subset of deep learning characterized by convolutional layers.

Figure 3

Diagram showing the general framework and main steps of radiomics, namely data selection (input), segmentation, feature extraction in the regions of interest (ROIs), exploratory analysis, and modeling.