The proposed research study investigates the relationship between Bone Mineral Density (BMD) values extracted from computed tomography (CT) scans, with a primary focus on their significance in vertebral segmentation. The study includes 25 subjects spanning five age groups; the study reveals a continuous reduction in mean Hounsfield Unit (HU) values with aging, validated by statistical analysis that emphasizes the importance of these findings across different vertebral levels. The data exposes a steady decline in mean BMD values with age, ranging from 175.05 HU in the 40s to 51.8 HU in the over-80s age group, exhibiting statistically significant differences (p<0.05). Subgroup analysis provides granular insights into age-related variations at specific lumbar vertebrae levels by contributing valuable information to the complexities of bone health assessment. The research connects mathematics and medical imaging to improve our understanding of vertebral characteristics by introducing the Radon Transform as a fundamental tool in CT image reconstruction. These findings include both p and mean values which have the potential to revolutionize the field of bone health assessment by affecting public health policy and opening the way for more personalized and successful treatment options. This includes the earlier detection of conditions like osteoporosis and improvements in patient care.

This study proposes a comprehensive framework for the segmentation and identification of vertebrae in CT scans using a combination of deep learning and traditional machine learning techniques. The Res U-Net architecture is employed to achieve a high model accuracy of 93.62% on the VerSe’20 dataset demonstrating effective performance in segmenting lumbar and thoracic vertebrae. Feature extraction is enhanced through the application of Otsu’s method which effectively distinguishes the vertebrae from the surrounding tissue. The proposed method achieves a Dice Similarity Coefficient (DSC) of 87.10% ± 3.72%, showcasing its competitive performance against other segmentation techniques. By accurately extracting vertebral features this framework assists medical professionals in precise preoperative planning, allowing for the identification and marking of critical anatomical features required during spinal fusion procedures. This integrated approach not only addresses the challenges of vertebrae segmentation but also offers a scalable and efficient solution for analyzing large-scale medical imaging datasets with the potential to significantly improve clinical workflows and patient outcomes.