Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Background: Saliva has been studied as a better indicator of disorders and diseases than blood. Specifically, the salivary glucose level is considered to be an indicator of diabetes mellitus (DM). However, saliva collection methods can affect the salivary glucose level, thereby affecting the correlation between salivary glucose and blood glucose. Therefore, this study aims to identify an ideal saliva collection method and to use this method to determine the population and individual correlations between salivary glucose and blood glucose levels in DM patients and healthy controls. Finally, an analysis of the stability of the individual correlations is conducted. Methods: This study included 40 age-matched DM patients and 40 healthy controls. In the fasting state, saliva was collected using six saliva collection methods, venous blood was collected simultaneously from each study participant, and both samples were analyzed at the same time using glucose oxidase peroxidase. A total of 20 DM patients and 20 healthy controls were arbitrarily selected from the above participants for one week of daily testing. The correlations between salivary glucose and blood glucose before and after breakfast were analyzed. Finally, 10 DM patients and 10 healthy controls were arbitrarily selected for one month of daily testing to analyze the stability of individual correlations. Results: Salivary glucose levels were higher in DM patients than healthy controls for the six saliva collection methods. Compared with unstimulated saliva, stimulated saliva had decreased glucose level and increased salivary flow. In addition, unstimulated parotid salivary glucose was most correlated with blood glucose level (R² = 0.9153), and the ROC curve area was 0.9316, which could accurately distinguish DM patients. Finally, it was found that the correlations between salivary glucose and blood glucose in different DM patients were quite different. The average correlation before breakfast was 0.83, and the average correlation after breakfast was 0.77. The coefficient of variation of the correlation coefficient before breakfast within 1 month was less than 5%. Conclusion: Unstimulated parotid salivary glucose level is the highest and is most correlated with blood glucose level, which can be accurately used to distinguish DM patients. Meanwhile, the correlation between salivary glucose and blood glucose was found to be relatively high and stable before breakfast. In general, the unstimulated parotid salivary glucose before breakfast presents an ideal saliva collecting method with which to replace blood-glucose use to detect DM, which provides a reference for the prediction of DM.