Purpose
To evaluate the association between lumbar lordosis and age using an AI-based automated measurement model applied to a large dataset of standing lateral spinal radiographs.
Materials and Methods
This retrospective study analyzed 904 high-quality radiographs selected from 2,397 images acquired between 2019 and 2021. Lumbar lordosis was defined as the angle between the superior endplates of L1 and S1 and automatically measured using a validated deep learning model. Subjects were categorized into nine age groups. One-way ANOVA compared lumbar lordosis across age groups, and Pearson correlation assessed the relationship between age and lumbar lordosis.
Results
Lumbar lordosis ranged from 0° to 84° (mean 45.9°±13.4°). The highest mean value was in the 10–19-year group (52.1°), and the lowest in the ≥80-year group (39.6°). Minimum values decreased to 0° in individuals aged ≥60 years. No significant differences were found across age groups (p=0.561). A weak but significant negative correlation was observed between age and lumbar lordosis (r=–0.247, p<0.0001).
Conclusions
AI-based automated measurement enabled efficient large-scale analysis and revealed a wide distribution of lumbar lordosis with a gradual age-related decline. These findings highlight the value of AI in spinal alignment assessment.

Purpose
Metabolic syndrome is a multifactorial condition associated with increased risks of cardiovascular disease and type 2 diabetes. This study aims to evaluate whether combining AI-based abdominal CT metrics with traditional InBody analysis enhances the prediction of metabolic syndrome.
Materials and Methods
This retrospective study included 977 adults who underwent both abdominal CT and InBody assessments. AI-derived measurements were obtained using a deep-learning V-Net model trained to segment seven body tissue types. InBody measurements included BMI, body fat percentage, fat mass, and waist-hip ratio. Metabolic syndrome was defined by NCEP-ATP III criteria. Logistic regression and ROC analyses were used to evaluate the predictive performance of AI-derived metrics, InBody metrics, and their combination.
Results
Body fat percentage and waist-hip ratio from InBody analysis were strong predictors of metabolic syndrome (AUC 0.82). AI-derived visceral fat was also significantly associated with metabolic syndrome (AUC 0.61). Combining both AI and InBody metrics slightly improved predictive performance (AUC 0.83), indicating a complementary diagnostic value.
Conclusions
While InBody metrics remain superior in predicting metabolic syndrome due to their close association with metabolic processes, AI-derived body composition metrics, particularly visceral fat, offer structural insights. The modest improvement in prediction when combined suggests the potential of an integrated diagnostic model in clinical practice.

Purpose
To develop and validate a deep learning–based artificial intelligence (AI) model for automated measurement of lumbar lordosis (LL) angles from whole spine lateral radiographs.
Materials and Methods
A total of 888 lateral spine X-rays (2019–2021) were retrospectively collected and annotated with four anatomical keypoints (L1 and S1 vertebral landmarks). An AI model using Detectron2 with a Keypoint R-CNN and ResNeXt-101 backbone was trained with data augmentation. Performance was evaluated on 50 test images, comparing AI results to manual annotations by two orthopedic surgeons using intraclass correlation coefficient (ICC), Pearson’s correlation, and Bland–Altman analysis.
Results
The model achieved an average precision of 71.63 for bounding boxes and 86.61 for keypoints. ICCs between AI and human raters ranged from 0.918 to 0.962. Pearson correlation coefficients were r=0.849 and r=0.903. Bland–Altman analysis showed minor underestimation biases (–3.42° and –4.28°) with acceptable agreement.
Conclusions
The AI model showed excellent agreement with expert measurements and high reliability in LL angle assessment. Despite a slight underestimation, it offers a scalable, consistent tool for clinical use. Further studies should evaluate generalizability and interpretability in broader settings.

Citations

• Deep Learning–based AI Analysis of the Correlation Between Lumbar Lordosis and Age
  Soo-Bin Lee, Ja-Yeong Yoon, Dong-Sik Chae, Sang-Bum Kim, Young-Seo Park, Kyung-Yil Kang, Min-Kyu Lee
  Journal of Advanced Spine Surgery.2025; 15(2): 78.     CrossRef
• Efficacy of Biportal Endoscopic Decompression for Lumbar Spinal Stenosis: A Meta-Analysis With Single-Arm Analysis and Comparative Analysis With Microscopic Decompression and Uniportal Endoscopic Decompression
  Shuangwen Lv, Haiwen Lv, Yupeng He, Xiansheng Xia
  Operative Neurosurgery.2024; 27(2): 158.     CrossRef

Advanced imaging technologies have revolutionized the diagnosis and management of spinal pathologies by providing superior precision and efficiency. Modalities such as PET-CT, SPECT, diffusion tensor imaging (DTI), and magnetic resonance spectroscopy (MRS) offer unique insights into the metabolic, structural, and functional aspects of spinal diseases, enabling better differentiation of lesions, improved surgical planning, and early detection of pathological changes. Furthermore, the integration of artificial intelligence (AI) has enhanced imaging workflows by enabling automated analysis, prediction of clinical outcomes, and segmentation of spinal structures. Despite these advancements, challenges such as technical limitations, high costs, and ethical concerns, including issues of data privacy and AI-generated inaccuracies, hinder widespread adoption. This review explores the clinical applications, limitations, and future directions of these emerging technologies, highlighting the need for multidisciplinary collaboration and large-scale research to standardize protocols and optimize patient outcomes. The seamless integration of advanced imaging and AI represents a transformative potential for improving diagnostic accuracy and treatment efficacy in spinal care.