Skip to content
Log in
Sponsored Have an interesting project or opportunity? → Hire me ↗
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

Author

Nuri Serdar Baş

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

The Association Between Lumbar Disc Degeneration and Paraspinal Muscle Morphology: The Role of Age in a Quantitative Magnetic Resonance Imaging-Based Study

Aim: The relationship between lumbar intervertebral disc degeneration and paraspinal muscle degeneration remains controversial. Although previous studies have reported associations between disc degeneration and muscle atrophy and fatty infiltration, the effect of age on this relationship has not been sufficiently clarified. This study aimed to investigate the associations that cumulative and L4–L5 level-specific disc degeneration have with paraspinal muscle morphology, and to determine whether these associations persisted after adjustment for age. Materials and Methods: This retrospective cross-sectional study included 84 patients who underwent lumbar magnetic resonance imaging (MRI) for low back pain. Disc degeneration was evaluated at all lumbar levels according to the Pfirrmann classification, and the Total Pfirrmann Score was calculated. Relative functional cross-sectional area (rFCSA) and fatty infiltration (FI) measurements of the multifidus, erector spinae, and psoas muscles at the L4–L5 level were performed using ImageJ software. The relationships between variables were examined using Spearman correlation analysis. Multiple linear regression analysis was performed to investigate independent predictors. Age-controlled partial correlation analyses were also performed to evaluate the potential confounding effect of age. Results: Of the 84 patients included in the study, 48 (57.1%) were female and 36 (42.9%) were male, with a mean age of 42.3 ± 8.4 years. The mean Total Pfirrmann Score was 14.3 ± 3.8. A moderate positive correlation was found between age and the Total Pfirrmann Score (rho = 0.519; p < 0.001). Significant positive correlations were observed between the Total Pfirrmann Score and multifidus fatty infiltration (rho = 0.316; p = 0.003) and erector spinae fatty infiltration (rho = 0.300; p = 0.006). A weak negative correlation was detected between psoas rFCSA and the Total Pfirrmann Score (rho = −0.247; p = 0.023). Multifidus and erector spinae rFCSA were not significantly associated with the Total Pfirrmann Score (p = 0.094 and p = 0.095, respectively). At the L4–L5 level, higher Pfirrmann grade was associated with lower multifidus rFCSA (rho = −0.233; p = 0.033) and lower psoas rFCSA (rho = −0.319; p = 0.003), whereas the inverse association with erector spinae rFCSA was borderline (rho = −0.215; p = 0.050). Multiple linear regression analysis showed that age was the only statistically significant predictor of the Total Pfirrmann Score in the multivariable model (p < 0.001). After adjustment for age, the associations of multifidus FI (r = 0.193; p = 0.079) and erector spinae FI (r = 0.194; p = 0.078) with the Total Pfirrmann Score did not reach statistical significance. In the age-adjusted L4–L5 analysis, only the inverse association between Pfirrmann grade and psoas rFCSA remained statistically significant (r = −0.232; p = 0.034). Conclusions: Greater cumulative lumbar disc degeneration was associated with increased fatty infiltration of the multifidus and erector spinae muscles and lower psoas rFCSA, whereas multifidus and erector spinae rFCSA were not associated with the Total Pfirrmann Score. At L4–L5, greater disc degeneration was associated with lower multifidus and psoas rFCSA, while the association with erector spinae rFCSA was borderline. After adjustment for age, the associations of multifidus and erector spinae fatty infiltration with cumulative disc degeneration were attenuated and did not reach statistical significance; however, a weak independent association cannot be excluded.

Abdurrahim Tekin, Umut Çelik, Akın Öztürk et al. · 0 citations
Open access 2026

From Geometric to Realistic: A Pipelined Deep Learning Framework for Cranial Implant Design Using PCA-Based Synthetic Data

Cranial implant design is a critical area in neurosurgery, directly impacting patient outcomes by addressing complex cranial defects resulting from trauma or surgical interventions. Despite advancements in deep learning and synthetic data generation, existing methodologies often fall short due to a lack of high-quality, labeled datasets, which limits the clinical applicability of automated solutions. This study aims to bridge this gap by developing a novel deep learning framework that utilizes Principal Component Analysis (PCA) to generate realistic synthetic cranial defect data, thereby enhancing the training of neural networks for implant design. The research employs a comprehensive approach, integrating data from multiple sources, including clinical datasets and synthetic augmentations, to train advanced models capable of volumetric completion. Key findings reveal that the proposed pipeline, which combines a boundary-specialized model with a volume-specialized model, achieves superior geometric fidelity and volumetric accuracy, with a Hausdorff Distance of 7.90 mm and an Implant DICE score of 81.89%. These results challenge the assumption that traditional geometric augmentation methods are sufficient for capturing the complexity of cranial defects. The study contributes to the field by establishing a new standard for synthetic data generation and multi-stage inference in medical image analysis, offering a robust foundation for the development of fully autonomous, 3D-printable cranial implants, thus enhancing the potential for immediate clinical application and improving patient care.

Gorkem Serbes, H. Ilhan, Osman Liv et al. · 0 citations