Background/Objectives: Transforaminal lumbar interbody fusion (TLIF) and lateral lumbar interbody fusion (LLIF) are widely utilized techniques for degenerative lumbar diseases. This study compared radiological and clinical outcomes of LLIF and TLIF in patients undergoing lumbar fusion. Methods: This non-randomized prospective observational study enrolled 117 patients (LLIF: n = 17; TLIF: n = 100), with an inherent imbalance in group sizes, who underwent one- or two-level lumbar interbody fusion. Primary outcome was segmental lordotic angle (SLA) at the operated level. Secondary outcomes included disc height, lumbar lordotic angle, sagittal vertical axis, and patient-reported outcomes. Assessments were conducted at baseline, 3, 6, 12, and 24 months. Linear mixed models analyzed longitudinal data. Results: Mean SLA improvement was not significantly different between the groups (LLIF: 3.04° vs. TLIF: 3.18°, p = 0.782). No significant differences were observed for disc height (p = 0.518), lumbar lordotic angle (p = 0.718), or sagittal vertical axis (p = 0.866). Patient-reported outcomes improved significantly in both groups. Linear mixed model analysis revealed no significant between-group effects for Oswestry Disability Index (p = 0.335) or low back pain (p = 0.069). TLIF showed higher rates of dural tears and wound complications, while LLIF had more sympathetic chain injuries and transient psoas weakness. Overall complication rates were comparable (p > 0.05). Conclusions: TLIF and LLIF demonstrate comparable radiographic and clinical outcomes at 24-month follow-up. Surgical technique selection should be individualized based on patient-specific anatomical and clinical factors, considering distinct approach-specific complication patterns.

Objective: Accurate segmentation of surgical instruments in endoscopic images is essential for developing computer-assisted surgical systems, yet creating annotated training datasets remains labor-intensive. This study aimed to evaluate the efficiency of point-based interactive segmentation using foundation models for surgical instrument annotation in spinal endoscopy.Methods: We conducted a retrospective study comparing point-based segmentation performance between Segment Anything Model (SAM) 2.0, SAM 2.1, and domain-adapted MedSAM 2.1 for surgical instrument segmentation in spinal endoscopy. A test set of 308 images from 10 patients undergoing full-endoscopic lumbar decompression/discectomy or biportal endoscopic decompression/discectomy was evaluated. Models were assessed using standardized point prompts placed at the ground truth mask centroid. Primary outcomes included Dice similarity coefficient at single-click and success rate (Dice≥0.85). Secondary analysis evaluated click-to-quality metrics across iterative refinement up to 10 clicks.Results: At single-click, MedSAM 2.1 achieved significantly higher Dice scores than SAM 2.1 (0.937±0.074 vs. 0.844±0.222, p<0.001; 95% confidence interval [CI] for difference, 0.070–0.116) and SAM 2.0 (0.937±0.074 vs. 0.824±0.236, p<0.001; 95% CI for difference, 0.088–0.138), with a 3-fold reduction in variability (standard deviation: 0.074 vs. 0.222). External validation on the publicly available Spine Endoscopic Atlas dataset (202 images from 10 patients) confirmed generalizability, with MedSAM 2.1 achieving Dice 0.918±0.083, compared to 0.724±0.281 for SAM 2.1 and 0.708±0.290 for SAM 2.0 (both p<0.001). Interrater agreement between 2 independent annotators demonstrated excellent reliability (intraclass correlation coefficient, 0.991; 95% CI, 0.986–0.994; mean pairwise Dice, 0.953±0.051). The MedSAM 2.1-assisted workflow reduced annotation time by 75.8% compared to manual polygon annotation (7.7±13.3 seconds vs. 31.8±18.2 seconds per image; p<0.001; 4.1-fold speedup). SAM 2.1 improved progressively with additional clicks (Dice 0.844 to 0.943 at 10 clicks), while MedSAM 2.1 showed nonmonotonic progression (0.937 to 0.947), indicating near-optimal first-click predictions.Conclusion: Domain-adapted MedSAM 2.1 improved single-click annotation accuracy and efficiency for surgical instruments in spinal endoscopy, suggesting that low-resource domain adaptation may facilitate institutional dataset construction for surgical artificial intelligence research.

Purpose: Automated surgical instrument segmentation is a prerequisite for AI-assisted guidance in endoscopic spine surgery. Deployment-realistic comparisons of foundation-model and conventional deep learning architectures — accounting for the detector dependency of bbox-prompted models — remain lacking. Methods: Seven deep learning pipelines were evaluated for binary instrument segmentation: U-Net, Attention U-Net, U-Net++, SegFormer-B0, DeepLabV3+, nnU-Net, and a fully automatic two-stage foundation-model pipeline (MedSAM2-Tiny segmentor + YOLOv8-nano detector). Strict patient-level data splitting was applied across two independent datasets (SNUBH biportal, n = 56 patients; SEA uniportal, n = 60 patients) with three-tier testing (internal, temporal external, cross-dataset external) and two training variants (biportal-only; combined biportal–uniportal). Results: With biportal-only training, the fully automatic foundation-model pipeline ranked last on cross-dataset external testing (DSC 0.776; 0.737 under a strict empty-mask convention), about 9% points below DeepLabV3+ (0.865). The same MedSAM2-Tiny segmentor reached DSC 0.946 with ground-truth bounding-box prompts, leaving a 16.9-point oracle-to-deployment gap driven by detector domain mismatch: 61% missed detections and 39% box-localization error. With combined training, all seven pipelines exceeded DSC 0.94; nnU-Net was highest (0.978), and the foundation-model pipeline (0.962) was not significantly different from SegFormer-B0 (0.960) or DeepLabV3+ (0.958) after Bonferroni correction, although the small external sample does not establish equivalence. The improvement was driven primarily by detector rather than segmentor learning, and all seven main pipelines except the nnU-Net 5-fold ensemble met the 30 frames-per-second real-time threshold. Conclusions: Foundation-model two-stage pipeline performance depends critically on detector training data coverage; once the segmentor approaches its oracle ceiling, detector domain coverage becomes the limiting factor for fully automatic deployment. When combined training is feasible, foundation-model and conventional architectures converge to comparable accuracy, although these rankings are specific to the datasets studied and require validation on independent cohorts. Reporting deployment DSC alongside the ground-truth bounding-box upper bound is recommended for future surgical-segmentation benchmarks.

The cervical spine is a complex, dynamic structure characterized by an expansive range of motion and biological priority for maintaining horizontal gaze. Unlike the rigid thoracolumbar segments, the cervical spine often develops compensatory hyperlordosis in response to global sagittal malalignment. However, aggressive surgical correction of the thoracolumbar axis can paradoxically reduce this compensation, potentially inducing iatrogenic kyphosis. This review synthesizes these dynamics through a "top-down driver" framework, shifting away from traditional pelvic-centric models. By analyzing longitudinal data from asymptomatic Asian cohorts and surgical registries, we evaluated the interplay between C2 slope, T1 slope (T1S), T1S cervical lordosis (T1S-CL), chin brow vertical angle, and integrated measures, such as the cervical-thoracolumbar pelvic angle (CTPA) and TPA. To restore economic balance, the surgeon must move beyond segmental correction and manage the integrated hierarchy of the spinal axis. Master regulators (C2 slope and T1S) dictate the primary axis, whereas secondary responders (T1S-CL mismatch and CTPA) represent the "biomechanical tax" paid by the body. Ultimately, recognizing the cervical spine as the "top-down driver" is essential for successful deformity management. Utilizing the proposed five-step clinical algorithm could allow surgeons to prioritize master regulators, such as C2 slope and T1S-CL mismatch, ensuring more physiologically harmonious global restoration.