Generating novel pituitary datasets from open-source imaging data and deep volumetric segmentation.

PURPOSE: The estimated incidence of pituitary adenomas in the general population is 10-30%, yet radiographic diagnosis remains a challenge. Diagnosis is complicated by the heterogeneity of radiographic features in both normal (e.g. complex anatomy, pregnancy) and pathologic states (e.g. primary endocrinopathy, hypophysitis). Clinical symptoms and laboratory testing are often equivocal, which can result in misdiagnosis or unnecessary specialist referrals. Computer vision models can aid in pituitary adenoma diagnosis; however, a major challenge to model development is the lack of dedicated pituitary imaging datasets. We hypothesized that deep volumetric segmentation models trained to extract the sellar and parasellar region from existing whole-brain MRI scans could be used to generate a novel dataset of pituitary imaging. METHODS: Six open-source whole-brain MRI datasets, created for research purposes, were included for model development. Deep learning-based volumetric segmentation models were trained using 318 manually annotated MRI scans from a single open-source MRI dataset. Out-of-distribution volumetric segmentation performance was then tested on 418 MRIs from five held-out research datasets. RESULTS: On our annotated images, agreement between manual and model volumetric segmentations was high. Dice scores (a measure of overlap) ranged 0.76-0.82 for both in-distribution and out-of-distribution model testing. In total, 6,755 MRIs from six data sources were included in the final generated pituitary dataset. CONCLUSIONS: We present the first and largest dataset of pituitary imaging constructed using existing MRI data and deep volumetric segmentation models trained to identify sellar and parasellar anatomy. The model generalizes well across patient populations and MRI scanner types. We hope our pituitary dataset will be an integral part of future machine learning research on pituitary pathologies.

Computed tomography assessment of robotic versus fluoroscopic implant accuracy in sacroiliac joint fusion.

OBJECTIVE: Computed tomography is considered the gold-standard imaging tool to evaluate spinal implant accuracy. However, there are no studies that evaluate the accuracy of robotic sacroiliac joint (SIJ) implant placement using CT to date. The aim of this study was to compare the accuracy of implant placement on CT between robotic and fluoroscopic navigation for SIJ fusion and the subsequent complications and clinical outcomes of suboptimally placed screws. METHODS: A retrospective analysis of SIJ fusions utilizing either robotic or fluoroscopic guidance at a single institution was conducted from 2014 to 2023. Implant placement accuracy was evaluated on intra- or postoperative CT. Primary endpoints were SIJ screw placement accuracy and complications. Secondary endpoints were pain status at the first and second follow-ups and rates of 2-year revision surgery. Statistical analysis was performed using chi-square tests. RESULTS: Sixty-nine patients who underwent 78 SIJ fusions were included, of which 63 were robotic and 15 were fluoroscopic. The mean age of the cohort at the time of surgery was 55.9 ± 14.2 years, and 35 patients (50.7%) were female. There were 135 robotically placed and 34 fluoroscopically placed implants. A significant difference was found in implant placement accuracy between robotic and fluoroscopic fusion (97.8% vs 76.5%, p < 0.001). When comparing optimal versus suboptimal implant placement, no difference was found in the presence of 30-day complications (p = 0.98). No intraoperative complications were present in this cohort. No difference was found in subjective pain status at the first (p = 0.69) and second (p = 0.45) follow-ups between optimal and suboptimal implant placement. No patients underwent 2-year revision surgery. CONCLUSIONS: Use of robotic navigation was significantly more accurate than the use of fluoroscopic navigation for SIJ implant placement. Complications overall were low and not different between optimally and suboptimally placed implants. Suboptimally placed implants did not differ in degree of subjective pain improvement or rates of revision surgery postoperatively.

Endovascular approaches for the treatment of dural carotid-cavernous fistulas: A systematic review.

INTRODUCTION: Dural carotid-cavernous fistulas (dCCFs), also known as indirect carotid-cavernous fistulas, represent abnormal connections between the arterial and venous systems within the cavernous sinus that are typically treated via endovascular approach. We aim to investigate the clinical characteristics of patients with dCCFs based on the endovascular treatment approach and assess angiographic and clinical outcomes. METHODS: A systematic review of the literature was performed. Data including number of patients, demographics, presenting clinical symptoms, etiology of fistula, Barrow classification, and embolization material were collected and evaluated. Outcome measures collected included degree of fistula occlusion, postoperative symptoms, complications, and mean follow-up time. RESULTS: A total of 52 studies were included examining four primary endovascular approaches for treating dCCFs: transarterial, transfemoral-transvenous (transpetrosal or other), transorbital (percutaneous or via cutdown), and direct transfacial access. Overall data was collected from 736 patients with 817 dCCFs. Transarterial approaches exhibit lower dCCF occlusion rates (75.6%) compared to transvenous techniques via the inferior petrosal sinus (88.1%). The transorbital approach via direct puncture or surgical cutdown offers a more direct path to the cavernous sinus, although with greater complications including risk of orbital hematoma. The direct transfacial vein approach, though limited, shows up to 100% occlusion rates and minimal complications. CONCLUSION: We provide a comprehensive review of four main endovascular approaches for dCCFs. In summary, available endovascular treatment options for dCCFs have expanded and provide effective solutions with generally favorable outcomes. While the choice of approach depends on individual patient factors and technique availability, traditional transvenous procedures have emerged as the first-line endovascular treatment. There is growing, favorable literature on direct transorbital and transfacial approaches; however, more studies directly comparing these general transvenous options are necessary to refine treatment strategies.

Development and validation of an artificial intelligence model to accurately predict spinopelvic parameters.

OBJECTIVE: Achieving appropriate spinopelvic alignment has been shown to be associated with improved clinical symptoms. However, measurement of spinopelvic radiographic parameters is time-intensive and interobserver reliability is a concern. Automated measurement tools have the promise of rapid and consistent measurements, but existing tools are still limited to some degree by manual user-entry requirements. This study presents a novel artificial intelligence (AI) tool called SpinePose that automatically predicts spinopelvic parameters with high accuracy without the need for manual entry. METHODS: SpinePose was trained and validated on 761 sagittal whole-spine radiographs to predict the sagittal vertical axis (SVA), pelvic tilt (PT), pelvic incidence (PI), sacral slope (SS), lumbar lordosis (LL), T1 pelvic angle (T1PA), and L1 pelvic angle (L1PA). A separate test set of 40 radiographs was labeled by four reviewers, including fellowship-trained spine surgeons and a fellowship-trained radiologist with neuroradiology subspecialty certification. Median errors relative to the most senior reviewer were calculated to determine model accuracy on test images. Intraclass correlation coefficients (ICCs) were used to assess interrater reliability. RESULTS: SpinePose exhibited the following median (interquartile range) parameter errors: SVA 2.2 mm (2.3 mm) (p = 0.93), PT 1.3° (1.2°) (p = 0.48), SS 1.7° (2.2°) (p = 0.64), PI 2.2° (2.1°) (p = 0.24), LL 2.6° (4.0°) (p = 0.89), T1PA 1.1° (0.9°) (p = 0.42), and L1PA 1.4° (1.6°) (p = 0.49). Model predictions also exhibited excellent reliability at all parameters (ICC 0.91-1.0). CONCLUSIONS: SpinePose accurately predicted spinopelvic parameters with excellent reliability comparable to that of fellowship-trained spine surgeons and neuroradiologists. Utilization of predictive AI tools in spinal imaging can substantially aid in patient selection and surgical planning.

Lumbar Endoscopic Unilateral Laminectomy for Bilateral Decompression in Degenerative Spondylolisthesis.

BACKGROUND: Degenerative spondylolisthesis is an important cause of chronic low back pain and radiculopathy in the adult U.S. POPULATION: Open decompression with or without fusion is considered the standard for management, yet optimal treatment remains controversial. Full endoscopic spine surgery offers an alternative surgical approach with possible advantages. There is a paucity of data on the use of full endoscopic spinal surgery in degenerative spondylolisthesis. Therefore, we present the clinical and radiographic outcomes of 73 patients with low-grade degenerative spondylolisthesis with severe stenosis, who underwent lumbar endoscopic unilateral laminectomy for bilateral decompression. METHODS: Patients with low-grade degenerative spondylolisthesis who underwent a lumbar endoscopic ULBD at 6 spine centers in North America were included in this study. Patients were followed up at 3, 9, and 12 months. Static and dynamic imaging was performed and evaluated routinely before surgery to identify the pathology and grade of spondylolisthesis. Patient-reported outcomes were prospectively collected. RESULTS: This study included 73 patients from 6 spine centers. Sixty-two patients were diagnosed with grade I spondylolisthesis, whereas 11 were diagnosed with grade II spondylolisthesis. Postoperatively, 70 patients reported improved symptoms and pain resolution, whereas 3 patients reported worse pain. Mean visual analog scale back and visual analog scale leg scores and Oswestry Disability Index showed a statistically significant improvement at 3, 9, and 12 months compared with the preoperative period. Radiographically, no patient in our study had progression of the grade of spondylolisthesis. CONCLUSIONS: Patients with low-grade degenerative spondylolisthesis causing severe stenosis can safely be treated with lumbar endoscopic unilateral laminectomy for bilateral decompression. A head-to-head trial should be undertaken to provide a higher level of clinical evidence.

90-Day Emergency Department Utilization and Readmission Rate After Full-Endoscopic Spine Surgery: A Multicenter, Retrospective Analysis of 821 Patients.

BACKGROUND AND OBJECTIVES: Emergency department (ED) utilization and readmission rates after spine surgery are common quality of care measures. Limited data exist on the evaluation of quality indicators after full-endoscopic spine surgery (FESS). The objective of this study was to detect rates, causes, and risk factors for unplanned postoperative clinic utilization after FESS. METHODS: This retrospective multicenter analysis assessed ED utilization and clinic readmission rates after FESS performed between 01/2014 and 04/2023 for degenerative spinal pathologies. Outcome measures were ED utilizations, hospital readmissions, and revision surgeries within 90 days postsurgery. RESULTS: Our cohort includes 821 patients averaging 59 years of age, who underwent FESS. Most procedures targeted the lumbar or sacral spine (85.75%) while a small fraction involved the cervical spine (10.11%). The most common procedures were lumbar unilateral laminotomies for bilateral decompression (40.56%) and lumbar transforaminal discectomies (25.58%). Within 90 days postsurgery, 8.0% of patients revisited the ED for surgical complications. A total of 2.2% of patients were readmitted to a hospital of which 1.9% required revision surgery. Primary reasons for ED visits and clinic readmissions were postoperative pain exacerbation, transient neurogenic bladder dysfunction, and recurrent disk herniations. Our multivariate regression analysis revealed that female patients had a significantly higher likelihood of using the ED (P = .046; odds ratio: 1.77, 95% CI 1.01-3.1 5.69% vs 10.33%). Factors such as age, American Society of Anesthesiologists class, body mass index, comorbidities, and spanned spinal levels did not significantly predict postoperative ED utilization. CONCLUSION: This analysis demonstrates the safety of FESS, as evidenced by acceptable rates of ED utilization, clinic readmission, and revision surgery. Future studies are needed to further elucidate the safety profile of FESS in comparison with traditional spinal procedures.