Radiologic Examination of High Riding Vertebral Artery and Analysis of Secure Areas.

OBJECTIVE: To radiologically examine the pedicle, lamina, and vertebral artery foraminal anatomies at the C2 vertebra for pedicular and laminar screw instrumentation at the axis in a Turkish population. METHODS: From 2018 to 2019, we evaluated 100 patients who underwent cervical computed tomography (CT) for various reasons (excluding cervical pathologies) at Marmara University Hospital. The C2 pedicles were measured on CT images using measurement tools. In addition, axial computed tomography was performed at 0.1 mm intervals. Bilateral measurements were performed for each case. RESULTS: The median right and left pedicle axial diameters were 5.01 and 5.09 mm, respectively for the male patients and 4.31 and 4.38 mm for the female patients, showing a statistically significant difference between the sexes (P < 0.01). Of the patients, 15% had narrow pedicles. The pedicle sagittal diameters were smaller than 5 mm in 30% of the computed tomographic series. The internal height was <2 mm in 4% of the cases. CONCLUSIONS: Our findings suggest significant individual and sex-related differences. Vertebral artery groove anomalies are commonly observed. Before performing a posterior craniocervical instrumentation surgery, a computed tomography (CT) examination is beneficial because high-riding vertebral arteries must be kept in mind in determining the appropriate screw diameter and screw trajectory.

Deep Learning-Assisted Segmentation and Classification of Brain Tumor Types on Magnetic Resonance and Surgical Microscope Images.

OBJECTIVE: The primary aim of this research was to harness the capabilities of deep learning to enhance neurosurgical procedures, focusing on accurate tumor boundary delineation and classification. Through advanced diagnostic tools, we aimed to offer surgeons a more insightful perspective during surgeries, improving surgical outcomes and patient care. METHODS: The study deployed the Mask R-convolutional neural network (CNN) architecture, leveraging its sophisticated features to process and analyze data from surgical microscope videos and preoperative magnetic resonance images. Resnet101 and Resnet50 backbone networks are used in the Mask R-CNN method, and experimental results are given. We subsequently tested its performance across various metrics, such as accuracy, precision, recall, dice coefficient (DICE), and Jaccard index. Deep learning models were trained from magnetic resonance imaging and surgical microscope images, and the classification result obtained for each patient was combined with the weighted average. RESULTS: The algorithm exhibited remarkable capabilities in distinguishing among meningiomas, metastases, and high-grade glial tumors. Specifically, for the Mask R-CNN Resnet 101 architecture, precision, recall, DICE, and Jaccard index values were recorded as 96%, 93%, 91%, and 84%, respectively. Conversely, for the Mask R-CNN Resnet 50 architecture, these values stood at 94%, 89%, 89%, and 82%. Additionally, the model achieved an impressive DICE score range of 94%-95% and an accuracy of 98% in pathology estimation. CONCLUSIONS: As illustrated in our study, the confluence of deep learning with neurosurgical procedures marks a transformative phase in medical science. The results are promising but underscore diverse data sets' significance for training and refining these deep learning models.

Assessment of the Quality and Reliability of YouTube as an Information Source for Transforaminal Interbody Fusion.

BACKGROUND: This study aims to assess the quality and reliability of the information for patients from YouTube videos on transforaminal interbody fusion (TLIF). MATERIAL AND METHODS: One hundred videos were listed by inputting "TLIF," "TLIF surgery," and "transforaminal interbody fusion" in the YouTube search engine. The top 50 most popular videos based on video power index (VPI), view ratio, and exclusion criteria were selected for review. One orthopedic consultant surgeon and one neurosurgeon consultant analyzed the videos together. The modified DISCERN score, the Global Quality Score (GQS), the Journal of the American Medical Association (JAMA) score, and a novel interbody fusion score were used to evaluate videos. Data of video length, view count, number of likes and dislikes, like ratio (like x 100/(like+dislike)), video source, and comment rate were collected. RESULTS: The quality of the videos could have been better according to all scoring systems, regardless of the video source. The scores of the videos published by patients and commercials were significantly lower than those of physicians and allied professionals (p <0.05). VPI and view ratios were similar in all sources.  Conclusion: The study demonstrates that YouTube videos providing information related to TLIF surgery are available and accessed by the public. The results of this study would suggest that YouTube is not currently an appropriate source of information on TLIF surgery for patients. Most of the YouTube videos about TLIF surgery contain information about the surgical technique and have limited information about the post-operative condition of the patients.