Background Parasellar invasion of pituitary adenomas (PAs) into the cavernous sinus (CS) is common. The management of the CS component of PA remains controversial. Objective The objective of this study was to analyze CS involvement in PA treated with endoscopic endonasal approaches, including incidence, surgical risks, surgical strategies, long-term outcomes, and our treatment algorithm. Methods We reviewed a series of 176 surgically treated PA with particular attention to CS involvement and whether the CS tumor was approached medial or lateral to the internal carotid artery. Results The median duration of follow-up was 36 months. Macroadenomas and nonfunctional adenomas represented 77 and 60% of cases, respectively. CS invasion was documented in 23% of cases. CS involvement was associated with a significantly diminished odds of gross total resection (47 vs. 86%, odds ratio [OR]: 5.2) and increased the need for subsequent intervention (4 vs. 40%, OR: 14.4). Hormonal remission was achieved in 15% of hormonally active tumors. Rates of surgical complication were similar regardless of CS involvement. Conclusion Our tailored strategy beginning with a medial approach and adding lateral exposure as needed resulted in good outcomes with low morbidity in nonfunctional adenomas. Functional adenomas involving the CS were associated with low rates of hormonal remission necessitating higher rates of additional treatment.

Early prediction of recurrence in high-grade glioma (HGG) is critical due to its aggressive nature and poor prognosis. Distinguishing true recurrence from treatment-related changes, such as radionecrosis, is a major diagnostic challenge. Machine learning (ML) offers a novel approach, leveraging advanced algorithms to analyze complex imaging data with high precision. A comprehensive search of PubMed, Embase, Scopus, Web of Science, and Google Scholar identified eligible studies. The sensitivity, specificity, accuracy, precision, F1 score, and the (area under the curve) AUC items were extracted from the included studies. After screening 1077 records, seven studies met the eligibility criteria for the systematic review, of which five were included in the meta-analysis. ML algorithm, particularly Support Vector Machines (SVM), demonstrated promising performance. A meta-analysis of five studies revealed a pooled sensitivity of 0.95 (95% CI: 0.84-0.99) and specificity of 0.80 (95% CI: 0.69-0.88). Additionally, the positive diagnostic likelihood ratio (DLR) was 4.75 (95% CI: 2.91-7.76), the negative DLR was 0.06 (95% CI: 0.02-0.21), and the diagnostic odds ratio was 80.97 (95% CI: 17.5-374.61). The diagnostic score was calculated as 4.39 (95% CI: 2.86-5.93), and the AUC was 0.86 (95% CI: 0.83-0.89). Subgroup analyses showed SVM-based models with higher sensitivity (0.98 vs. 0.87) and specificity (0.82 vs. 0.77) than non-SVM (p = 0.13). Comparing glioblastoma and Grade 3 tumors, sensitivities were 94 % vs. 97 %, and specificities were 79 % vs. 83 %, with no significant heterogeneity. These findings suggest that ML models, particularly SVM, offer promising diagnostic performance in distinguishing true tumor recurrence from treatment-related changes.

To discuss the clinical presentation, pathological diagnosis, and surgical outcome for a series of 42 consecutive patients treated for lateral and third ventricular tumors. This is a retrospective series study conducted between 2001 and 2015 and included 42 patients (mean age: 25 years; range: 2 months-65 years) with lateral and third ventricle tumors surgically treated at King Khaled University Hospital, Riyadh, Kingdom of Saudi Arabia. Demographic, clinical, radiological, surgical, histopathological, and follow up data were analyzed. The most common symptoms at presentation included headache (69%), nausea/vomiting (38%), visual deficits (24%), and seizures (17%). Lesions were located in the lateral ventricle in 15 patients, third ventricle in 20 patients, and involved both the lateral and third ventricles in 7 patients. The most common tumor types in the overall cohort were colloid cysts (n=6) and pineal tumors (n=6). The postoperative complication rate was 36%. The most common postoperative complications were seizure and hydrocephalus (n=5 each, 12%). Surgical mortality was 5%. The selection of the surgical approach for intraventricular tumor resection is fundamentally dependent on the surgeon`s experience and preference. We recommend that this decision be based on the anatomic considerations that provide the best and safest access to the mass, rather than on the risk of seizure following transcortical approach.

In this paper, we study and evaluate the task of semantic segmentation of the spinal cord in ultrasound medical imagery. This task is useful for neurosurgeons to analyze the spinal cord movement during and after the laminectomy surgical operation. Laminectomy is performed on patients that suffer from an abnormal pressure made on the spinal cord. The surgeon operates by cutting the bones of the laminae and the intervening ligaments to relieve this pressure. During the surgery, ultrasound waves can pass through the laminectomy area to give real-time exploitable images of the spinal cord. The surgeon uses them to confirm spinal cord decompression or, occasionally, to assess a tumor adjacent to the spinal cord. The Freely pulsating spinal cord is a sign of adequate decompression. To evaluate the semantic segmentation approaches chosen in this study, we constructed two datasets using images collected from 10 different patients performing the laminectomy surgery. We found that the best solution for this task is Fully Convolutional DenseNets if the spinal cord is already in the train set. If the spinal cord does not exist in the train set, U-Net is the best. We also studied the effect of integrating inside both models some deep learning components like Atrous Spatial Pyramid Pooling (ASPP) and Depthwise Separable Convolution (DSC). We added a post-processing step and detailed the configurations to set for both models.