Comparison of microscopic full-laminectomy (open surgery) and microendoscopic minimally invasive hemilaminectomy for thoracic extramedullary spinal tumours.

BACKGROUND: Minimally invasive treatments for spinal cord tumours are common. The aim of this study was to compare the perioperative outcomes of patients with thoracic extramedullary spinal tumours (TEST) treated by microendoscopic minimally invasive surgery-hemilaminectomy through a homemade tubular retractor (MIS-TR) and microscopic full laminectomy (open surgery). METHODS: Between February 2016 and February 2021, 51 patients with TEST were included. According to their clinical data, patients were classified into the MIS-TR group (n = 30) and the open surgery group (n = 21) and assessed. RESULTS: In both groups, the mean operation time, change in perioperative ASIA score, and modified Macnab score were comparable. The average postoperative hospital stay in the MIS-TR group was substantially shorter than that in the open surgery group (p < 0.0001). The mean blood loss volume in the MIS-TR group was substantially lower than that in the open surgery group (p = 0.001). The perioperative complication rate in the MIS-TR group was considerably lower than that in the open surgery group (p < 0.0001). At the 3-month follow-up, there was no substantial difference in the Oswestry Disability Index (ODI) score improvement between the two groups. Nonetheless, at the 12-month follow-up, the average ODI in the MIS-TR group was considerably lower than that in the open surgery group (p = 0.023). The main influencing factors for complete postoperative recovery were preoperative ASIA score (OR 7.848, P = 0.002), surgical complications (OR 0.017, P = 0.008) and age (OR 0.974, P = 0.393). CONCLUSIONS: MIS-TR is safer and more effective than open surgery for treating TEST, but the long-term recovery of MIS-TR is not better than that of open surgery.

Multi-center application of a convolutional neural network for preoperative detection of cavernous sinus invasion in pituitary adenomas.

OBJECTIVE: Cavernous sinus invasion (CSI) plays a pivotal role in determining management in pituitary adenomas. The study aimed to develop a Convolutional Neural Network (CNN) model to diagnose CSI in multiple centers. METHODS: A total of 729 cases were retrospectively obtained in five medical centers with (n = 543) or without CSI (n = 186) from January 2011 to December 2021. The CNN model was trained using T1-enhanced MRI from two pituitary centers of excellence (n = 647). The other three municipal centers (n = 82) as the external testing set were imported to evaluate the model performance. The area-under-the-receiver-operating-characteristic-curve values (AUC-ROC) analyses were employed to evaluate predicted performance. Gradient-weighted class activation mapping (Grad-CAM) was used to determine models' regions of interest. RESULTS: The CNN model achieved high diagnostic accuracy (0.89) in identifying CSI in the external testing set, with an AUC-ROC value of 0.92 (95% CI, 0.88-0.97), better than CSI clinical predictor of diameter (AUC-ROC: 0.75), length (AUC-ROC: 0.80), and the three kinds of dichotomizations of the Knosp grading system (AUC-ROC: 0.70-0.82). In cases with Knosp grade 3A (n = 24, CSI rate, 0.35), the accuracy the model accounted for 0.78, with sensitivity and specificity values of 0.72 and 0.78, respectively. According to the Grad-CAM results, the views of the model were confirmed around the sellar region with CSI. CONCLUSIONS: The deep learning model is capable of accurately identifying CSI and satisfactorily able to localize CSI in multicenters.