Objective To assess clinical outcomes of therapeutic video-mediastinoscopy （VMS）. Methods Clinical data of 82 patients undergoing VMS in Zhongshan Hospital of Dalian University from December 2008 to October 2011 were retrospectively analyzed. Among them，24 patients received therapeutic VMS，including 18 men and 6 women with their median age of 56 （22-81） years. Three patients underwent operation through a neck incision，4 patients through a parasternal incision，and 17 patients through a lateral intercostal incision. Five patients received local anesthesia and basal anesthesia，and all the other patients received general anesthesia through single-lumen or double-lumen endotracheal intubation. Results Twelve patients with pleural effusion underwent pleural or lung biopsy and talc pleurodesis. Pathology examination showed malignant diseases in 11 patients and tuberculous pleural effusion in 1 patient. The median operation time was 35 （30-50） minutes，and postoperative hospital stay was 3-6 days. These patients were followed up for 1 month without recurrence of pleural effusion. Ten patients with mediastinal mass received pathological diagnosis and complete mass resection with their median operation time of 55 （30-270） minutes and median hospital stay of 7 （5-40） days. Two patients with hyperhidrosis underwent bilateral intercostal VMS sympathectomy. Their operation time was 60 minutes and 50 minutes respectively，and their hospital stay was 3 days. Postoperatively their sweating symptoms obviously resolved. They were followed up for 3 months，and their hands，feet and armpit were warm and dry. There was no in-hospital death in this group. Two patients （8.3%） had postoperative complications including 1 patient with phrenic nerve injury and another patient with pneumonia. Opioid analgesic drugs were not used postoperatively in 9 patients. Conclusion Therapeutic VMS is a safe，effective，minimally invasive and cosmetic procedure，but it is not suitable for resection of a large mediastinal mass.
ObjectiveTo evaluate the value of imaging quantification parameters in artificial intelligence (AI) assisted diagnosis systems in clinical decision-making for lung nodules ≤2 cm and the diagnostic efficacy of AI. MethodsLung nodule patients admitted to Zhongshan Hospital affiliated with Dalian University from 2020 to 2023 were included. Imaging parameters of lung nodules were extracted using AI assisted diagnosis systems. Multifactor analysis was used to screen predictors for distinguishing benign and malignant nodules and high-risk predictors for recurrent invasive adenocarcinoma, and a diagnostic model was established and its performance evaluated. The diagnostic efficacy of the AI system was judged according to pathological results. ResultsA total of 594 patients with lung nodules were included, including 202 males and 392 females, with an average age of 24-82 (58.75±11.55) years. Volume, average CT value, and 3D maximum diameter of non-solid nodules were independent predictors of malignant nodules, with thresholds of 287.4 mm3, -491 HU, and 12.0 mm, respectively. The area under the curve (AUC) for diagnostic efficacy was ranked from high to low as combined model (0.802), volume (0.783), average CT value (0.749), and 3D maximum diameter (0.714); the average CT value and 3D long diameter of solid nodules were independent predictors of malignant nodules, with thresholds of -81 HU and 17.5 mm, respectively, and AUC values of 0.874 and 0.686, respectively, with the combined prediction AUC of 0.957; the mass of cystic nodules was an independent predictor of malignancy when the mass >180.7 mg. Independent predictors of high recurrence risk of invasive adenocarcinoma in non-solid nodules were consolidation-tumor ratio (CTR), average CT value, 3D long diameter, and volume, with thresholds of 0.14, -386 HU, 15.6 mm, and 1018.9 mm3, respectively, and diagnostic efficacy was ranked from high to low as combined model (0.788), 3D long diameter (0.735), volume (0.725), average CT value (0.720), and CTR (0.697). The accuracy of AI in predicting benign and malignant target nodules was 87.4%, with positive predictive value of 96.6% and negative predictive value of 58.9%. ConclusionIn clinical decision-making for lung nodules ≤2 cm, AI assisted diagnosis systems have high application value.