Gastric cancer remains a highly prevalent malignancy worldwide, with surgical resection currently constituting the cornerstone of treatment aimed at improving long-term patient survival. Owing to their notable advantages, including reduced surgical trauma and accelerated postoperative recovery, minimally invasive procedures are progressively supplanting conventional open surgery and have become the mainstream approach in gastric cancer management. Concurrently, the rapid advancement of artificial intelligence (AI) technologies has enabled real-time intraoperative monitoring of surgical scenes, thereby furnishing novel technical support for adjunctive decision-making, surgical navigation, and skill assessment during gastrectomy. This article provides a systematic review of the current status of AI applications in minimally invasive gastric cancer surgery, with a particular focus on research progress pertaining to instrument recognition, surgical phase identification, delineation of normal anatomical structures, detection of metastatic foci, and early warning of intraoperative adverse events. Furthermore, we discuss the potential value of AI in enhancing surgical efficiency, ensuring patient safety, and optimizing surgical education. On this basis, we further analyze the principal challenges and inherent risks confronting current AI systems, with the aim of informing future technological innovation and facilitating clinical translation.

Objective:To investigate the effect of tranexamic acid combined with rivaroxaban on perioperative blood loss in patients undergoing posterior lumbar interbody fusion and its potential benefits.Methods:This is a retrospective study. The clinical data of 90 patients who underwent posterior lumbar interbody fusion for lumbar spinal stenosis or spondylolisthesis at Affiliated Hospital of Jining Medical University between September 2019 and September 2021 were analyzed. These patients were divided into two groups: group A ( n = 46) and group B ( n = 44) based on their medication. Patients in group A received an intravenous infusion of 0.5 g tranexamic acid and 100 mL of 5% glucose injection 15 minutes before the surgical incision. The incision wound was soaked externally with 1 g of tranexamic acid solution for 5 minutes before the surgical incision was closed, and it was suctioned before its closure. Patients in group B received the same procedure, except that oral rivaroxaban was administered 10 mg, once daily, after surgery till 35 days after surgery. The operative time, intraoperative blood loss, and the amount of drainage were recorded. Total blood loss, occult blood loss, incidence of lower extremity deep vein thrombosis, incidence of pulmonary embolism and epidural hematoma, and C-reactive protein levels were determined. Results:There were no significant differences in operative time, intraoperative blood loss, the amount of drainage, total blood loss, and occult blood loss between the two groups (all P > 0.05). Postoperative C-reactive protein levels in group A [29.94 (15.75, 50.25) mg/L] were significantly higher than those in group B [7.89 (4.94, 11.10) mg/L, Z = -5.68; P < 0.05]. Lower extremity deep vein thrombosis, pulmonary embolism, or epidural hematoma did not occur in either group. In group A, one patient was infused with 200 mL of leucodepleted red blood cell suspension, while the other patient received 150 mL of autologous blood transfusion. In group B, two patients were infused with 525 mL and 200 mL of leucodepleted red blood cell suspensions, respectively, while the rest did not require blood transfusion. Conclusion:The combined use of tranexamic acid and rivaroxaban after posterior lumbar interbody fusion does not increase perioperative bleeding, and it has additional anti-inflammatory effects without increasing the incidence of lower extremity deep vein thrombosis and pulmonary embolism, as well as the formation of epidural hematomas and the need for blood transfusion.

Objective To investigate the geometric feature of femoral medullary cavity through CT scanning and it's matching with femoral intramedullary nail,and to analysis the reason for difficulties in implanting distal lock pin.Methods Thirty dried femur specimens were measured through CT scanning,and twenty images were taken evenly according to the total length of shaft of femur from each femur.In each image,the data of the central axis point and eight points around medullary cavity wall in X and Y axes were obtained,which were used to reconstruct the three-dimensional models of medullary cavity,central axis,intramedullary nail by computer software.And the models were overlapped for comparison.Then the coronal and sagittal fold line charts for central axis of medullary cavity were drawn.The inserting process of intramedullary nail was simulated to observe whether the nail would punch out of the medullary cavity wall.Results The central axis of femoral medullary cavity and intramedullary nail were overlapped and compared.They matched well in the coronal plane,but the curves of femoral medullary cavity were larger than those of intramedullary nails in sagittal plane.While simulating the inserting process of intramedullary nail,6 nails punched out of the medullary cavity wall in coronal plane (20％,6/30),so did 13 nails in sagittal plane (43％,13/30).Conclusion Intramedullary nails match well with most of the femoral medullary cavities.However,the anatomic structure of the femoral medullary cavity differs individually.Curves of some femoral medullary cavity are large,which can cause deformation of intramedullary nail,and this is the main reason for the failure of distal locking.