Objective The aim of this article is to verify the clinical effect of the near-infrared fluorescent liver cancer surgery projection navigation system without display screen. Methods Three patients who need to undergo open hepatectomy for liver cancer in the Affiliated Hospital of Southwest Medical University from March 2021 to May 2021 were included, verifying the accuracy, stability, and time delay effect of the self-developed near-infrared fluorescence projection navigation system for the location of tumor in surgeries. Results The intraoperative tumor location could be accurately displayed by the near-infrared fluorescence projection system and there was no significant difference between the location of the tumor displayed by intraoperative ultrasound. The tumor location displayed by the near-infrared fluorescence projection system was not influenced by the tumor movement and had no visual-time delay. Postoperative pathology confirmed that the projection range was consistent with the tumor range. Conclusion This near-infrared fluorescence projection technology innovates the intraoperative tumor imaging mode and can accurately navigate open hepatectomy in small sample trials, and it is expected to achieve wide clinical application through subsequent iterative optimization and verification.
Objective To investigate the application progress of mixed reality (MR) technology in hepatobiliary and pancreatic fields. Method The relevant literatures on the application of MR technology of the hepatobiliary and pancreatic field in recent years at home and abroad were reviewed. Results MR technology had been widely used in the hepatobiliary and pancreatic field, including preoperative diagnosis and evaluation, surgical plan formulation, doctor-patient communication, intraoperative navigation precision surgery, teaching practice and many other aspects, which had the advantages of shortening the operation time, reducing the difficulty of surgery and improving the success rate of surgery. To some extent, it had promoted the innovation of clinical diagnosis and treatment in the field of liver, gallbladder and pancreas. Conclusions The application and development of MR related techniques are of great significance to the operation and teaching in the hepatobiliary and pancreatic field. With the development and progress of MR technology and modern medicine, MR technology will give full play to its advantages in intelligent real-time navigation hepatobiliary and pancreatic surgery system and promote the further development of hepatobiliary and pancreatic surgery.
ObjectiveTo propose a lung artery segmentation method that integrates shape and position prior knowledge, aiming to solve the issues of inaccurate segmentation caused by the high similarity and small size differences between the lung arteries and surrounding tissues in CT images. MethodsBased on the three-dimensional U-Net network architecture and relying on the PARSE 2022 database image data, shape and position prior knowledge is introduced to design feature extraction and fusion strategies to enhance the ability of lung artery segmentation. The performance metrics for evaluating the model include Dice Similarity Coefficient (DSC), sensitivity, accuracy, and Hausdorff distance (HD95). ResultsThe study included lung artery imaging data from 203 patients, which were divided into training set (100 patients), validation set (30 patients), and test set (73 patients). Through the backbone network, a rough segmentation of the lung arteries was performed to obtain a complete vascular structure; the branch network integrating shape and position information was used to extract features of small pulmonary arteries, reducing interference from the pulmonary artery trunk and left and right pulmonary arteries. Experimental results show that the segmentation model based on shape and position prior knowledge has a higher DSC (82.81%±3.20% vs. 80.47%±3.17% vs. 80.36%±3.43%), sensitivity (85.30%±8.04% vs. 80.95%±6.89% vs. 82.82%±7.29%), and accuracy (81.63%±7.53% vs. 81.19%±8.35% vs. 79.36%±8.98%) compared to traditional three-dimensional U-Net and V-Net methods. HD95 can reach (9.52±4.29) mm, which is 6.05 mm lower than traditional methods, showing excellent performance in segmentation boundaries. ConclusionThe lung artery segmentation method based on shape and position prior knowledge can achieve precise segmentation of lung artery vessels and has potential application value in tasks such as bronchoscopy or percutaneous puncture surgery navigation.