Medical image registration plays an important role in medical diagnosis and treatment planning. However, the current registration methods based on deep learning still face some challenges, such as insufficient ability to extract global information, large number of network model parameters, slow reasoning speed and so on. Therefore, this paper proposed a new model LCU-Net, which used parallel lightweight convolution to improve the ability of global information extraction. The problem of large number of network parameters and slow inference speed was solved by multi-scale fusion. The experimental results showed that the Dice coefficient of LCU-Net reached 0.823, the Hausdorff distance was 1.258, and the number of network parameters was reduced by about one quarter compared with that before multi-scale fusion. The proposed algorithm shows remarkable advantages in medical image registration tasks, and it not only surpasses the existing comparison algorithms in performance, but also has excellent generalization performance and wide application prospects.
Objective To discuss the effectiveness of breast reconstruction with dual plane prosthesis implantation or anterior pectoralis prosthesis implantation under endoscopy by using prospective comparative study, in order to provide a reference for clinical surgical selection. Methods A total of 54 female patients with breast cancer admitted between January 2023 and December 2023 and met the selection criteria were selected as research subjects. According to the random number table, 54 patients were divided into trial group and control group with 27 cases in each. The patients in the trial group and control group were treated with dual plane prosthesis implantation and anterior pectoralis prosthesis implantation for breast reconstruction after glandular resection under endoscopy, respectively. There was no significant difference between the two groups (P>0.05) in the terms of age, body mass index, affected side, breast clinical stages, molecular typing, disease duration, breast volume of healthy side, breast ptosis of affected side, and preoperative Breast-Q score (social mental health, sexual health, breast satisfaction, chest somatic health). The operation-related indicators (operation time, total volume of drainage within 7 days after operation, extubation time, and hospital stay), occurrence of complications, breast reconstruction efficacy related indicators (transverse and longitudinal distance difference), and the pre- and post-operative differences (change values) of Breast-Q scores for each item were compared between the two groups. Results There was no significant difference in operation time, total volume of drainage within 7 days after operation, extubation time, and hospital stay between the two groups (P>0.05). All patients of the two groups were followed up 3-12 months (mean, 6.3 months). Three patients (11.11%) in trial group and 5 patients (18.52%) in control group experienced complications, and there was no significant difference in the occurrence of complications (P>0.05). At 7 days after operation, the transverse and longitudinal distance differences were significantly less in trial group than in control group (P<0.05). The Breast-Q scores of the two groups at 7 days after operation were significantly higher in all items than those before operation (P<0.05), but there was no significant difference in all change values between the two groups (P>0.05). ConclusionFor patients with breast cancer, comparison of breast reconstruction with anterior pectoralis prosthesis implantation, breast reconstruction with dual plane prosthesis implantation has better breast reconstruction effectiveness and higher safety.