https://ojs.sgsci.org/journals/amr <p><em><strong>Advanced Medical Research</strong></em> is an international, fully peer-reviewed journal covering all aspects of Medical, including fields of basic and clinical science research. The mission of the Journal is to foster and promote multidisciplinary studies, especially the practice, policy and theory of Medicine. Medical Science, including fields of basic and clinical science research Taking the lead in timely publication in medical fields, the increased availability of such information is aimed to ultimately promote the publish and exchange of views of new achievements in medicine.</p> <p><strong>ISSN(Online): 2972-3175</strong></p> Global Science Publishing en-US Advanced Medical Research 2972-3175 <p>This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommerical-NoDerivatives 4.0 International License.</p> https://ojs.sgsci.org/journals/amr/article/view/311 <p>Polyp segmentation is a critical task in medical image analysis, particularly in colonoscopy, where it plays a vital role in the early detection and treatment of colorectal cancer. In recent years, advancements in deep learning, especially the application of Convolutional Neural Networks (CNNs) and Transformer models, have significantly improved segmentation performance. Despite these advancements, the generalizability of these models across different datasets is often limited. Recently, Meta released the Segment Anything Model 2 (SAM2), which has demonstrated exceptional performance in both video and image segmentation tasks. This paper aims to develop a universal polyp segmentation model by fine-tuning the pre-trained encoder of SAM2. We introduce a learnable prompt layer within the Transformer blocks and employ a full-scale skip connection structure as a decoder to integrate multi-scale semantic features. Our model outperforms state-of-the-art methods on datasets such as Kvasir-Seg and CVC-ClinicDB. Additionally, our experiments show that the model exhibits excellent transfer learning capabilities on unseen datasets, making it a robust and generalizable model in the field of polyp segmentation.</p> Yixiao Liu Copyright (c) 2025 Yixiao Liu https://creativecommons.org/licenses/by-nc-nd/4.0 2025-02-25 2025-02-25 4 1 1 9 10.62836/amr.v4i1.311 https://ojs.sgsci.org/journals/amr/article/view/310 <p>Objective: To investigate the efficacy and safety of F4.8 visual puncture minirenal mirror in the treatment of seminal vesiculitis. Methods: A total of 60 patients with seminal vesiculitis admitted to the Department of Urology, Affiliated Hospital of Hebei University from July 2022 to July 2024 were selected as the study subjects. Patients treated with F4.8 visual puncture minirenal mirror were assigned to the minirenal mirror group (n = 30), while those treated with pharmacotherapy were assigned to the pharmacotherapy group (n = 30). The basic surgical conditions of the minirenal mirror group were analyzed, and the total effective rate at 3 months, as well as improvements in hematospermia, sexual function, pain symptoms, complications, and recurrence rates at 6 months post-treatment, were compared between the two groups. Results: The total effective rate and improvement in sexual function at 6 months post-treatment in the minirenal mirror group were significantly higher than those in the pharmacotherapy group (<em>p</em> &lt; 0.05). The recurrence rate at 6 months post-treatment was lower in the minirenal mirror group than in the pharmacotherapy group (<em>p</em> &lt; 0.05). No significant complications were observed in the pharmacotherapy group during follow-up. In the minirenal mirror group, 13 cases (43.33%) experienced mild hematuria postoperatively, 5 cases (16.67%) had perineal discomfort, and 1 case (3.33%) had fever. Conclusion: F4.8 visual puncture minirenal mirror is a reliable and safe treatment for seminal vesiculitis.</p> Yanan Chen Fan Yang Dan Shen Xin Liu Lishun Li Deyan Kong Linan Zhang Lianshui Yu Copyright (c) 2025 Yanan Chen, Fan Yang, Dan Shen, Xin Liu, Lishun Li, Deyan Kong, Linan Zhang, Lianshui Yu https://creativecommons.org/licenses/by-nc-nd/4.0 2025-02-19 2025-02-19 4 1 1 7 10.62836/amr.v4i1.310