Search

Aiming at defects such as low contrast in infrared ship images, uneven distribution of ship size, and lack of texture details, which will lead to unmanned ship leakage misdetection and slow detection, this paper proposes an infrared ship detection model based on the improved YOLOv8 algorithm (R_YOLO). The algorithm incorporates the Efficient Multi-Scale Attention mechanism (EMA), the efficient Reparameterized Generalized-feature extraction module (CSPStage), the small target detection header, the Repulsion Loss function, and the context aggregation block (CABlock), which are designed to improve the model's ability to detect targets at multiple scales and the speed of model inference. The algorithm is validated in detail on two vessel datasets. The comprehensive experimental results demonstrate that, in the infrared dataset, the YOLOv8s algorithm exhibits improvements in various performance metrics. Specifically, compared to the baseline algorithm, there is a 3.1% increase in mean average precision at a threshold of 0.5 (mAP (0.5)), a 5.4% increase in recall rate, and a 2.2% increase in mAP (0.5:0.95). Simultaneously, while less than 5 times parameters, the mAP (0.5) and frames per second (FPS) exhibit an increase of 1.7% and more than 3 times, respectively, compared to the CAA_YOLO algorithm. Finally, the evaluation indexes on the visible light data set have shown an average improvement of 4.5%. [ABSTRACT FROM AUTHOR]

PURPOSE： To investigate the expression of tissue-active protein kinase C receptor 1 (RACK1) and epithelin glycoprotein 40 (EGP40) in oral squamous cell carcinoma (OSCC) and their relationship with clinicopathological features and prognosis., Methods: A total of 103 patients with OSCC who were admitted to Shangrao People's Hospital from January 2016 to February 2019 were prospectively selected as the research subjects. All patients underwent radical resection of OSCC and were followed up for 3 years. Immunohistochemistry was used to detect the positive expression levels of RACK1 and EGP40 in cancer tissues and adjacent tissues. The positive expression of RACK1 and EGP40 in cancer tissues and adjacent tissues were compared. The relationship between the positive expression level of RACK1 and EGP40 in cancer tissues of OSCC patients and clinicopathological parameters was analyzed. Factors affecting postoperative recurrence and metastasis in OSCC patients were analyzed. The relationship between the expression of RACK1 and EGP40 in cancer tissues and postoperative disease-free survival of OSCC patients was analyzed. SPSS 18.0 software package was used for statistical analysis of the data., Results: The positive expression rate of RACK1 and EGP40 in cancer tissues was significantly higher than those in adjacent tissues (P＜0.05). The positive expression rate of RACK1 and EGP40 in cancer tissues of OSCC patients with poorly differentiated, stage III, cervical lymph node metastasis, and infiltrating vessels was significantly higher than that in patients with moderate and high differentiation, stage II, no cervical lymph node metastasis, and no infiltrating vessels(P＜0.05). The positive expression rate of RACK1 in cancer tissue of OSCC patients in T3 stage was significantly higher than that in T2 stage(P＜0.05). Cox multivariate regression analysis showed pathological grade (RR=6.290, 95%CI: 2.588-15.287), cervical lymph node metastasis(RR=5.995, 95%CI: 2.467-14.571), RACK1 positive rate (RR=4.495, 95%CI: 1.850-10.925) and EGP40 positive rate (RR=4.559, 95%CI: 1.876-11.079) were factors affecting the recurrence and metastasis of OSCC patients after surgery(P＜0.05). The disease-free survival curve of patients with negative expression of RACK1 was significantly better than that of patients with positive expression (P＜0.05). The disease-free survival curve of patients with negative expression of EGP40 was significantly better than that of patients with positive expression (P＜0.05)., Conclusions: The expression of RACK1 and EGP40 in cancer tissues of OSCC patients is related to clinicopathological parameters and prognosis. Patients with positive expression of RACK1 and EGP40 have a high risk of recurrence and metastasis after surgery.