Search

During the drying and processing of raisins, the presence of foreign matter such as fruit stems, branches, stones, and plastics is a common issue. To address this, we propose an enhanced real-time detection approach leveraging an improved YOLOv8 model. This novel method integrates the multi-head self-attention mechanism (MHSA) from BoTNet into YOLOv8's backbone. In the model's neck layer, selected C2f modules have been strategically replaced with RFAConv modules. The model also adopts an EIoU loss function in place of the original CIoU. Our experiments reveal that the refined YOLOv8 boasts a precision of 94.5%, a recall rate of 89.9%, and an F1-score of 0.921, with a mAP reaching 96.2% at the 0.5 IoU threshold and 81.5% across the 0.5–0.95 IoU range. For this model, comprising 13,177,692 parameters, the average time required for detecting each image on a GPU is 7.8 milliseconds. In contrast to several prevalent models of today, our enhanced model excels in mAP0.5 and demonstrates superiority in F1-score, parameter economy, computational efficiency, and speed. This study conclusively validates the capability of our improved YOLOv8 model to execute real-time foreign object detection on raisin production lines with high efficacy. [ABSTRACT FROM AUTHOR]

Background: The efficacy and safety of dabigatran etexilate for Chinese patients with cerebral venous thrombosis (CVT) has not been well established. Methods: CHOICE-CVT was an exploratory, single-center, randomized, open-label study in the National Center for Neurological Disorders involving Chinese patients with CVT aged 18 to 80 years who were randomly assigned (1:1) to either dabigatran etexilate or warfarin. Oral anticoagulants were initiated after 10–15 days of LMWH. The primary efficacy and safety endpoints included the number of patients with recurrent CVT and/or deep venous thrombosis (DVT) and major clinical bleeding within 180 days. Secondary efficacy endpoints included venous recanalization and change in papilledema at day 180. Secondary safety outcomes comprised death, clinical nonmajor bleeding, and any bleeding. The study was registered with ClinicalTrials.gov under NCT03930940. Results: Between October 2017 and February 2023, a total of 89 patients were enrolled and randomly assigned to receive either dabigatran etexilate (n = 44) or warfarin (n = 45). At day 180, the dabigatran etexilate group showed a statistically nonsignificant but likely clinically significant number of patients with recurrent CVT and/or DVT (8 (18.2%; 95% CI, 6.3–30.0) vs 3 (6.7%; 95% CI, 0.0–14.2), p = 0.099, with a power (1-β) of 38.401%) compared with the warfarin group. The dabigatran etexilate group showed a comparable number of patients with clinical major bleeding (0 (0) vs 0 (0) p = 1.000), and clinical nonmajor bleeding (1 (2.3%; 95% CI, 0.0–6.9) vs 1 (2.2%; 95% CI, 0.0–6.7)) but demonstrated a lower risk of any bleeding (1 (2.3%; 95% CI, 0.0–6.9) vs 9 (20.0%; 95% CI, 7.8–32.2)) compared with the warfarin group. Most patients in both groups achieved venous recanalization according to the Modified Qureshi scale (27 (75%; 95% CI, 60.1–89.9) in the dabigatran etexilate group vs 34 (82.9%; 95% CI, 70.9–95.0) in the warfarin group) and exhibited improvement in papilledema as per the Frisén classification (35 (97.2%; 95% CI, 91.6–100.0) in the dabigatran etexilate group vs 37 (88.1%, 95% CI, 77.9–98.3) in the warfarin group). Conclusions: These findings regarding efficacy and safety support the consideration of dabigatran etexilate therapy as a viable treatment option for Chinese patients with CVT. [ABSTRACT FROM AUTHOR]