The timely and efficient generation of weed maps is essential for weed control tasks and precise spraying applications. Based on the general concept of site-specific weed management (SSWM), many researchers have used unmanned aerial vehicle (UAV) remote sensing technology to monitor weed distributions, which can provide decision support information for precision spraying. However, image processing is mainly conducted offline, as the time gap between image collection and spraying significantly limits the applications of SSWM. In this study, we conducted real-time image processing onboard a UAV to reduce the time gap between image collection and herbicide treatment. First, we established a hardware environment for real-time image processing that integrates map visualization, flight control, image collection, and real-time image processing onboard a UAV based on secondary development. Second, we exploited the proposed model design to develop a lightweight network architecture for weed mapping tasks. The proposed network architecture was evaluated and compared with mainstream semantic segmentation models. Results demonstrate that the proposed network outperform contemporary networks in terms of efficiency with competitive accuracy. We also conducted optimization during the inference process. Precision calibration was applied to both the desktop and embedded devices and the precision was reduced from FP32 to FP16. Experimental results demonstrate that this precision calibration further improves inference speed while maintaining reasonable accuracy. Our modified network architecture achieved an accuracy of 80.9% on the testing samples and its inference speed was 4.5 fps on a Jetson TX2 module (Nvidia Corporation, Santa Clara, CA, USA), which demonstrates its potential for practical agricultural monitoring and precise spraying applications.

No abstract

ObjectiveThe objective of this study was to compare outcomes of re-repair with those of mitral valve replacement (MVR) for failed initial mitral valve repair (MVr).MethodsWe searched the Pubmed, Embase, and Cochrane Library databases for studies that compared mitral valve re-repair with MVR for the treatment of failed initial MVr. Data were extracted by two independent investigators and subjected to a meta-analysis. Odds ratio (OR), risk ratio (RR), hazard ratio (HR), ratio difference (RD), mean difference (MD), and 95% confidence interval (CI) were calculated with the Mantel-Haenszel and inverse-variance methods for mode of repair failure, perioperative outcomes, and follow-up outcomes.ResultsEight retrospective cohort studies were included, with a total of 938 patients, and mean/median follow-up ranged from 1.8 to 8.9 years. Pooled incidence of technical failure was 41% (RD: 0.41; 95% CI: 0.32 to 0.5; P = 0.00; I2 = 86%; 6 studies, 846 patients). Pooled mitral valve re-repair rate was 36% (RD: 0.36; 95% CI: 0.26–0.46; P = 0; I2 = 91%; 8 studies, 938 patients). Pooled data showed significantly lower perioperative mortality (RR: 0.22; 95% CI: 07 to 0.66; I2 = 0%; P = 0.008; 6 studies, 824 patients) and significantly lower long-term mortality (HR:0.42; 95% CI: 0.3 to 0.58; I2 = 0%; P = 0; 7 studies, 903 patients) in the re-repair group compared with MVR.ConclusionsMitral valve re-repair was associated with better immediate and sustained outcomes for failed MVr and should be recommended if technically feasible.

BackgroundPost-infarction left ventricular (LV) pseudoaneurysm is a rare mechanical complication of myocardial infarction that carries a substantial risk of sudden rupture. The purpose of this study was to compare the surgical results of post-infarction LV pseudoaneurysm with those of conservative treatment.MethodsFrom 2016 to 2021, 22 patients were hospitalized for LV pseudoaneurysm, including 17 cases (77.3%) caused by myocardial infarction. Of the 17 patients, 10 (58.8%) underwent surgical repair, while seven (41.2%) were treated medically. The clinical course, echocardiograph data, and surgical outcomes were analyzed. Survival rates of the surgical and conservative groups were compared.ResultsThere were no perioperative deaths. Intra-aortic balloon pumping support was required in two (20%) patients. No follow-up mortality was observed in the surgical group and at the last follow-up, all the patients were classified as New York Heart Association class I–II. In the conservative group, there was one (14.3%) hospital death and two (28.6%) additional deaths during follow-up. A significant difference was found in survival between the two groups (P = 0.024).ConclusionsSurgical repair of post-infarction LV pseudoaneurysm can be performed with good results, while conservative treatment carries a significant risk of sudden death. Surgical repair is indicated for every patient diagnosed, even those with a small pseudoaneurysm without symptoms.

Objectives: To assess the outcomes of transcatheter mitral valve repair (TMVr) for failed previous surgical mitral valve repair (MVr). Methods: We searched Pubmed, Embase, and Cochrane Library databases for studies that reported the outcomes of TMVr for failed initial surgical MVr. Data were extracted by 2 independent investigators and subjected to meta-analysis. The 95% confidence interval (CI) was calculated for preoperative demographics, peri-operative outcomes, and follow-up outcomes using binary and continuous data from single-arm studies. Results: Eight single-arm studies were included, with a total of 212 patients, and mean follow-up ranged from 1.0 to 15.9 months. The pooled rate of residual procedural mitral regurgitation ≤mild was 76% (95% CI: 67%~84%; I 2 = 0%; 7 studies, 199 patients). During follow-up, mitral regurgitation ≤mild was found in 68% of patients (95% CI: 52%~82%; I 2 = 57%; 6 studies, 147 patients). Follow-up survival was 94% (95% CI: 88%~98%; I 2 = 0%; 7 studies, 196 patients). 83% patients (95% CI: 75%~89%; I 2 = 47%; 6 studies, 148 patients) were in NYHA class I or II. Conclusions: TMVr for failed surgical MVr was safe and effective, which should be recommended in selected patients if technically feasible.

Background: The definitive treatment for chronic thromboembolic pulmonary hypertension (CTEPH) is pulmonary endarterectomy (PEA), which has good longterm outcomes. However, after surgery, a quarter of the patients still have residual pulmonary hypertension (RPH). In pulmonary hemodynamics, there are no unified criteria for RPH, even though the level may affect long-term survival.Methods: Between March 1997 and December 2021, 253 CTEPH patients were treated at our center with PEA. Patients were evaluated retrospectively and classified into early (1997)(1998)(1999)(2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013)(2014) and late (2015-2021) groups. The clinical characteristics and perioperative outcomes of the two groups were compared, and risk factor analysis for RPH and long-term survival for all cases was performed.Results: There was no statistically significant difference in demographics between the two groups. However, the Early Group had a significantly higher rate of perioperative death (9.8% vs. 1.2%, p = .001), RPH (48.8% vs. 14.0%, p < .001), and reperfusion pulmonary edema (18.3% vs. 2.9%, p < .001). The median follow-up time was 66.0 months, and overall survival rates at 5, 10, 15, and 18 years after PEA were 91.2%, 83.9%, 64.5%, and 46.0%, respectively. Age and postoperative systolic pulmonary artery pressure (sPAP) were independently related to long-term outcomes in the multivariate Cox analyses. Patients with postoperative sPAP less than 46 mm Hg had a higher chance of survival. Conclusions: PEA improved CTEPH hemodynamics immediately and had a positive effect on long-term survival. Patients with postoperative sPAP ≥ 46 mm Hg indicate clinically significant RPH and have a lower long-term survival rate.

Background Pulmonary artery sarcoma (PAS) is an extremely rare tumour, preferably treated by surgery. However, the surgical management remains largely debatable as only less than half of patients with PAS can undergo thorough excision. Case summary A 32-year-old man with a tumour involving the right ventricle outflow tract, pulmonary trunk extending into the bifurcation, and right pulmonary arteries underwent complete resection using a homologous pulmonary valve and vascular grafts for reconstruction, combined with right pulmonary endarterectomy (PEA) for potential seeding metastasis. Histopathological examination demonstrated undifferentiated pleomorphic sarcoma with surgical margins free of disease. The patient remains asymptomatic, and follow-up computed tomography five months after surgery indicated no recurrence or metastasis. Discussion Radical resection of a PAS with reconstruction using pulmonary valve allograft and polytetrafluoroethylene vascular grafts is technically feasible and successful. Additionally, PEA may eliminate the potential intima implantation metastasis.